Fact-checked by Grok 2 weeks ago

Quality of experience

Quality of experience (QoE) is the degree of delight or annoyance experienced by an when interacting with an application or service, arising from the fulfillment—or lack thereof—of their expectations regarding its utility, enjoyment, and performance in light of personal traits and situational context. Distinct from (QoS), which quantifies objective network parameters like , , and , QoE emphasizes subjective human perception, integrating influences from content characteristics, system impairments, user demographics, and environmental factors to determine overall acceptability. QoE assessment typically employs subjective methods, such as user ratings via mean opinion scores () in controlled experiments, alongside objective models that predict perceptions from measurable inputs like video bitrate or delay, though these models often struggle with inter-user variability and real-world dynamics. In practice, QoE drives optimization in domains including video streaming, where buffering events degrade satisfaction, and emerging technologies like or applications, where immersion and responsiveness critically affect user retention. Challenges in QoE include its inherent subjectivity, complicating scalable, measurement and , as well as pitfalls in predictive modeling for adaptive systems, such as over-reliance on averaged data that masks individual differences or contextual shifts. Despite these, empirical studies underscore QoE's causal link to service , with degradations in perceived quality directly correlating to churn rates in delivery.

Historical Development

Origins and Early Concepts

The evaluation of user-perceived in communications traces its roots to early 20th-century research, where assessments focused on technical factors like delays and their impact on flow, as documented in reports from 1914. By 1948, analyses began explicitly connecting objective technical parameters to subjective user appreciation of service reliability and clarity, marking an initial recognition of perceptual elements in assessment. The modern concept of Quality of Experience (QoE) emerged in the late 1990s amid the transition from circuit-switched to packet-based networks, driven by the need to address limitations of purely technical (QoS) metrics in capturing end-user satisfaction. Early formulations emphasized subjective user perceptions over network-layer parameters; for instance, a 2000 study by Bouch et al. examined download times from a user perspective, highlighting how response delays affected perceived acceptability and prefiguring QoE's focus on experiential outcomes. This period saw the term "Quality of Experience" gain traction in technical literature, initially in philosophical and psychological contexts before 1990 but increasingly in engineering discussions on and services thereafter. Key early definitions crystallized in the early 2000s, with Siller and Woods in 2003 articulating QoE as the cumulative effect on end-users' perceptions shaped by application-layer influences, content characteristics, and network conditions, distinct from lower-level QoS indicators. Concurrent work by Brooks, Hestnes, and colleagues in 2003 explored QoE in person-to-person communication, deriving user-based metrics to map subjective ratings onto technical QoS parameters for practical network optimization. These concepts built on human-computer interaction (HCI) foundations, such as cognitive modeling from , , and Newell's 1983 framework, which linked task performance to perceptual efficiency, influencing QoE's integration of psychological factors. By 2007, the (ITU) formalized QoE in Recommendation P.10/G.100 as "the overall acceptability of an application or service, as perceived subjectively by the end-user," establishing a standardized for subsequent research.

Evolution in Telecommunications and Multimedia

The concept of quality assessment in originated with subjective evaluation methods for voice transmission, formalized in ITU-T Recommendation P.800 (August 1996), which introduced the (MOS) scale for rating perceived audio quality on a 1-5 scale through listener panels. This approach addressed end-to-end experience in circuit-switched public switched telephone networks (PSTN), where factors like delay and were empirically linked to user satisfaction via controlled testing. With the transition to packet-switched IP networks in the late 1990s, particularly for (VoIP), limitations of objective (QoS) metrics—such as and —prompted a shift toward holistic user-centric measures, leading to the emergence of the "Quality of Experience" (QoE) term around 2000-2005 to capture subjective satisfaction beyond network parameters. formalized QoE in Recommendation P.10 Amendment 1 (2007), defining it in Appendix I as "the overall acceptability of an application or service, as perceived subjectively by the end-user." In telecom, this evolution supported mobile and broadband services, with Technical Report 102 643 (November 2009) extending QoE frameworks to include subjective testing for IP-based , emphasizing influences like content and device variability. In multimedia domains, QoE assessment advanced with the proliferation of adaptive streaming over IP, driven by services like Netflix's launch of video streaming in 2007, necessitating models for video quality under variable bandwidth. Recommendation P.1203 (December 2016) marked a by providing , bitstream-based algorithms for estimating QoE in HTTP adaptive streaming (HAS), integrating audiovisual scores from short-term video/audio modules to predict MOS-like ratings without full decoding, validated against subjective datasets. This standard addressed causal factors like stalling and bitrate switches, reflecting empirical correlations from lab studies showing rebuffering events reduce perceived quality by up to 30% in 10-30 second clips. Subsequent updates, such as P.1203.3 (2019), incorporated higher resolutions up to , aligning with deployments where multimedia traffic exceeded 70% of mobile data by 2020. These developments underscore a progression from telecom's voice-focused, lab-based subjectivity to multimedia's scalable, objective-parametric hybrids, enabling optimization in diverse ecosystems while grounding evaluations in verifiable trials rather than isolated proxies.

Core Definitions and Concepts

Formal Definitions from Standards Bodies

The Telecommunication Standardization Sector () formally defines Quality of Experience (QoE) in Recommendation P.10/G.100 (with amendments including those from 2006 onward, latest edition incorporating updates as of September 2024) as "the degree of delight or annoyance of the of an application or ." This definition captures the holistic, end-to-end impact on perception, extending beyond isolated parameters to include , , and usage , as elaborated in related recommendations like G.1033 (2019). The (ETSI) offers a complementary in TR 102 643 (version 1.0.1, 2009), stating that QoE represents the "overall acceptability of an application or service, as perceived subjectively by the end-user." ETSI emphasizes subjective end-user judgment while acknowledging alignment with ITU frameworks, noting that QoE measurement integrates human factors alongside system performance. In ETSI TS 102 250-1, QoE further incorporates the user's role in evaluating total quality, distinguishing it from purely objective metrics by including personal involvement in the assessment process. Other standards bodies, such as ISO/IEC, do not provide a standalone formal definition of QoE but reference it in contexts like media coding (e.g., ISO/IEC 23001-11:2019 and 2023 editions) as a perceptual outcome influenced by energy-efficient delivery without compromising user satisfaction. These organizations often defer to for core QoE conceptualization in and applications. Quality of Experience (QoE) is fundamentally subjective, encompassing the end-user's overall perception of acceptability, delight, or annoyance derived from interacting with a service or application, in contrast to objective metrics like Quality of Service (QoS), which quantify technical parameters such as packet loss, latency, jitter, and throughput without regard to human perception. While QoS focuses on network-level performance guarantees to ensure reliable data transmission, QoE integrates these factors with psychological, contextual, and content-related influences that affect user satisfaction, often resulting in non-linear mappings where minor QoS degradations can cause disproportionate QoE drops. QoE also diverges from broader (UX) metrics, which emphasize interface design, usability, and long-term interaction patterns across products, whereas QoE is more narrowly rooted in and service delivery, prioritizing end-to-end system effects like playback smoothness in video streaming over aesthetic or navigational elements. Unlike UX frameworks that may incorporate qualitative feedback on aesthetics or personalization, QoE metrics, as standardized by bodies like , stress measurable perceptual quality influenced by service impairments, such as buffering delays in IPTV, which can be assessed via subjective scales like (MOS) but remain distinct from UX's focus on holistic product engagement. Further distinctions arise with metrics like user satisfaction scores in customer service contexts, which capture post-interaction on support resolution rather than perceptual during service consumption; QoE, by comparison, evaluates ongoing experiential during active use, such as voice call clarity or web page load times, incorporating both functional performance and emotional response without conflating it with transactional outcomes. This separation ensures QoE's applicability in optimizing -specific parameters, avoiding overgeneralization from UX's design-centric or satisfaction's outcome-based approaches.

Influencing Factors

Technical and Network Factors

Technical and network factors influencing quality of experience (QoE) primarily involve transmission impairments that disrupt the temporal and spatial integrity of media signals, such as in video streaming, VoIP, and real-time communications. These include bandwidth limitations, end-to-end latency, jitter (packet delay variation), and packet loss rates, which correlate with perceptual degradations like rebuffering events, audio/video artifacts, and issues. Standards bodies like the quantify their impacts through models that map objective parameters to subjective QoE scores, emphasizing causal links between network conditions and user-perceived acceptability. Bandwidth, or available throughput, determines the sustainable data rate for media encoding and delivery; insufficient levels force bitrate reductions or adaptive streaming downshifts, leading to lower resolution and increased compression artifacts that diminish visual fidelity. In video streaming, studies show that throughput below 2 Mbps for HD content results in frequent quality switches, reducing mean opinion scores (MOS) by up to 1.5 points on a 5-point scale. Packet loss, occurring when data packets fail to reach the receiver (e.g., due to congestion or errors), introduces visible impairments like frame freezing or macroblocking in compressed video, with loss rates exceeding 1% causing MOS drops of 20-30% in subjective tests for H.265/HEVC streams. ITU-T P.940 models incorporate a network impairment factor specifically for video packet loss, predicting compounded effects with encoding parameters. Latency, the one-way propagation delay, accumulates from encoding, , and decoding stages, impairing in bidirectional services; G.114 recommends keeping mouth-to-ear delays under 150 ms for satisfactory conversational QoE in , as higher values introduce unnatural pauses and turn-taking difficulties. exacerbates this by varying inter-packet arrival times, necessitating larger playout s that inflate effective delay and cause choppy playback if unmitigated; thresholds above 20 ms degrade audio/video smoothness, with empirical studies on applications showing it amplifies QoE penalties when combined with loss rates over 0.5%. In controlled experiments, 's variability proves more disruptive to video than constant alone, as it triggers adaptive buffer adjustments that users perceive as inconsistent .

Human Perception and Psychological Factors

Human perception of quality in multimedia and telecommunications services integrates sensory detection of signal attributes with cognitive interpretation, often diverging from objective metrics due to thresholds like just-noticeable differences in distortion or latency. Visual and auditory acuity determine baseline sensitivity to impairments; for instance, reduced contrast sensitivity in older adults amplifies perceived video degradation compared to younger viewers. Gender differences also modulate perception, with studies indicating females report higher annoyance from audio-visual asynchrony in immersive media than males. These low-level sensory variations underscore why QoE models incorporate human influence factors alongside system parameters. Psychological factors further shape QoE through higher-level processing, including expectations derived from prior exposures—the ""—where users benchmark current service against remembered highs, lowering satisfaction if unmet. Mood and emotional state exert causal influence; negative affect heightens intolerance for delays or artifacts, as evidenced in media sessions where user delight correlates inversely with perceived impairments. compounds this, elevating listening effort and diminishing tolerance for suboptimal audio in prolonged sessions. Cognitive styles, such as field-dependence, affect holistic judgments, with field-dependent individuals prioritizing contextual coherence over isolated flaws. Individual traits like and prior computing experience introduce variability; extroverted users may derive higher enjoyment from interactive despite technical flaws, while technical novices amplify dissatisfaction from hurdles. Socio-cultural and educational backgrounds modulate these effects, with linked to nuanced detection of subtle degradations in web-browsing QoE. Empirical assessments confirm age-related declines in perceptual acuity exacerbate QoE drops in dynamic content like 360° video, where older participants exhibit greater sensitivity to motion artifacts. These factors necessitate personalized modeling in QoE prediction to align with causal perceptual realities rather than averaged population norms.

Environmental and Contextual Factors

Environmental factors, including ambient lighting and noise, modulate the perceptual quality of multimedia services by interacting with sensory processing. Research indicates that elevated ambient noise levels impair audio-visual QoE, as background interference masks content signals and increases cognitive load during video consumption on devices like televisions. Similarly, suboptimal lighting conditions, such as excessive glare or dim illumination, degrade visual acuity and color perception, leading to reduced acceptability ratings in subjective tests for video playback. These effects stem from physiological limits in human vision and audition, where environmental mismatches amplify distortions that would otherwise be tolerable in controlled lab settings. Contextual factors encompass situational variables like user , , session duration, and economic costs, which shape expectations and thresholds. For example, mobile usage in dynamic environments, such as , heightens sensitivity to due to divided and motion-induced artifacts, lowering overall QoE compared to viewing. Recommendation G.1035 identifies session duration as a key contextual influencer, noting that prolonged exposure to impairments accumulates dissatisfaction, with QoE declining nonlinearly over time in voice and video services. Costs associated with usage further contextualize , as metered prompts conservative and heightened scrutiny of drops. Social context introduces interpersonal dynamics that alter QoE through emotional and attentional mechanisms. Studies on video streaming reveal that solitary viewing yields higher QoE scores for equivalent quality than group settings, where observers induce or conversational interruptions. In multiplayer , social presence—such as competing with friends versus strangers—mitigates from delays, with participants reporting up to 20% higher acceptability when socially engaged, per controlled experiments. These variances highlight how relational factors override isolated metrics, emphasizing the need for context-aware models in .

Comparisons with Analogous Concepts

QoE versus Quality of Service (QoS)

Quality of Service (QoS) encompasses the measurable technical attributes of a or delivery, including parameters like , , rate, and throughput, which are objectively quantifiable and engineered to meet performance standards. ITU-T Recommendation E.800 (2008) defines QoS as "the collective effect of performance which determines the degree of satisfaction of a user of the ," though in practice, it prioritizes network-centric metrics over subjective elements. These attributes are typically monitored and controlled at the infrastructure level to ensure reliable transmission, as seen in protocols like DiffServ or MPLS that prioritize traffic classes based on delay budgets under 150 ms for voice services. Quality of Experience (QoE), by comparison, evaluates the end-user's overall subjective perception of acceptability, integrating QoS influences with non-technical factors such as content quality, device usability, environmental context, and personal expectations. Recommendation P.10/G.100 (2017) specifies QoE as "the degree of delight or annoyance of the user of an application or service," further noting its dependence on complete end-to-end effects beyond mere transmission. Unlike QoS, which can be assured through provisioning, QoE requires subjective assessments like (MOS) ratings on a 1-5 scale, where scores below 3.5 often indicate frustration in video streaming despite adequate bandwidth. While QoS forms a foundational input to QoE—evidenced by studies showing non-linear mappings where QoE drops exponentially with increasing beyond 1%—the two diverge in that high QoS does not guarantee high QoE, as user and can override technical fidelity. For example, parametric models like those in ITU-T G.107 (2015) predict voice QoE from QoS via the E-model formula R = 94.2 - I_e/effective, where network impairments reduce perceived quality independently of content appeal. This distinction underscores QoE's broader scope, demanding holistic optimization rather than isolated network tuning, with empirical data from telecom deployments revealing up to 30% QoE variance attributable to non-QoS factors like buffering tolerance.

QoE versus User Experience (UX)

Quality of Experience (QoE) refers to the overall acceptability of an application or service as perceived subjectively by the end-user, particularly in the delivery of content over networks, where factors such as video , audio clarity, and impairments directly influence . This originated in , emphasizing the of on user satisfaction during content consumption. In contrast, (UX) encompasses a person's perceptions, emotions, beliefs, preferences, and responses arising from the use or anticipated use of a product, system, or service throughout its lifecycle, as defined in ISO 9241-210. Rooted in human-computer interaction (HCI) principles, UX focuses on aspects like interface usability, aesthetic design, task efficiency, and emotional engagement, often evaluated independently of underlying network infrastructure. For instance, UX assessments typically employ tools such as the (SUS) to measure learnability and error recovery in software interfaces. The primary distinction lies in scope and context: QoE is tightly coupled to networked service delivery, where technical parameters like (e.g., delays exceeding 150 ms in video streaming) or rates above 1% can degrade perceived quality, as quantified through (MOS) scales in studies. UX, however, prioritizes elements, such as intuitive navigation or , which may remain unaffected by network variability; a well-designed can yield high UX scores even with suboptimal connectivity. Overlaps occur in integrated systems like streaming platforms, where buffering-induced frustration (a QoE impairment) can compound poor responsiveness (a UX deficit), but QoE models often treat UX as a modulating factor rather than the core focus. This separation underscores QoE's emphasis on end-to-end service acceptability in , versus UX's broader application to standalone product interactions.

Measurement and Assessment

Subjective Evaluation Techniques

Subjective evaluation techniques for quality of experience (QoE) involve human participants rating the perceived acceptability of media or services under controlled conditions, providing a direct measure of end-user satisfaction. These methods, standardized by the (), aggregate individual opinions into metrics like the (), which quantifies overall quality on a five-point scale where 1 indicates "bad," 3 "fair," and 5 "excellent." Experiments typically require 15 to 24 screened subjects per condition to ensure statistical reliability, with ratings collected post-exposure to avoid bias. The Absolute Category (ACR) method presents stimuli independently for rating without reference, yielding MOS values that reflect absolute perceived quality; it is widely used for audio and video QoE due to its simplicity but can overlook subtle . In contrast, Degradation Category (DCR) assesses severity relative to a pristine reference on a five-point (e.g., 5 for "imperceptible" to 1 for "very annoying"), enhancing to differences in high-quality scenarios like streaming services. Comparison Category (CCR) evaluates paired stimuli, rating one as better, worse, or the same, which supports differential analysis but demands more test time. These techniques apply across domains: P.800 specifies ACR for speech transmission QoE, while P.910 extends non-interactive methods to video, including immersive formats. For , P.809 outlines tailored subjective tests focusing on interactivity and immersion. Limitations include subjectivity variability, addressed via subject training and outlier rejection, and scalability challenges for real-time services, prompting hybrid approaches. Empirical data from such tests correlate with user retention; for instance, scores below 3.5 often predict abandonment in VoIP calls.

Objective Modeling and Prediction

Objective modeling and prediction of Quality of Experience (QoE) involves algorithmic techniques that estimate perceived quality from measurable parameters, such as network , rates, bitrate variations, and content , without requiring direct user input. These methods enable proactive monitoring and optimization in systems like video streaming, where subjective assessments are impractical due to scale. models, a core subset, apply mathematical functions to map (QoS) metrics to QoE scores; for example, exponential decay functions often quantify the impact of rebuffering events, with each second of stall reducing perceived quality by up to 20-30% in adaptive streaming scenarios. Such models, standardized in P.1203 for multimedia services, achieve prediction accuracies correlating 0.8-0.9 with mean opinion scores () in validation datasets comprising thousands of test conditions. Bitstream-embedded and signal-based objective models extend parametric approaches by analyzing partial or full media content. Full-reference metrics, like (PSNR) or structural similarity index (SSIM), compare original and degraded signals to predict visual quality, yielding correlations exceeding 0.85 with subjective ratings for compressed videos up to . Reduced-reference variants transmit lightweight features (e.g., histograms) alongside the stream for , while no-reference models infer degradations solely from the received signal, using techniques like natural scene statistics to detect artifacts. In packet-switched networks, these models incorporate temporal factors, such as frame freezing duration, with empirical studies showing jitter above 30 ms correlating to QoE drops of 1-2 points on a 5-point . Machine learning-driven predictions have advanced objective QoE estimation by learning complex, nonlinear mappings from large datasets of QoS-QoE pairs. Supervised algorithms, including support vector and random forests, trained on features like throughput variability and encoding parameters, report Pearson correlations of 0.90+ against in cross-dataset evaluations for HTTP adaptive streaming. Deep learning variants, such as convolutional neural networks combined with gated recurrent units, process spatiotemporal features for immersive content, achieving 92% accuracy in binary QoE classification (acceptable vs. unacceptable) across 150 distorted video sequences. Hybrid frameworks integrate network-layer data with application metrics, as in open-source tools using on encrypted traffic, enabling real-time estimation with latencies under 100 ms. Despite these advances, objective models face challenges in context generalization; for instance, parameters tuned for conditions may underperform in field trials by 10-15% due to unmodeled variables like variability or habits. Validation against diverse subjective corpora, often involving 50-200 participants per condition, is standard to mitigate , with ongoing research emphasizing for emerging applications like .

Hybrid and Data-Driven Approaches

Hybrid approaches to QoE assessment combine subjective user evaluations, such as Mean Opinion Scores (MOS), with objective metrics like (PSNR) or network parameters to balance perceptual accuracy and computational efficiency. Subjective methods provide ground-truth human judgments but suffer from high variability and cost, while objective models enable real-time prediction yet often fail to fully capture contextual influences; hybrids address this by establishing parametric mappings between the two, as demonstrated in video streaming evaluations where hybrid techniques correlate user ratings with impairments like buffering and bitrate fluctuations. In web-based services, hybrid frameworks aggregate subjective ratings directly from users with objective data logged during sessions, such as page load times and error rates, to derive a composite QoE score that informs service improvements. For multi-view video compression, a time-efficient method merges double-stimulus continuous scale (DSCQS) for subjective with automated scoring, reducing evaluation time while maintaining with perceptual . Data-driven methods employ to predict QoE from large datasets of labeled subjective outcomes paired with features like delay, , , throughput, and bitrate, enabling scalable inference without ongoing human testing. A model trained on over 20,000 records of network parameters, compliant with P.1203, predicts with 95.8% accuracy, supporting real-time monitoring in multimedia networks by automating data ingestion and focusing solely on observable impairments. Advanced hybrid data-driven models integrate ensemble techniques, such as two-level stacking with meta-learners, to refine predictions for video services over ; these outperform single models by 4-5% in accuracy when evaluating against combined network and video quality parameters, facilitating proactive QoE optimization. Such approaches handle imbalanced datasets common in QoE studies—where high-quality experiences dominate—through techniques like or algorithmic adjustments, as reviewed in analyses of evaluation factors including user behavior and content type.

Management and Optimization

Strategies at the Network Layer

Strategies at the network layer target impairments such as packet delay, , and loss, which directly degrade perceived in applications like video streaming and communication. These approaches leverage IP-level mechanisms to prioritize QoE-sensitive traffic over best-effort flows, often integrating with higher-layer feedback for dynamic adjustments. Unlike application-specific adaptations, network-layer interventions operate transparently across diverse services, focusing on and path optimization to sustain throughput and reduce variability. Quality of Service (QoS) provisioning forms a foundational strategy, employing techniques like traffic , marking, and scheduling to differentiate flows based on sensitivity to delay or . (DiffServ) aggregates packets into classes via Differentiated Services Code Point (DSCP) markings, enabling expedited forwarding for low-latency needs, as demonstrated in evaluations showing reduced for VoIP traffic in congested IP networks. (IntServ) complements this with per-flow resource reservation using protocols like (RSVP), reserving to prevent admission of excess flows that could drop QoE below thresholds, though scalability limits its use to smaller domains. Congestion control enhancements adapt algorithms to QoE metrics rather than pure throughput, such as adjusting congestion windows based on () predictions to balance utilization and impairment. In cellular environments, feedback-driven methods like those using first-delivery-time and receiving rate mitigate by modulating sending rates, achieving up to 20% QoE gains in real-time video over variable links. Machine learning-augmented controls, decoupled from traditional signals, statistically allocate bandwidth to favor high-QoE sessions, as in systems optimizing for conversational services where delay spikes correlate with 15-30% drops. Traffic engineering optimizes routing and load distribution to preempt bottlenecks, using (MPLS) for explicit path selection that minimizes in IP backbones. Dynamic path computation based on real-time link states reduces by 10-25% in multimedia flows, per simulations in service-oriented networks. (SDN) enables centralized QoE-aware policies, such as flow rerouting to underutilized paths, improving video session stability without per-client overhead. These strategies, when combined, yield measurable QoE uplifts, with studies reporting 3-38% improvements in adaptive streaming scenarios through coordinated and delay management.

Application and Service-Level Interventions

Application-level interventions for Quality of Experience (QoE) focus on adaptations within software applications and service architectures to mitigate impairments arising from content delivery, rendering, or user interaction, independent of underlying network conditions. Techniques such as adaptive streaming protocols, exemplified by (DASH), dynamically adjust video bitrate based on buffer status and device capabilities, reducing rebuffering events that degrade perceived quality. A 2018 study on DASH implementations reported a 20-30% improvement in QoE scores for video-on-demand services by minimizing stalls, as measured via (MOS) ratings from user trials. Service-level strategies often involve server-side optimizations, including content-aware and prefetching mechanisms, to align delivery with user preferences and device heterogeneity. For instance, Netflix's perceptual video coding employs models to optimize encoding parameters, preserving visual fidelity while compressing data by up to 25% compared to traditional methods, as validated in their 2020 engineering reports correlating reduced bitrate with maintained above 4.0 on a 5-point scale. Similarly, caching hierarchies at content delivery networks (CDNs) like Akamai's reduce for frequently accessed assets, with empirical data from a 2022 analysis showing latency reductions of 40-60 ms yielding QoE uplifts in interactive services like online gaming. Personalization at the enhances QoE by tailoring experiences to individual contexts, such as recommendation algorithms that prioritize high-quality streams or adjustments for . YouTube's 2021 updates to its incorporated viewport-dependent rendering for devices, focusing encoding resources on the viewed portion of 360-degree videos, which improved subjective quality ratings by 15% in controlled experiments. However, these interventions must account for trade-offs; over-aggressive adaptation can introduce artifacts like temporal inconsistencies, as noted in recommendations P.1203, where model predictions highlight a 10-15% QoE penalty from mismatched frame rates. Hybrid service models integrate feedback loops, such as crowdsourced QoE monitoring via apps like Speedtest by Ookla, to iteratively refine delivery policies. A 2023 deployment in services demonstrated that real-time user telemetry-driven adjustments cut perceived input lag by 50 ms on average, boosting satisfaction metrics in large-scale user studies. Despite efficacy, implementation challenges include computational overhead; service providers report up to 15% increases in server load from QoE-centric optimizations, necessitating scalable architectures.

Role of AI and Automation in QoE Enhancement

() and automation play pivotal roles in enhancing Quality of Experience (QoE) by enabling , dynamic , and adaptive optimization in systems such as video streaming and mobile networks. models, including deep neural networks, map objective metrics like bitrate, , and to subjective QoE scores, achieving prediction accuracies up to 92.59% in ensemble classifiers for multimedia services. For example, hybrid convolutional neural network-long architectures predict QoE in video playback by analyzing network fluctuations, allowing preemptive adjustments to maintain user satisfaction. Deep reinforcement learning (DRL) automates resource management to directly optimize QoE, treating network decisions as sequential actions in an where rewards are tied to user-perceived quality. In 5G heterogeneous networks, DRL-based strategies allocate and compute resources dynamically, outperforming traditional heuristics by reducing rebuffering events and improving video quality metrics in simulations conducted as of February 2025. Similarly, DRL-integrated selection combines QoS parameters with QoE feedback, adapting to varying loads in environments as tested in July 2025 frameworks. Automation extends to self-organizing networks and intent-based , where processes vast datasets for and QoE-aware slicing in O-RAN architectures. Genetic algorithms adapted for QoE-driven video service enhancement in setups automate user association and resource scheduling, yielding measurable gains in mean opinion scores during peak loads. Interpretable models like Takagi-Sugeno-Kang adaptive networks further support by providing transparent QoE predictions over varying protocols, facilitating verifiable deployment in production streaming systems as of September 2025. These tools shift QoE management from reactive to proactive paradigms, leveraging causal links between system states and experiential outcomes for scalable improvements.

Applications and Case Studies

QoE in 5G Networks and Mobile Services

In networks, Quality of Experience (QoE) encompasses user-perceived with services, influenced by factors such as latency, throughput, reliability, and application-specific performance, extending beyond traditional (QoS) parameters to include subjective elements like content rendering and interactivity. specifications in Release 17 introduced mechanisms for collecting application-layer QoE measurements, such as average throughput, initial playout delay, and buffer levels, enabling operators to monitor and optimize services like video streaming and (VR) across slices and (RAN) visibility. These enhancements support diverse use cases, including enhanced (eMBB) for high-definition streaming and ultra-reliable low-latency communication (URLLC) for mission-critical applications, where QoE directly correlates with efficiency and user retention. Compared to networks, delivers measurable QoE gains through targeted performance targets: end-to-end reduced to 1 ms or less (versus 25 ms in ), peak throughput exceeding 10 Gbps (versus hundreds of Mbps in ), and reliability up to 99.999% within latency budgets, as defined in M.2410 and Release 16. These metrics enable seamless experiences in services, such as holographic communications requiring 7 Gbps throughput or remote with sub-millisecond delays, reducing user frustration from buffering or disconnects observed in prior generations. Empirical deployments confirm these benefits; for instance, commercial networks exhibit improved power efficiency and QoE in heterogeneous environments, though variability arises from spectrum allocation and device capabilities. QoE optimization in 5G mobile services relies on dynamic and network slicing, where operators prioritize traffic via 5QI (5G QoS Identifier) mappings to sustain high user satisfaction under load. In video streaming case studies using scalable H.265 encoding over testbeds, QoE models based on congestion index (maximum required divided by available , ranging 1.0–1.8) predict Mean Opinion Scores () with 94% accuracy against subjective evaluations from over 2,300 data points across 64 participants, showing minimal degradation when dropping resolution layers (e.g., to Full MOS of 4.24 vs. 4.21 at low congestion). access (FWA) deployments, as analyzed in 2023 industry reports, leverage 's high throughput to provide alternatives with QoE comparable to , expanding access in underserved areas while maintaining low for streaming and .
Key 5G MetricTarget ValueQoE Impact in Mobile Services
Latency≤1 ms (URLLC: 0.5 ms)Enables responsive AR/ and control, reducing perceived delays in interactive apps.
Throughput1–10 GbpsSupports UHD streaming without interruptions, enhancing satisfaction in bandwidth-intensive services.
Reliability99.999%Ensures consistent performance for VoIP and , minimizing dropouts in urban mobility scenarios.
Despite advancements, challenges persist in maintaining QoE during handovers in heterogeneous networks, where frequent cell transitions can introduce affecting streaming continuity, necessitating AI-driven predictive algorithms for mitigation. Release 18 extensions for multicast/broadcast services () further refine QoE reporting across device states (CONNECTED, INACTIVE, ), but empirical limitations in subjective models highlight the need for hybrid approaches integrating real-user feedback with objective predictions.

QoE in Virtual Reality and Immersive Experiences

In (VR) and immersive experiences, quality of experience (QoE) extends beyond traditional audiovisual fidelity to encompass psychological , known as presence—the sensation of being physically located within the —and the absence of adverse physiological effects such as cybersickness, which manifests as , disorientation, and oculomotor discomfort. Empirical assessments reveal that presence correlates negatively with cybersickness severity; optimized VR systems achieving high presence (e.g., via accurate motion and wide field-of-view rendering) typically reduce sickness incidence, though individual susceptibility varies, with studies reporting symptom onset in 20-80% of users depending on exposure duration and content velocity. Presence is quantified using validated scales like the Igroup Presence Questionnaire (IPQ), where scores above 4.0 on a 7-point indicate strong , directly linking to overall QoE satisfaction in tasks like or social interaction. Technical parameters profoundly influence VR QoE, with network latency emerging as a primary disruptor in interactive scenarios. Controlled experiments demonstrate that end-to-end latencies exceeding 50-100 ms degrade task performance by 15-30% in collaborative environments, eliciting frustration and reduced mutual understanding among users, as measured by subjective ratings on 5-point QoE scales dropping below acceptable thresholds (e.g., mean scores <3.5). Video quality factors, including resolution (e.g., 4K per eye) and frame rates above 90 Hz, enhance perceptual realism and presence, with subjective studies showing a 20-40% QoE uplift when bitrate exceeds 50 Mbps for 360-degree content, though diminishing returns occur beyond perceptual limits. In immersive telepresence applications, such as holographic , additional degradations from compression artifacts further erode QoE, prompting hybrid metrics combining objective bitrate with subjective acceptability scores. Cybersickness poses a persistent barrier, often exacerbated by sensory mismatches between visual cues and vestibular inputs; post-exposure Simulator Sickness Questionnaire (SSQ) scores rise proportionally with vection-inducing motions, correlating with a 10-25% QoE decrement in prolonged sessions (>15 minutes). Mitigation strategies, validated in empirical trials, include field-of-view adjustments (e.g., reducing to 90-110 degrees) and adaptive refresh rates, which lower SSQ totals by up to 30% without sacrificing presence. For multi-user immersive experiences, social context modulates tolerance: group interactions buffer latency-induced dissatisfaction, with QoE ratings improving by 15% in co-located versus remote setups under equivalent network conditions. Recent physiological QoE models integrate EEG and to predict sickness onset in , enabling proactive interventions like content pausing, though challenges persist due to inter-subject variability. Assessment in VR demands multimodal approaches, blending subjective self-reports with objective proxies; for instance, eye-tracking data reveals fixation stability as a correlate of presence (r=0.65), while network-emulated studies on cloud-based confirm rates >1% amplify cybersickness by disrupting motion rendering. In emerging 6DoF () immersive systems, accurate head and hand tracking fidelity—achieving <20 ms motion-to-photon —yields QoE scores 25% higher than 3DoF counterparts, underscoring the causal role of spatiotemporal consistency in user engagement. Limitations include in deployments, where variability introduces , yet edge-computing optimizations have demonstrated 40% reductions in field trials, enhancing QoE for mobile .

QoE in Real-Time Communication and Streaming

In real-time communication () applications, such as VoIP and WebRTC-based videoconferencing, QoE is predominantly determined by network impairments that disrupt conversational flow and media fidelity. End-to-end latency below 150 milliseconds one-way is essential to maintain natural interactivity, as higher delays introduce perceptible lag that lowers (MOS) ratings. , the variation in packet delay, should remain under 30 milliseconds to prevent audio choppiness or video , while rates exceeding 1% cause audible artifacts or frame drops, compounding dissatisfaction in subjective assessments. These factors are modeled in frameworks like recommendations, where combined impairments yield non-linear QoE degradation, emphasizing causal links from packet-level issues to perceptual annoyance. Video streaming, including live broadcasts and services, prioritizes seamless playback over strict synchrony, with QoE hinging on rebuffering events, bitrate , and initial startup delay. Adaptive bitrate (ABR) algorithms dynamically scale video to throughput, but frequent quality switches or stalls erode ; for instance, a 1% rise in rebuffering can diminish user by over three minutes in a 90-minute live session. buffer dynamics directly influence stalling probability, where insufficient prefetching amplifies QoE penalties from variable bandwidth, as quantified in P.1203 models that predict per-segment from bitrate, stalling duration, and encoding artifacts. Empirical data from large-scale events reveal that undetected buffering impairments correlate with abrupt viewer drop-offs, underscoring the need for proactive monitoring. Optimization in both domains leverages QoS mappings to QoE predictors, such as for RTC packet recovery and buffer-occupancy heuristics in ABR to preempt stalls, reducing rebuffering by 10-20% in controlled tests. Machine learning frameworks, trained on network KPIs like delay and throughput, achieve over 95% accuracy in MOS forecasting for multimedia, enabling real-time adaptations without intrusive probing. Challenges arise in heterogeneous environments, where WebRTC studies show impairments interact multiplicatively—e.g., exacerbates effects—demanding hybrid objective-subjective validation to avoid over-reliance on isolated metrics.

Challenges, Criticisms, and Limitations

Issues with Subjectivity and Reproducibility

Subjective assessments of Quality of Experience (QoE) inherently depend on individual user perceptions, which are influenced by factors such as personal background, emotional state, expectations, and contextual variables, resulting in high variability across participants for identical stimuli. This variability manifests in subjective rating scales, where inter-subject differences can lead to standard deviations of 1-2 points on common 5-point () metrics, complicating aggregation into reliable averages. Unlike objective (QoS) parameters—such as rates or throughput, which remain consistent under controlled conditions—QoE eludes standardization due to its reliance on human judgment, often requiring large participant pools (typically 20-40 per guidelines) to mitigate but not eliminate inconsistencies. Reproducibility in QoE research is further undermined by the obtrusive nature of laboratory-based subjective tests, which isolate users from natural usage contexts like distractions or device mobility, yielding results that poorly generalize to real-world deployments. Systematic reviews of ecologically valid user studies from 2011 to 2021 highlight persistent methodological gaps, including inconsistent stimulus presentation protocols and insufficient control for confounding variables like or learning effects, which erode the ability to replicate findings across experiments. For instance, subjective QoE evaluations in video streaming often fail to reproduce due to unaccounted demographic diversities, with studies reporting coefficients between repeated sessions as low as 0.6-0.8, indicating moderate but unreliable consistency. Efforts to address these issues through hybrid objective-subjective models or no-reference metrics aim to approximate QoE without full user involvement, yet they struggle with validation against subjective , perpetuating debates on their . Longitudinal field studies exacerbate challenges, as temporal factors like evolving user tolerance or conditions introduce uncontrolled variance, often rendering datasets non-shareable for machine learning-based QoE prediction due to and heterogeneity concerns. Despite recommendations for standardized subjective methodologies, such as double-stimulus comparisons, inherent human perceptual biases— including anchoring and order effects—persist, underscoring the causal disconnect between isolated metrics and holistic experience.

Economic and Scalability Constraints

Implementing comprehensive Quality of Experience (QoE) management systems in networks incurs substantial economic burdens, primarily from the high initial investments required for advanced infrastructures such as (SDN) and (NFV), which, despite enabling long-term cost reductions in service deployment, demand significant upfront capital for integration and upgrades. QoE monitoring and personalized optimization further elevate operational expenses through continuous and adaptive resource allocation, particularly for value-added services like and / (AR/VR) applications. Additionally, hardware upgrades, such as replacing millions of (CPE) units with monitoring-capable devices, impose direct financial strain on internet service providers (ISPs), often necessitating shifts to subscription-based models that disrupt traditional vendor economics. Scalability constraints exacerbate these economic challenges in large-scale deployments, where traditional QoE probing methods suffer from on devices, including CPU, , and limitations that hinder continuous across high-density user bases. In multi-radio access technology (RAT) environments like New Radio (NR) and /7, conventional systems exhibit limited for diverse services, complicating dynamic and increasing computational overhead for tasks such as decoding ultra-high-definition (UHD) video streams or applying (ML) to encrypted . Cloud-based centralized introduces further delays and network overhead in scenarios, while via SDN/NFV, though flexible, requires precise probe placement to manage delay-sensitive without proportional cost escalation. Emerging network-centric approaches mitigate some scalability issues by relying solely on passive network metrics (e.g., delay, , ) for QoE prediction, as demonstrated in ML frameworks like models achieving (MOS) estimation with an R² of 0.968, thereby reducing and enhancing applicability in large-scale networks handling datasets of approximately 22,000 video segments. These methods also preserve data privacy by avoiding application-layer content inspection, indirectly lowering economic risks associated with , though they still demand robust of diverse network conditions for validation. Overall, while such innovations promise cost efficiencies over subjective human assessments, the persistent overhead of multi-modal data generation in edge and cloud environments underscores the need for ongoing trade-offs between QoE granularity and deployment feasibility.

Debates on Over-Reliance on User-Centric Metrics

Critics of user-centric metrics in Quality of Experience (QoE) assessment contend that excessive dependence on subjective measures, such as , obscures critical distributional aspects of user satisfaction, including the proportion of dissatisfied users and rating variability, which a simple average fails to capture. , typically derived from ratings on a 1-5 during controlled subjective tests, aggregates individual opinions into a mean but discards about standard deviations or quantiles, potentially misleading service providers into underestimating churn risks from quality outliers. This limitation arises because human perception varies due to factors like individual biases, , and contextual influences, rendering insufficient for nuanced QoE modeling in diverse deployments. Scalability poses another core criticism, as conducting large-scale subjective experiments demands significant resources for participant recruitment, standardized viewing conditions, and post-processing to mitigate rater inconsistencies, making it impractical for real-time optimization or monitoring millions of users. Subjective tests often involve small sample sizes—frequently under 50 raters per condition per recommendations—which amplify variance and limit generalizability across demographics, devices, or cultural contexts, leading to models that poorly predict QoE in uncontrolled environments. Over-reliance exacerbates this by prioritizing perceived over verifiable parameters like or , which correlate imperfectly with subjective outcomes and enable automated, reproducible assessments essential for scalable systems. Reproducibility challenges further fuel the debate, with subjective metrics susceptible to inter- and intra-rater es, where individual preferences or anchoring effects skew results, as evidenced by studies normalizing scores to remove systematic subject yet still reporting high variability. In video streaming contexts, for instance, reliance on has been critiqued for yielding aggregated scores that mask tail-end degradations, such as rare but severe stalling events disproportionately impacting user retention. Proponents of balanced approaches advocate models integrating no-reference metrics (e.g., derived from bitrate fluctuations) with subjective data to enhance predictive accuracy without the full burden of repeated human trials, arguing that pure user-centric evaluation risks decoupling QoE from causalities like constraints. These concerns have prompted alternatives like quantile-based distributions or psychometric scaling to supplement , aiming to preserve user insights while addressing empirical shortcomings.

Advances in Predictive Analytics and AI Integration

Recent developments in for Quality of Experience (QoE) have increasingly incorporated (ML) and deep learning (DL) techniques to forecast user perceptions from objective (QoS) parameters, enabling proactive network adjustments in real-time delivery. A 2024 study introduced a framework for QoE prediction in services compliant with ITU-T P.1203 standards, utilizing ML algorithms to process features like bitrate variability and , achieving higher fidelity mappings than parametric models by training on diverse datasets of subjective scores. Similarly, a continuous QoS-to-QoE evaluation method proposed in early 2024 employs regression-based ML to correlate network metrics such as and throughput with perceptual quality scores, demonstrating improved prediction accuracy in adaptive streaming scenarios over legacy bitstream models. In video streaming applications, hybrid architectures combining convolutional neural networks (CNNs) with gated recurrent units (GRUs) and attention mechanisms have advanced QoE prediction by capturing spatial-temporal dependencies in video frames and transmission artifacts. Research from October 2025 evaluated such models, reporting superior performance metrics—including up to 15% gains in (MOS) alignment—compared to prior non-hybrid DL approaches, validated through extensive benchmarks on datasets like LIVE-Netflix. Interpretable ML methods, such as the TSKAN model introduced in September 2025, further enhance transparency by applying over raw time-series traffic data, yielding explainable QoE forecasts that outperform black-box neural networks in deployment interpretability for video services. Generative modeling frameworks, exemplified by a lightweight approach from April 2025, balance computational efficiency with predictive precision, generating synthetic QoE distributions from limited telecom data to simulate edge cases, thus reducing training overhead by factors of 5-10 relative to full DL baselines. For emerging and networks, integration emphasizes and adaptive intelligence, with surveys from October 2025 highlighting DL-driven models that dynamically optimize to sustain QoE amid variable loads. These systems leverage classifiers, achieving QoE accuracies exceeding 92% in controlled tests using techniques like ensemble heterogeneous parallel trees (EHPT). Data-driven paradigms, as detailed in a 2024 tutorial, position such as foundational for intent-based networking, where agents predict and mitigate degradations proactively, though challenges persist in generalizing across heterogeneous behaviors and devices. Overall, these advances shift QoE management from reactive monitoring to anticipatory , supported by scalable, high-fidelity models trained on large-scale empirical datasets.

Standardization and Industry Evolutions Post-2023

In 2024, the Study Group 12 advanced QoE evaluation frameworks by publishing Recommendation P.1402, which provides guidance on applying techniques for predicting QoS and QoE in telecommunication networks, enabling more accurate models for network performance management. This builds on prior roadmaps and addresses the integration of AI-driven objective models for emerging services, including speech and audiovisual content. Concurrently, SG12's work program for 2025-2028 emphasizes standardized assessment methods for QoE in applications, prioritizing empirical validation over subjective variability. The Release 18, finalized with normative specifications in the fourth quarter of 2023 and influencing deployments thereafter, introduced enhancements to NR QoE measurement collection, allowing operators to gather application-layer data from for services like video streaming and . These updates support self-organizing networks and management data analytics, with further refinements in Release 19—initiated in the second quarter of 2024—targeting AI/ML integration for NG-RAN to predict and optimize QoE in dynamic environments. For instance, XR-specific enhancements in Releases 18 and 19 focus on reduction and improvements to sustain QoE for multiple users, verified through simulation-based evaluations showing up to 20-30% gains in supported sessions. Industry adaptations post-2023 have emphasized application-level QoE beyond traditional QoS KPIs, as evidenced by the Infra Project's release of a on October 29, 2024, which graduates metaverse-ready initiatives and promotes standardized metrics for immersive services. operators like have leveraged these evolutions for mobile video QoE optimization, reporting improved user retention through standardized models that correlate network parameters with perceptual quality. In , regulatory pushes in September 2024 called for high-QoE networks prioritizing reliable connectivity over mere coverage, influencing metrics like buffering ratios and interactivity latency in deployments. Video streaming sectors observed metric uplifts in 2024, with global VOD quality scores rising due to adaptive bitrate refinements and reduced rebuffering events, per benchmarks. These shifts reflect a causal emphasis on end-user data analytics, mitigating issues in AI-enhanced systems.

References

  1. [1]
    The relation between quality of service and quality of experience
    Aug 25, 2020 · Quality of experience (QoE) is now taken to be “the degree of delight or annoyance of the user of an application or service,” following ITU-T Recommendation P. ...
  2. [2]
    Quality of Experience in Communications Ecosystem
    Two key concepts in this endeavour are quality of service (QoS) and quality of experience (QoE). Traditionally, QoS is used as an acronym primarily in a ...
  3. [3]
    A taxonomy of quality of service and Quality of Experience of ...
    It consists of three layers: (1) The QoS-influencing factors related to the user, the system, and the context of use; (2) the QoS interaction performance ...Missing: key | Show results with:key
  4. [4]
    A survey of quality of experience - ACM Digital Library
    QoE (Quality of Experience) is a "new" terminology introduced to describe this user's perception. It reflects how satisfied/dissatisfied the end users are with ...
  5. [5]
    Quality of Experience for Streaming Services: Measurements ...
    Jan 9, 2020 · In this paper, we present the importance of QoE in wireless and mobile networks (4G, 5G, and beyond), by providing standard definitions and the most important ...
  6. [6]
    Defining Quality of Experience for the Internet of Things - IEEE Xplore
    Sep 10, 2020 · The Internet of Things (IoT) brings a set of unique and complex challenges to the field of Quality of Experience (QoE) evaluation.
  7. [7]
    A survey of challenges and methods for Quality of Experience ...
    Apr 29, 2022 · This paper reviews different aspects of performing perception-based QoE assessment for interactive VR applications and presents options and recommendations for ...
  8. [8]
    Quality of Experience Recent Trends and Challenges - AIP Publishing
    This paper provides in-depth point of view of recent trends and challenges in the field of QoE, definitions and factors that are essential to users of QoE ...
  9. [9]
    A Tutorial on Data-Driven Quality of Experience Modeling With ...
    Jun 25, 2025 · This tutorial focuses on data-driven QoE modeling using XAI, which addresses explainability, context adaptability, uncertainty quantification, ...<|separator|>
  10. [10]
    [PDF] Quality of Experience in Video Streaming: Status Quo, Pitfalls, and ...
    Abstract—Quality of experience (QoE) becomes both the holy grail and a free-for-all in adaptive bitrate (ABR) video streaming. On the one hand, the design, ...
  11. [11]
    [PDF] Quality of Experience and Human-computer Interaction - UPV
    Abstract—This paper first traces the historic evolution of the. Quality of Experience (QoE) concept, and then connects common points between the study of ...
  12. [12]
  13. [13]
    [PDF] On the notion of quality of experience
    Before 1990, the quality of experience was primarily used in philosophical and psychological articles, where it appeared occasionally. Since the 1990s, the term ...
  14. [14]
    [PDF] User based QoS expressed in technical network QoS terms
    Hestnes, B., Brooks, P., Heiestad, S., Ulseth, T., Aaby., C. (2003). Quality of Experience in real-time person- person communication - User based QoS expressed ...
  15. [15]
  16. [16]
    [PDF] Federal Communications Commission - PUBLIC NOTICE
    Nov 30, 2021 · 3 ITU-T Recommendation P.800, (08/1996), Methods for subjective determination of transmission quality. 4 ITU-T Recommendation P.805 (04/2007) ...
  17. [17]
    QoE Column - ACM SIGMM Records
    We call this 'quality of experience'.” This early definition of QoE encompasses all aspects of a user's interaction with a product, including its physical feel, ...
  18. [18]
    [PDF] ETSI TR 102 643 V1.0.0 (2009-11)
    Consistent with the ITU-T definitions of QoE and QoSE, the majority of work to date on QoE has concerned subjective measurement of experience and QoE is ...Missing: milestones | Show results with:milestones
  19. [19]
    The Importance of the Quality of Experience (QoE) in the Telecom ...
    Feb 24, 2023 · The concept of Quality of Experience (QoE) since the late 1990s and early 2000s hasn't been only limited to the telecommunications industry but ...Missing: history | Show results with:history
  20. [20]
    New ITU-T Recommendation P.1203 supports quality estimation of ...
    Mar 6, 2017 · In December 2016, ITU-T SG12 approved recommendation P.1203, which describes algorithms ("models") that estimate the end user media quality ...
  21. [21]
    P.1203.3 - ITU-T Recommendation database
    Jan 13, 2019 · ITU-T P.1203.3 (01/2019) ; Approval date: 2019-01-13 ; Provisional name: P.NATS ; Approval process: AAP ; Status: In force ; Maintenance ...
  22. [22]
    Mobile QoE: Network readiness for new services - Ericsson
    The ITU-T Rec. P.1203 is the world's first standard for measuring the QoE of video streaming services for longer viewing sessions and has been established for ...Missing: milestones | Show results with:milestones
  23. [23]
  24. [24]
    P.10 : Vocabulary for performance, quality of service and ... - ITU
    Sep 20, 2024 · New Appendix I - Definition of Quality of Experience (QoE) This Amendment was superseded by Amendment 2, Superseded. P.10/G.100 (2006) ...
  25. [25]
  26. [26]
    [PDF] ETSI TR 102 643 V1.0.1 (2009-12)
    The main content of the WBGTS are Quality of Experience (QoE) guidelines for real-time communication services expressed in Quality of Service (QoS) terms.
  27. [27]
    Quality of Experience - ETSI Portal
    QoE is defined by the ITU in terms of user perception and/or user satisfaction. However, data about QoE would be more comprehensive and potentially more valid ...Missing: formal IEC
  28. [28]
    ISO/IEC 23001-11:2019(en), Information technology
    This metadata facilitates reduced energy usage during media consumption without any degradation in the quality of experience (QoE). However, it is also possible ...
  29. [29]
    Understanding QoS and QoE in Telecoms: A Comprehensive Guide
    Dec 16, 2023 · QoS refers to the performance and reliability of the network infrastructure, while QoE focuses on the end user's perception of the service quality.
  30. [30]
    Difference between Quality of Service (QoS) and ... - GeeksforGeeks
    Jul 23, 2025 · QoS targets the technical aspects influencing the network performance while QoE targets the level of satisfaction that the users gain from the use of the ...
  31. [31]
    From QoS to QoE: A Shift Towards the User Experience - RTInsights
    Apr 3, 2024 · The impact of bad user experiences and the focus of a QoE approach far outweigh those of an outage, which is the priority for a QoS approach ...
  32. [32]
    [PDF] Take away, summary and conclusion from the QoS and QoE ... - ITU
    QoE focuses on the entire service experience; it is a holistic concept, similar to the field of User Experience, but with its roots in telecommunication. .
  33. [33]
    [PDF] ITU-T Rec. G.1080 (12/2008) Quality of experience requirements for ...
    Summary. Recommendation ITU-T G.1080 defines user requirements for quality of experience (QoE) for. Internet protocol television (IPTV) services.
  34. [34]
    Quality of Service (QoS) and Quality of experience (QoE)
    Mar 1, 2024 · Quality of Service (QoS) and Quality of experience (QoE). The International Telecommunication Union (ITU) characterizes Quality of Service (QoS) ...
  35. [35]
    What is quality of experience (QoE or QoX)? - TechTarget
    Mar 13, 2025 · Quality of experience (QoE or QoX) is a measure of the overall level of a customer's satisfaction and experience with a product or service.<|separator|>
  36. [36]
    Measuring real services in a real environment to grasp the true ...
    Apr 1, 2022 · QoS work is based on technical performance (i.e., it is mainly technology-centered) whereas QoE is based on end-user behaviour (it is user- ...
  37. [37]
    P.940 : Computational model used for the monitoring and quality assessment of videotelephony services
    **Summary of Network Impairments Affecting Video QoE in ITU-T P.940:**
  38. [38]
    P.564 : Conformance testing for voice over IP transmission quality assessment models
    ### Summary of IP Network Impairments for Speech Quality (ITU-T P.564)
  39. [39]
    Impact of Packet Loss Rate on Quality of Compressed High ... - NIH
    Mar 2, 2023 · This paper analyzes the adverse impact of packet loss on video quality encoded with various combinations of compression parameters and resolutions.
  40. [40]
    The Impact of Network Impairment on Quality of Experience (QoE) in ...
    Aug 6, 2025 · Here, we consider a random packet loss pattern as it has a significant detrimental effect on the video stream quality as compared to other types ...
  41. [41]
    (PDF) The Impact of Network Impairments on the QoE of WebRTC ...
    Sep 13, 2022 · A dedicated system was implemented to introduce controlled network impairments (delay, jitter, and packet loss) to impair the communication ...
  42. [42]
    Latency, Jitter & Packet Loss Explained - TPx Communications
    Oct 2, 2025 · Jitter: The variation in latency—when data packets don't arrive in a consistent flow. High jitter can cause choppy video and garbled audio.
  43. [43]
  44. [44]
    On the influence of individual differences in cross-modal ...
    Sep 14, 2020 · In this paper we report the results of a study which investigated the role that individual differences (such as age, gender, education, and smell sensitivity) ...
  45. [45]
    [PDF] The Influnce of Gender on QoE Subjective Assessment for ... - ijcit
    The user profiles consist of several aspects: age, gender, education background for video content type, prior experiences in viewing videos and mobile videos, ...
  46. [46]
  47. [47]
  48. [48]
  49. [49]
    Listening Effort Informed Quality of Experience Evaluation - Frontiers
    Jan 4, 2022 · Thus, the QoE evaluation approach has been widely adopted to rapidly test the perceptual effect of new products and services.
  50. [50]
    Perceived quality of multimedia educational content: A cognitive ...
    Feb 8, 2006 · In this paper, we report the results of an empirical study, which investigated the relationship between user cognitive styles and perceptual ...<|separator|>
  51. [51]
    (PDF) Do Personality and Culture Influence Perceived Video Quality ...
    Aug 7, 2025 · This article presents an attempt to explore the influence of personality and cultural traits on perception of multimedia quality. As a first ...
  52. [52]
    PsyQoE: Improving Quality-of-Experience Assessment With ...
    Aug 28, 2024 · We propose PsyQoE, a new QoE assessment framework that uniquely focuses on user perceptions during media sessions. Besides providing real-time ...Missing: human | Show results with:human
  53. [53]
  54. [54]
    Multidimensional modelling of quality of experience for video ...
    QoE for video streaming can be modelled by using perception of quality of video and perception of ease of use of application as predictors.
  55. [55]
    Towards the Evaluation of the Effects of Ambient Illumination and ...
    In this paper, we investigate the effects of ambient illumination and noise on two multimedia consumption scenarios: watching a video on TV and reading a comic ...
  56. [56]
    Factors Influencing Quality of Experience | Request PDF
    QoE can be subject to a range of complex and strongly interrelated factors, falling into three categories: human, system and context influence factors (IFs).
  57. [57]
    Understanding the role of social context and user factors in video ...
    This paper aims to identify the role of social context and user factors (such as interest and demographics) in determining quality of viewing experience.
  58. [58]
    The impact of network and social context on quality of experience for ...
    We further analyze the impact of social context on the reported results of the conducted QoE study, investigating to what extent playing with friends/strangers ...
  59. [59]
    (PDF) Quality of Service vs. Quality of Experience - ResearchGate
    The service perceived quality (also called Quality of Experience, QoE) gives telecommunication companies an important perspective and insights regarding their ...
  60. [60]
    From QoS Distributions to QoE Distributions: a System's Perspective
    Mar 28, 2020 · In this paper we extend these findings to show how to approximate user rating distributions given a QoS-to-MOS mapping function and second order statistics.Missing: distinction research<|control11|><|separator|>
  61. [61]
  62. [62]
    Quality of experience versus user experience | Request PDF
    QoE has primarily emerged from telecommunication research, while UX has its foundations in the field of Human-Computer Interaction (Wechsung & De Moor, 2014) .
  63. [63]
    ISO 9241-210:2010(en), Ergonomics of human-system interaction
    Note 1 to entry: User experience includes all the users' emotions, beliefs, preferences, perceptions, physical and psychological responses, behaviours and ...
  64. [64]
  65. [65]
    Quality of Experience - Kaitotek
    Quality of Experience (QoE) indicates how satisfied the user is for using the application/service. QoE is always an application-specific measure.
  66. [66]
    [PDF] Measuring Video Quality in the Network
    User Experience (UX): How a person feels about the experience delivered. UX is one factor in QoE. In this article, we provide an overview of how to measure ...
  67. [67]
    A new approach for predicting the Quality of Experience in ... - arXiv
    Jun 12, 2024 · QoE focuses on the user's satisfaction with the service, helping operators to adjust their services to meet user expectations. However, ...
  68. [68]
    QoE Modelling, Measurement and Prediction: A Review
    Oct 28, 2014 · This paper presents an extensive re-view of the state-the-art research in the area of QoE modelling, mea-surement and prediction. In particular ...
  69. [69]
    Packet-based PSNR time series prediction for video teleconferencing
    The proposed first approach adopts a parametric model for the impact on the video quality due to losing a packet, while the second proposed approach is ...
  70. [70]
    New objective QoE models for evaluating ABR algorithms in DASH
    May 15, 2020 · This paper has presented three new models for calculating the QoE in an objective way. Both objective and subjective evaluations presented in ...
  71. [71]
    On Machine Learning Based Video QoE Estimation Across Different ...
    This paper explores machine learning models for video QoE estimation, comparing network-specific, general, and cross-tested models, finding general models ...
  72. [72]
    Objective QoE Prediction for Video Streaming Services: A Novel Full ...
    Data from real users scoring 150 distorted video sequences have been used to train the machine learning algorithm based on QoE model developed in this work.
  73. [73]
    [2406.08564] Machine Learning-Driven Open-Source Framework for ...
    Jun 12, 2024 · This paper introduces a machine learning-based framework for objectively assessing QoE in multimedia networks. The open-source framework ...
  74. [74]
    QoE Modelling, Measurement and Prediction: A Review
    This paper presents a pioneering context-aware approach for quality of experience (QoE) measurement and prediction that is capable of incorporating several QoE ...
  75. [75]
    An Efficient Network-Based QoE Assessment Framework for ...
    Feb 19, 2025 · This paper presents an open-source framework for assessing QoE in multimedia networks using only key network parameters.
  76. [76]
    Quality of Experience Measurements for Video Streaming over ...
    To investigate QoE measurement, this paper presents three approaches namely subjective approach, objective approach, and hybrid approach. It also presents ...
  77. [77]
    A User-Centric Approach for Web Quality of Experience Measurement
    Mar 26, 2020 · This approach quantifies QoE based on subjective ratings which are directly appraised by users and objective metrics which are gathered during ...
  78. [78]
    Quality of experience measurement of compressed multi-view video
    A hybrid time-efficient approach for perceptual QoE evaluation is proposed. · The method is a mixed version of SAMVIQ and DSCQS, where the double stimuli is ...
  79. [79]
  80. [80]
    Enhancing QoS and QoE in IMS Enabled Next Generation Networks
    Abstract: The ultimate goal of optimization techniques at the network and application layer is to ensure end-user perceived QoS.
  81. [81]
    [PDF] Bridging the Gap between QoE and QoS in Congestion Control
    Jul 12, 2023 · This paper is included in the Proceedings of the. 2023 USENIX Annual Technical Conference. July 10–12, 2023 • Boston, MA, USA. 978-1-939133-35-9.
  82. [82]
    RFC 9522 - Overview and Principles of Internet Traffic Engineering
    Feb 21, 2024 · This document describes the principles of traffic engineering (TE) in the Internet. The document is intended to promote better understanding of the issues ...
  83. [83]
    What is Quality of Service (QoS) in Networking? - Fortinet
    QoS is the use of mechanisms or technologies that work on a network to control traffic and ensure the performance of critical applications with limited network ...
  84. [84]
    quality of service (QoS) - TechTarget
    Jun 19, 2023 · QoS mechanisms fall under specific categories, depending on the roles they play in managing the network. Classification and marking.Qos Parameters · How Does Qos Work? · Qos Mechanisms<|separator|>
  85. [85]
    QoE-aware congestion control algorithm for conversational services
    We propose in this paper a Quality-centric Mean Opinion Score (MOS) based congestion control that determines an optimal congestion window updating policy for ...Missing: optimization | Show results with:optimization
  86. [86]
    Mustang: Improving QoE for Real-Time Video in Cellular Networks ...
    Sep 23, 2024 · We propose Mustang, an algorithm designed to overcome the jitter in cellular networks. Mustang makes use of the FDT and receiving rate as feedback information ...<|control11|><|separator|>
  87. [87]
    DiffPerf: An In-Network Performance Optimization for Improving User ...
    We address this bandwidth allocation problem by proposing DiffPerf, an in-network system that relies on a lightweight learning algorithm to statistically ...
  88. [88]
    (PDF) Traffic engineering and QoS/QoE supporting techniques for ...
    Aug 6, 2025 · The paper presents a user experience-centric approach to traffic engineering and QoS/quality of experience (QoE) support for service-oriented ...
  89. [89]
    Network Traffic Engineering - Kentik
    QoS Policies: Implementing Quality of Service (QoS) policies can control and prioritize traffic based on the type of data, its importance, and the required ...The Importance of Network... · The Relationship Between...
  90. [90]
    QoE Management for Future Networks - SpringerLink
    May 25, 2018 · For these reasons, the concept of Quality of Experience (QoE) has gained strong interest, both from academic research and industry stakeholders.Qoe Management For Future... · 3 Specific Qoe Management... · 3.3 Qoe Management With Sdn
  91. [91]
    Quality of Experience Oriented Cross-Layer Optimization for Real ...
    Mar 13, 2024 · The experimental results show that the TPPO+MS-DQN algorithm proposed in this study can improve the QoE by 3.6% to 37.8%. More specifically, the ...
  92. [92]
    P.1203 : Parametric bitstream-based quality assessment of ... - ITU
    Feb 12, 2020 · This amendment was never published separately; its content has been included in the published Rec. ITU-T P.1203 (2016). Superseded. Top - ...Missing: date | Show results with:date
  93. [93]
    Machine Learning Based Classifiers for QoE Prediction Framework ...
    This work also explored the ML-oriented schemes for providing a target QoE framework depending on the network, data link, and physical layer parameters.
  94. [94]
    Enhancing QoE Prediction for Video Streaming Using a Hybrid CNN ...
    Oct 10, 2025 · Advanced models like CGRU-QoE (Convolutional Gated. Recurrent Unit for QoE Prediction) use CNNs to gather overall information and use attention ...
  95. [95]
    Deep Reinforcement Learning-Based Resource Allocation for QoE ...
    Feb 10, 2025 · By incorporating artificial intelligence (AI) into these strategies, networks can achieve smarter resource manage- ment, leading to enhanced ...
  96. [96]
    A hybrid and self-adaptive QoS and QoE-driven RAT selection ...
    Jul 1, 2025 · This paper proposes a novel hybrid and adaptive approach based on Deep Reinforcement Learning (DRL) that combines QoS and Quality of Experience (QoE) factors.
  97. [97]
    [PDF] QoE-Driven Optimization in 5G O-RAN Enabled HetNets for ...
    The paper introduces QoE2F, a new application using an adaptive genetic algorithm to improve video service quality in 5G O-RAN HetNets by solving user ...
  98. [98]
  99. [99]
    An Introduction to 5G Quality of Experience (QoE) - Ofinno
    May 14, 2024 · 5G QoE measurement collection is targeting to specify a mechanism to collect application layer measurements from the users.
  100. [100]
    None
    ### Summary of 5G vs 4G Improvements (Latency, Throughput, Reliability, QoE)
  101. [101]
  102. [102]
    Empirical analysis of 5G deployments: A comparative assessment of ...
    In [3], the authors investigate the performance, power consumption, and Quality-of-Experience (QoE) of commercial 5G networks, examining various deployment ...
  103. [103]
    [PDF] ETSI TS 123 501 V18.9.0 (2025-04)
    This Technical Specification (TS) has been produced by ETSI 3rd Generation Partnership Project (3GPP). The present document may refer to technical ...
  104. [104]
    [PDF] QoE Modelling for Ultra-HD Video Streaming in 5G Networks
    Measured QoE: The quality of experience index calculated and reported by the 5G-QoE platform during empirical evaluations. • Predicted QoE: The theoretical ...
  105. [105]
    [PDF] 5G-Use-Cases.pdf
    Nov 6, 2023 · First, FWA expands the competitive landscape, as Mobile. Network Operators can now offer high-speed internet services traditionally dominated by ...
  106. [106]
    Dynamic handover optimization in 5G heterogeneous networks
    This paper proposes a novel dynamic handover approach designed to optimize seamless connectivity in heterogeneous 5G wireless networks.
  107. [107]
    Presence and Cybersickness in Virtual Reality Are Negatively Related
    Feb 3, 2019 · This review paper summarizes the concepts of presence and cybersickness and highlights the strengths and gaps in our understanding about their relationship.
  108. [108]
    Presence and Cybersickness in Virtual Reality Are Negatively Related
    Feb 4, 2019 · This review paper summarizes the concepts of presence and cybersickness and highlights the strengths and gaps in our understanding about their relationship.
  109. [109]
    A subjective study on QoE of 360 video for VR communication
    In this paper, the QoE of 360 videos is considered in terms of four aspects, namely perceptual quality, presence, acceptability, and cybersickness.
  110. [110]
    Impact of Latency on QoE, Performance, and Collaboration ... - MDPI
    Mar 8, 2024 · The results showed that high end-to-end latency between two VR clients had adverse effects on user performance, mutual understanding between ...
  111. [111]
    The Effect of Video Quality on Quality of Experience in Virtual Reality
    May 28, 2020 · Seeing is Believing: The Effect of Video Quality on Quality of Experience in Virtual Reality. Publisher: IEEE. Cite This.
  112. [112]
    Subjective QoE Assessment for Virtual Reality Cloud-based First ...
    This paper presents subjective tests (N=30) and investigates the effect of network-emulated QoS metrics (N=28) on the commercial Nvidia CloudXR service.
  113. [113]
    Cybersickness and Its Severity Arising from Virtual Reality Content
    Virtual reality (VR) experiences often elicit a negative effect, cybersickness, which results in nausea, disorientation, and visual discomfort.
  114. [114]
  115. [115]
    [PDF] Neurophysiological Indicators to Assess Quality-of-Experience ...
    lieving: the effect of video quality on quality of experience in virtual reality,” in 2020 Twelfth. International Conference on Quality of Multimedia ...
  116. [116]
    Assessing the Impact of Network Quality-of-Service on Metaverse ...
    Jul 15, 2024 · This paper empirically measures user QoE of metaverse VR caused by network QoS. Specifically, by focusing on both public social hubs and private user-created ...
  117. [117]
    [PDF] Towards Perceptual Evaluation of Six Degrees of Freedom Virtual ...
    The subjective study in this work shows that in order to achieve a higher overall quality of experience in virtual reality, rendering accurate motion ...
  118. [118]
    What are Thresholds for Good and Poor Network Packet Loss, Jitter...
    May 17, 2018 · We use the thresholds of < 1% for Packet loss, < 20ms of Jitter and <300ms RTT as our “good”. The RTT is set as 300 as the ITU-T's 150ms above is one way, not
  119. [119]
    [PDF] Understanding the Impact of Video Quality on User Engagement
    For example, a 1% in- crease in buffering ratio can reduce user engagement by more than three minutes for a 90-minute live video event. We also see that the.
  120. [120]
    Suffering from buffering? Detecting QoE impairments in live video ...
    In this paper, we present a measurement study of adaptive bitrate video streaming for a large-scale live event.
  121. [121]
    Improving the Quality of Experience of Video Streaming Through a ...
    To deal with network bandwidth change, research has been performed to improve the user QoE of video streaming services using deep learning and reinforcement ...Missing: peer- | Show results with:peer-
  122. [122]
    Assessing the quality of experience in wireless networks for ... - NIH
    Apr 25, 2024 · This study introduces a multimedia QoE evaluation method for wireless networks based on advanced deep learning models, with the goal of ...
  123. [123]
    Enhancing Quality of Experience (QoE) assessment models for ...
    In this paper, we study a number of existing objective quality assessment models for assessing the QoE of video applications, and compare their performance with ...
  124. [124]
    Recommendation ITU-T P.910 (10/2023) - Subjective video quality ...
    ACR may be insensitive to some impairments that are easily detected by degradation category rating (DCR) or comparison category rating (CCR). For example, a ...
  125. [125]
  126. [126]
    (PDF) Non-Intrusive Online Quality of Experience Assessment for ...
    Generally, current approaches for QoE assessment are obtrusive, laboratory based and offline. Estimation of user satisfaction in static manner based on mean ...
  127. [127]
    a systematic review of guidelines and implications for QoE research
    Jul 5, 2023 · The concept of conducting ecologically valid user studies is gaining traction in the field of Quality of Experience (QoE).<|separator|>
  128. [128]
    Subjective and Objective Quality-of-Experience Evaluation Study for ...
    Sep 26, 2024 · This study evaluates live video streaming quality using subjective and objective methods, introduces a new dataset, and proposes a new QoE ...
  129. [129]
    [PDF] Methods for Objective and Subjective Video Quality Assessment and ...
    Objective methods and specifically No-Reference (NR) or. Reduced-Reference (RR) methods are preferable because they are practical for implementation in real- ...
  130. [130]
    A tool for quality of experience (QoE) in long-term context research
    This paper presents 'Daily Video', an innovative application designed to facilitate longitudinal studies in the realm of quality of experience (QoE).
  131. [131]
  132. [132]
    Subjective and Objective Quality Assessments of Display Products
    Jun 26, 2021 · Unfortunately, the SC method can only provide the qualitative results (for example, which is better between the two images), but is unable to ...
  133. [133]
    (PDF) Quality of Experience Management in Mobile Networks
    Jul 2, 2025 · These include the complexity of balancing resource allocation across diverse services to maintain optimal user experiences, as well as technical ...
  134. [134]
    Challenges of future multimedia QoE monitoring for internet service ...
    Jun 2, 2017 · From a historical perspective, we can observe different developments in the approaches for network and service quality monitoring. As mentioned ...
  135. [135]
  136. [136]
    An Efficient Network-Based QoE Assessment Framework for ...
    Mar 17, 2025 · By focusing solely on network metrics, the framework offers significant advantages in scalability, real-time applicability, and data privacy, ...
  137. [137]
    Revolutionizing QoE-Driven Network Management with Digital ...
    Consequently, proactive network management strategies can be validated and refined in virtualized networks to improve user QoE.
  138. [138]
    QoE beyond the MOS: Added value using quantiles and distributions
    ### Summary of Limitations of MOS and Criticisms of User-Centric Metrics
  139. [139]
    an in-depth look at QoE via better metrics and their relation to MOS
    Sep 2, 2016 · QoE and influence factors on user ratings. From the definition of quality first introduced by Jekosch (2005), it follows that quality is the ...
  140. [140]
    (PDF) No silver bullet: QoE metrics, QoE fairness, and user diversity ...
    Recent studies have shown that it is possible to characterize subject bias and variance in subjective assessment tests. Apparent differences among subjects ...
  141. [141]
    [PDF] The Accuracy of Subjects in a Quality Experiment
    Second, the sensitivity and accuracy of most subjective analyses can be improved if the subject scores are normalized by removing subject bias. Third, to some ...
  142. [142]
    Generative QoE Modeling: A Lightweight Approach for Telecom ...
    Apr 30, 2025 · This study introduces a lightweight generative modeling framework that balances computational efficiency, interpretability, and predictive accuracy.
  143. [143]
  144. [144]
    ITU-T P.1402 - Guidance for the development of machine-learning ...
    Jul 2, 2024 · Recommendation ITU-T P.1402 introduces machine-learning techniques and their application for quality of service (QoS) and quality of ...
  145. [145]
    ITU-T Recommendation database
    Considerations for the development of new QoS and QoE related objective models to be embedded in Recommendations prepared by ITU-T Study Group 12, In force.
  146. [146]
    ITU-T WP: 2025-2028: SG12: P​erformance, quality of service (QoS ...
    Quality of experience (QoE), quality of service (QoS) and performance requirements and assessment methods for multimedia applicationsMissing: milestones | Show results with:milestones<|separator|>
  147. [147]
    RAN3 Led Features in Release 18 - 3GPP
    RAN3 led features in Rel-18 include AI/ML for NG-RAN, SON/MDT, QoE, mobile IAB, NR Timing Resiliency, URLLC, Network Slicing, and Non-public Networks Phase 2.Son/mdt Enhancements · Nr Qoe Enhancement · Mobile Iab For Nr
  148. [148]
    AI/ML for NG-RAN & 5G-Advanced towards 6G - 3GPP
    Aug 8, 2025 · Working Group RAN3 completed Rel-18 normative work in Q4 2023, while Rel-19 work items started in Q2 2024 and normative work is ongoing. Data ...
  149. [149]
    Overview of NR Enhancements for Extended Reality (XR) in 3GPP ...
    Dec 1, 2024 · The introduced enhancements are aiming to reduce latency, increase number of simultaneously supported XR users as well as improving power saving ...Iii Xr Enhancements In... · Iii-D Capacity Enhancements · Iv Evaluation Of Xr...
  150. [150]
    TIP Releases QoE Measurement Framework and Graduates ...
    Oct 29, 2024 · By making QoE the foundation of network design, we get two major benefits: first, the network is built around user needs, making the services ...<|separator|>
  151. [151]
    Great mobile QoE starts with excellent video - Ericsson
    Great mobile experience quality starts with excellent video streaming. Discover how standardized QoE models can unlock new opportunities for MNOs.
  152. [152]
    The Call for High Quality of Experience networks in Europe - MedUX
    Sep 16, 2024 · The call is for high-quality QoE networks in Europe, shifting focus to meaningful connectivity, going beyond coverage, and ensuring reliable, ...<|separator|>
  153. [153]
    Video Streaming Industry Report 2024 - NPAW
    Video-on-demand (VOD) Playtime per User has dipped slightly, with fewer titles watched. Despite lower engagement, quality metrics improved significantly.Missing: evolutions | Show results with:evolutions