Should I Stay or Should I Go

Plakia, Maria; Tzamousis, Evripides; Asvestopoulou, Thomais; Pantermakis, Giorgos; Filippakis, Nick; Schulzrinne, Henning; Kane-Esrig, Yana; Papadopouli, Maria

doi:10.1145/3377873

Cited by 6 publications

(8 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, we indicate that QoS impairments are a key element impacting the recommendation system context, and provide a systematic way to quantify its effect on QoE. Virtual QoS impairments may be due to content that is out of cache, and in that sense are similar to impairments due physical items being out of stock [41].…”

Section: B Context-aware and Multi-criteria Recommendersmentioning

confidence: 89%

See 1 more Smart Citation

When Should Recommenders Account for Low QoS?

Nogueira,

Pinheiro,

Assis

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Content recommendation systems, also known as recommenders, are pervasive and have significant impact on user demands over the Internet. Platforms such as YouTube and Netflix constantly seek to improve their recommendation systems, to provide better quality of experience (QoE) for their users. QoE, in turn, depends on a multitude of factors, including the quality of recommendation (QoR), e.g., based on users histories and content categories, and the quality of service (QoS), e.g., measured by network delay and throughput. Even though QoS is key in a best-effort Internet, existing recommendation systems overlook it, resulting in recommendations that are suboptimal in terms of QoE. In this study, our goal is to devise a QoS-aware, QoE-friendly, content recommendation system and indicate its feasibility in the wild. For this purpose, we conducted an experiment with real users driven by the following question: When should recommenders account for low QoS? Each user is requested to evaluate pairs of videos, that vary in their contents and QoS levels. We experimentally determined category-dependent thresholds that determine the sensitivity of users with respect to QoS and QoR. Given the collected insights on QoS-aware recommendations, we considered our second research question: Can recommenders compensate for low QoS? We conducted experiments over the Internet, relying on YouTube API and network measurements tools, and report our findings on (i) the characterization of QoS and (ii) the compensation for low QoS. Our measurements suggest that content far from the trends tends to be far from the user. We quantified the extent to which unpopular content tends to be served with a lower QoS and established a methodology to determine the relationship between content popularity and its physical proximity to users. Then, we verified that making requests a bit trendier can hit much closer content.

show abstract

Section: B Context-aware and Multi-criteria Recommendersmentioning

confidence: 89%

“…In [41], [42] the authors considered user engagement as their target QoE metric. In particular, in [42] the authors accounted for users' interests and QoS factors to build an engagement/QoE predictive model.…”

Section: A Qos and Qoe Parametersmentioning

confidence: 99%

When Should Recommenders Account for Low QoS?

Nogueira,

Pinheiro,

Assis

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Recently, published papers that focus on user engagement identified a correlation of video quality and network performance with engagement metrics. 26…”

Section: Video Qoe Predictionmentioning

confidence: 99%

“…Takahashi et al 25 studied the impact of quality factors such as stalling, initial delay, and average bitrate on the cumulative quite rate; they found that the combined impact of the number of stalling events, the average stalling duration, and the average bitrate have to be considered when designing a model to estimate the user engagement. While in Reference 26 it has shown a strong mapping where user engagement can be correlated to stalling ratio and a negative correlation between user engagement and quality switches in the context of non‐mobile scenarios. As a further exploration in the study of customer engagement behavior, dynamic interactivity, and user experience, the first work that studies the popularity of video content is done by Chatzopoulou et al, 27 who have found that video popularity has high correlation with four metrics that are: view count, favorites, comments, and ratings.…”

Section: Related Workmentioning

confidence: 99%

“…Furthermore, OTTs providers tend to optimize their services to maximize user engagement as it is considered a proxy for QoE. Recently, published papers that focus on user engagement identified a correlation of video quality and network performance with engagement metrics 26 . In Reference 34, a correlation of some network features with abandonment ratio is identified.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

QoE‐aware traffic monitoring based on user behavior in video streaming services

Laiche

Letaïfa

Aguili

2021

Concurrency and Computation

View full text Add to dashboard Cite

In recent years, online video content has gained a lot of popularity and the exponential growth of video traffic continues in every area of the connected world. Thus, understanding the quality of experience (QoE) perceived by end-users of video streaming services is important for both network operators and over the top providers since estimating end user's QoE has become one of the main points to meet user expectations. However, it is not trivial to ensure an adequate QoE since user experience is affected by various influencing factors (e.g., context factors, human factors, and system factors), and it is still challenging to identify the QoE key influencing factors. To address these challenges, we focused on improving QoE estimation and management strategies by exploiting valuable human and context information because the influence of social contextual information and user behavior on the perceptual quality is often neglected.In this article, we first proposed a classification of influence factors into four categories which are: system factors, human factors, context factors, and social-behavioral factors. We developed a monitoring web application where video content is played to end-users so that subjective and objective video metrics are collected. We built a new machine learning (ML) based model for QoE prediction. We used well-known supervised ML algorithms like decision tree, k-nearest neighbors, and support vector machine. Finally, we proposed a QoE management approach in the context of software defined network/multi-access edge computing that implements the proposed QoE prediction model to optimize the video delivery transmission chain.

show abstract

Estimating Latent Traffic Demand From QoS Degradation Using a Time Series Causal Inference Approach

Ishibashi,

Uchida

2024

IEEE Access

View full text Add to dashboard Cite

Should I Stay or Should I Go

Cited by 6 publications

References 5 publications

When Should Recommenders Account for Low QoS?

When Should Recommenders Account for Low QoS?

QoE‐aware traffic monitoring based on user behavior in video streaming services

Estimating Latent Traffic Demand From QoS Degradation Using a Time Series Causal Inference Approach

Contact Info

Product

Resources

About