Measuring and monitoring YouTube Quality of Experience is a challenging task, especially when dealing with cellular networks and smartphone users. Using a large-scale database of crowdsourced YouTube-QoE measurements in smartphones, we conceive multiple machine-learning models to infer different YouTube-QoE-relevant metrics and userbehavior- related metrics from network-level measurements, without requiring root access to the smartphone, video-player embedding, or any other reverse-engineering-like approaches. The dataset includes measurements from more than 360 users worldwide, spanning over the last five years. Our preliminary results suggest that QoE-based monitoring of YouTube mobile can be realized through machine learning models with high accuracy, relying only on network-related features and without accessing any higher-layer metric to perform the estimations.
%0 Journal Article
%1 info3-article-2019-10
%A Wassermann, Sarah
%A Wehner, Nikolas
%A Casas, Pedro
%D 2019
%J ACM SIGMETRICS Performance Evaluation Review
%K myown copy
%N 3
%P 155-158
%T Machine Learning Models for YouTube QoE and User Engagement Prediction in Smartphones
%V 46
%X Measuring and monitoring YouTube Quality of Experience is a challenging task, especially when dealing with cellular networks and smartphone users. Using a large-scale database of crowdsourced YouTube-QoE measurements in smartphones, we conceive multiple machine-learning models to infer different YouTube-QoE-relevant metrics and userbehavior- related metrics from network-level measurements, without requiring root access to the smartphone, video-player embedding, or any other reverse-engineering-like approaches. The dataset includes measurements from more than 360 users worldwide, spanning over the last five years. Our preliminary results suggest that QoE-based monitoring of YouTube mobile can be realized through machine learning models with high accuracy, relying only on network-related features and without accessing any higher-layer metric to perform the estimations.
@article{info3-article-2019-10,
abstract = {Measuring and monitoring YouTube Quality of Experience is a challenging task, especially when dealing with cellular networks and smartphone users. Using a large-scale database of crowdsourced YouTube-QoE measurements in smartphones, we conceive multiple machine-learning models to infer different YouTube-QoE-relevant metrics and userbehavior- related metrics from network-level measurements, without requiring root access to the smartphone, video-player embedding, or any other reverse-engineering-like approaches. The dataset includes measurements from more than 360 users worldwide, spanning over the last five years. Our preliminary results suggest that QoE-based monitoring of YouTube mobile can be realized through machine learning models with high accuracy, relying only on network-related features and without accessing any higher-layer metric to perform the estimations.},
added-at = {2019-10-08T15:21:25.000+0200},
author = {Wassermann, Sarah and Wehner, Nikolas and Casas, Pedro},
biburl = {https://www.bibsonomy.org/bibtex/29a3cdceb86852a7cb38d17ab1b0e53f1/uniwue_info3},
interhash = {dd5620c1fcd66672b4bde5dd5d85a6f5},
intrahash = {9a3cdceb86852a7cb38d17ab1b0e53f1},
journal = {ACM SIGMETRICS Performance Evaluation Review},
keywords = {myown copy},
month = {1},
number = 3,
pages = {155-158},
timestamp = {2022-03-14T00:14:08.000+0100},
title = {Machine Learning Models for YouTube QoE and User Engagement Prediction in Smartphones},
volume = 46,
year = 2019
}