Narrowing the Gap Between QoS Metrics and Web QoE Using Above-the-fold Metrics

Loading...
Thumbnail Image

Access rights

openAccess

URL

Journal Title

Journal ISSN

Volume Title

A4 Artikkeli konferenssijulkaisussa

Date

2018-03

Major/Subject

Mcode

Degree programme

Language

en

Pages

12
31-43

Series

Passive and Active Measurement, Volume 10771, Lecture Notes in Computer Science book series (LNCS)

Abstract

Page load time (PLT) is still the most common application Quality of Service (QoS) metric to estimate the Quality of Experience (QoE) of Web users . Yet, recent literature abounds with proposals for alternative metrics (e.g., Above The Fold, SpeedIndex and their variants) that aim at better estimating user QoE. The main purpose of this work is thus to thoroughly investigate a mapping between established and recently proposed objective metrics and user QoE. We obtain ground truth QoE via user experiments where we collect and analyze 3,400 Web accesses annotated with QoS metrics and explicit user ratings in a scale of 1 to 5, which we make available to the community. In particular, we contrast domain expert models (such as ITU-T and IQX) fed with a single QoS metric, to models trained using our ground-truth dataset over multiple QoS metrics as features. Results of our experiments show that, albeit very simple, expert models have a comparable accuracy to machine learning approaches. Furthermore, the model accuracy improves considerably when building per-page QoE models, which may raise scalability concerns as we discuss.

Description

Keywords

QoE, Qos, ATF, Above-the-fold, Web QoE

Other note

Citation

da Hora, D N, Asrese, A, Christophides, V, Teixeira, R & Rossi, D 2018, Narrowing the Gap Between QoS Metrics and Web QoE Using Above-the-fold Metrics . in R Beverly, G Smaragdakis & A Feldmann (eds), Passive and Active Measurement : 19th International Conference . vol. 10771, Lecture Notes in Computer Science book series (LNCS), vol. 10771, Springer, Berlin, pp. 31-43, Passive and Active Measurement Conference, Berlin, Germany, 26/03/2018 . https://doi.org/10.1007/978-3-319-76481-8