@inproceedings{zhang-etal-2025-webquality,
title = "{W}eb{Q}uality: A Large-scale Multi-modal Web Page Quality Assessment Dataset with Multiple Scoring Dimensions",
author = "Zhang, Tao and
Wang, Yige and
ZhuHangyu, ZhuHangyu and
Xin, Li and
Xiang, Chen and
Zhou, Tian Hua and
Ma, Jin",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-long.25/",
doi = "10.18653/v1/2025.naacl-long.25",
pages = "583--596",
ISBN = "979-8-89176-189-6",
abstract = "The assessment of web page quality plays a critical role in a range of downstream applications, yet there is a notable absence of datasets for the evaluation of web page quality. This research presents the pioneering task of web page quality assessment and introduces the first comprehensive, multi-modal Chinese dataset named WebQuality specifically designed for this task. The dataset includes over 65,000 detailed an-notations spanning four sub-dimensions and incorporates elements such as HTML+CSS, text, and visual screenshot, facilitating in-depth modeling and assessment of web page quality. We performed evaluations using a variety of baseline models to demonstrate the complexity of the task. Additionally, we propose Hydra, an integrated multi-modal analysis model, and rigorously assess its performance and limitations through extensive ablation studies. To advance the field of web quality assessment, we offer unrestricted access to our dataset and codebase for the research community, available at https://github.com/incredible-smurf/WebQuality"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2025-webquality">
<titleInfo>
<title>WebQuality: A Large-scale Multi-modal Web Page Quality Assessment Dataset with Multiple Scoring Dimensions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yige</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">ZhuHangyu</namePart>
<namePart type="family">ZhuHangyu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Xin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Xiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tian</namePart>
<namePart type="given">Hua</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jin</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-189-6</identifier>
</relatedItem>
<abstract>The assessment of web page quality plays a critical role in a range of downstream applications, yet there is a notable absence of datasets for the evaluation of web page quality. This research presents the pioneering task of web page quality assessment and introduces the first comprehensive, multi-modal Chinese dataset named WebQuality specifically designed for this task. The dataset includes over 65,000 detailed an-notations spanning four sub-dimensions and incorporates elements such as HTML+CSS, text, and visual screenshot, facilitating in-depth modeling and assessment of web page quality. We performed evaluations using a variety of baseline models to demonstrate the complexity of the task. Additionally, we propose Hydra, an integrated multi-modal analysis model, and rigorously assess its performance and limitations through extensive ablation studies. To advance the field of web quality assessment, we offer unrestricted access to our dataset and codebase for the research community, available at https://github.com/incredible-smurf/WebQuality</abstract>
<identifier type="citekey">zhang-etal-2025-webquality</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-long.25</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-long.25/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>583</start>
<end>596</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T WebQuality: A Large-scale Multi-modal Web Page Quality Assessment Dataset with Multiple Scoring Dimensions
%A Zhang, Tao
%A Wang, Yige
%A ZhuHangyu, ZhuHangyu
%A Xin, Li
%A Xiang, Chen
%A Zhou, Tian Hua
%A Ma, Jin
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-189-6
%F zhang-etal-2025-webquality
%X The assessment of web page quality plays a critical role in a range of downstream applications, yet there is a notable absence of datasets for the evaluation of web page quality. This research presents the pioneering task of web page quality assessment and introduces the first comprehensive, multi-modal Chinese dataset named WebQuality specifically designed for this task. The dataset includes over 65,000 detailed an-notations spanning four sub-dimensions and incorporates elements such as HTML+CSS, text, and visual screenshot, facilitating in-depth modeling and assessment of web page quality. We performed evaluations using a variety of baseline models to demonstrate the complexity of the task. Additionally, we propose Hydra, an integrated multi-modal analysis model, and rigorously assess its performance and limitations through extensive ablation studies. To advance the field of web quality assessment, we offer unrestricted access to our dataset and codebase for the research community, available at https://github.com/incredible-smurf/WebQuality
%R 10.18653/v1/2025.naacl-long.25
%U https://aclanthology.org/2025.naacl-long.25/
%U https://doi.org/10.18653/v1/2025.naacl-long.25
%P 583-596
Markdown (Informal)
[WebQuality: A Large-scale Multi-modal Web Page Quality Assessment Dataset with Multiple Scoring Dimensions](https://aclanthology.org/2025.naacl-long.25/) (Zhang et al., NAACL 2025)
ACL