Automatically measuring the quality of user generated content in forums

The amount of user generated content on the Web is growing and identifying high quality content in a timely manner has become a problem. Many forums rely on its users to manually rate content quality but this often results in gathering insuffcient rating. Automated quality assessment models have lar...

Full description

Bibliographic Details
Main Authors: Chai, Kevin, Wu, Chen, Potdar, Vidyasagar, Hayati, Pedram
Other Authors: Kevin Wong
Format: Conference Paper
Published: Springer 2011
Subjects:
Online Access:http://hdl.handle.net/20.500.11937/32636
_version_ 1848753717703081984
author Chai, Kevin
Wu, Chen
Potdar, Vidyasagar
Hayati, Pedram
author2 Kevin Wong
author_facet Kevin Wong
Chai, Kevin
Wu, Chen
Potdar, Vidyasagar
Hayati, Pedram
author_sort Chai, Kevin
building Curtin Institutional Repository
collection Online Access
description The amount of user generated content on the Web is growing and identifying high quality content in a timely manner has become a problem. Many forums rely on its users to manually rate content quality but this often results in gathering insuffcient rating. Automated quality assessment models have largely evaluated linguistic features but these techniques are less adaptive for the diverse writing styles and terminologies used by dierent forum communities. Therefore, we propose a novel model that evaluates content, usage, reputation, temporal and structural features of user generated content to address these limitations. We employed a rule learner, a fuzzy classier and Support Vector Machines to validate our model on three operational forums. Our model outperformed the existing models in our experiments and we veried that our performance improvements were statistically signicant.
first_indexed 2025-11-14T08:28:57Z
format Conference Paper
id curtin-20.500.11937-32636
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T08:28:57Z
publishDate 2011
publisher Springer
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-326362023-01-27T05:52:09Z Automatically measuring the quality of user generated content in forums Chai, Kevin Wu, Chen Potdar, Vidyasagar Hayati, Pedram Kevin Wong Lance Fung Hussein Abbass user generated content forums content quality assessment The amount of user generated content on the Web is growing and identifying high quality content in a timely manner has become a problem. Many forums rely on its users to manually rate content quality but this often results in gathering insuffcient rating. Automated quality assessment models have largely evaluated linguistic features but these techniques are less adaptive for the diverse writing styles and terminologies used by dierent forum communities. Therefore, we propose a novel model that evaluates content, usage, reputation, temporal and structural features of user generated content to address these limitations. We employed a rule learner, a fuzzy classier and Support Vector Machines to validate our model on three operational forums. Our model outperformed the existing models in our experiments and we veried that our performance improvements were statistically signicant. 2011 Conference Paper http://hdl.handle.net/20.500.11937/32636 10.1007/978-3-642-25832-9_6 Springer restricted
spellingShingle user generated content
forums
content quality assessment
Chai, Kevin
Wu, Chen
Potdar, Vidyasagar
Hayati, Pedram
Automatically measuring the quality of user generated content in forums
title Automatically measuring the quality of user generated content in forums
title_full Automatically measuring the quality of user generated content in forums
title_fullStr Automatically measuring the quality of user generated content in forums
title_full_unstemmed Automatically measuring the quality of user generated content in forums
title_short Automatically measuring the quality of user generated content in forums
title_sort automatically measuring the quality of user generated content in forums
topic user generated content
forums
content quality assessment
url http://hdl.handle.net/20.500.11937/32636