ABSTRACT
In this paper, we address the problem of author extraction (AE) from user generated content (UGC) pages. Most existing solutions for web information extraction, including AE, adopt supervised approaches, which require expensive manual annotation. We propose a novel unsupervised approach for automatically collecting and labeling training data based on two key observations of author names: (1) people tend to use a single name across sites if their preferred names are available; (2) people tend to create unique usernames to easily distinguish themselves from others, e.g. travelbug61. Our AE solution only requires features extracted from a single UGC page instead of relying on clues from multiple UGC pages. We conducted extensive experiments. (1) The evaluation of automatically labeled author field data shows 95.0% precision. (2) Our method achieves an F1 score of 96.1%, which significantly outperforms a state-of-the-art supervised approach with single page features (F1 score: 68.4%) and has a comparable performance to its multiple page solution (F1 score: 95.4%). (3) We also examine the robustness of our approach on various UGC pages from forums and review sites, and achieve promising results as well.
- F. Abel, N. Henze, E. Herder, and D. Krause. Interweaving public user profiles on the web. UMAP, 2010. Google ScholarDigital Library
- C.-C. Chang and C.-J. Lin. LIBSVM: A library for support vector machines. ACM TIST, 2011. Google ScholarDigital Library
- D. Gruhl, R. Guha, D. Liben-Nowell, and A. Tomkins. Information diffusion through blogspace. In WWW, 2004. Google ScholarDigital Library
- J. Liu, Y. Song, and C. Lin. Competition-based user expertise score estimation. In SIGIR, 2011. Google ScholarDigital Library
- P. Luo, F. Lin, Y. Xiong, Y. Zhao, and Z. Shi. Towards combining web classification and web information extraction: a case study. In SIGKDD, 2009. Google ScholarDigital Library
- M. Newman. Communities, modules and large-scale structure in networks. Nature Physics, 2011.Google Scholar
- X. Song, J. Liu, Y. Cao, C. Lin, and H. Hon. Automatic extraction of web data records containing user-generated content. In CIKM, 2010. Google ScholarDigital Library
- K. Wang, C. Thrasher, and B. Hsu. Web scale nlp: A case study on url word breaking. In WWW, 2011. Google ScholarDigital Library
- K. Wang, C. Thrasher, E. Viegas, X. Li, and B. Hsu. An overview of microsoft web n-gram corpus and applications. In NAACL, 2010. Google ScholarDigital Library
- J. Yang, R. Cai, Y. Wang, J. Zhu, L. Zhang, and W. Ma. Incorporating site-level knowledge to extract structured data from web forums. In WWW, 2009. Google ScholarDigital Library
- Y. Zhai and B. Liu. Web data extraction based on partial tree alignment. In WWW, 2005. Google ScholarDigital Library
- J. Zhu, Z. Nie, J. Wen, B. Zhang, and W. Ma. Simultaneous record detection and attribute labeling in web data extraction. In SIGKDD, 2006. Google ScholarDigital Library
Index Terms
- An unsupervised method for author extraction from web pages containing user-generated content
Recommendations
Unsupervised user-generated content extraction by dependency relationships
WISE'11: Proceedings of the 12th international conference on Web information system engineeringUser-generated contents are very valuable for event detection, opinion mining and so on, but the extraction of those data is difficult because users are given strong power to present their contents in Web 2.0 pages. Compared to machine-generated contents,...
Unsupervised named-entity extraction from the Web: An experimental study
The KnowItAll system aims to automate the tedious process of extracting large collections of facts (e.g., names of scientists or politicians) from the Web in an unsupervised, domain-independent, and scalable manner. The paper presents an overview of ...
Acronym extraction and disambiguation in large-scale organizational web pages
CIKM '09: Proceedings of the 18th ACM conference on Information and knowledge managementIn this paper, we focus on the automatic extraction and disambiguation of acronyms in large-scale organizational web pages, which is important but difficult due to the diversity of acronyms and the scale of organizational web pages. We propose two novel ...
Comments