UofA | Computing Science | January 2012-1 |
Opinion Mining: Research and Application Challenges
(Independent Study)
Instructors: Osmar R. Zaïane (Computing Science)
|
Students: Afra Abnar, Maryam Tavafi Esmaeili, Amine Trabelsi
OBJECTIVE/DESCRIPTION:
Opinion Mining may be defined as the computational treatment and analysis of text in order to extract people's opinions. The recent availability of huge amounts of what is called "user-generated content" on the web, like forums' discussions, electronic reviews, and "tweets" produce a need to mine users' opinion. Undeniably, this data can provide business companies with an ideal framework to survey customers' opinions then develop products or design marketing strategies accordingly. Moreover, it can help people take decisions on buying products or voting for politicians by exposing other people opinions on the subject. Therefore, an elaborated system or a framework that analyses available data on the web and provides a better access to opinion and sentiment information is needed.
Building such a system raise several challenges. Basically, three predominant problems exist in opinion mining: (1) the opinion extraction problem; (2) the sentiment classification problem (labeling the polarity of a document as positive or negative); (3) the presentation/summarization problem.
The course will mainly consist of a series of discussions on topics relevant to opinion mining and sentiment analysis. It aims to:
- provide the students with an overview of the current state in Opinion Mining research and applications;
- give the students the opportunity to critically discuss the shortcomings of existing methods, as well as, comparing different used techniques (not much work has been done in this direction);
- detect possible improvement and/or design new solutions to opinion extraction, sentiment classification and presentation/summarization problems.
Workload:
The course will cover the following topics:
- Instructor and Students will meet weekly to discuss papers related to the topic.
- Students will prepare paper presentations for the research papers to be discussed.
- Students will write a literature review and annotated bibliography by the end of semester
- Students may have to do some algorithm implementations and testing to reproduce paper results.
A minimum of 10 research papers (per student) will be selected from a variety of journals, conference proceedings and other sources e.g.:
- Natural Language Engineering Journal;
- Foundations and Trends in Information Retrieval Journal;
- Proceedings of the International Conference on Artificial Intelligence and Law;
- Proceedings of the Annual Meeting on Association for Computational Linguistics;
- Proceedings of the International Conference on Language Resources and Evaluation;
- Proceedings of the ACM SIGKDD international conference on Knowledge discovery in data mining;
- Proceedings of the Conference on Empirical Methods in Natural Language Processing;
Examples of seed papers include:
- Pang, B. and Lee, L. 2008. "Opinion Mining and Sentiment Analysis." Found. Trends Inf. Retr. 2:1-135;
- Liu, B. 2009. Web Data Mining: Exploring Hyperlinks, Contents, and Usage Data (Data-Centric Systems and Applications): Springer;
- Esuli, A. and Fabrizio, S. 2006. "SENTIWORDNET: A Publicly Available Lexical Resource for Opinion Mining." Pp. 417-422 in 5th Conference on Language Resources and Evaluation;
- Tan, C. Lee, L. Tang, J. Jiang, L. Zhou, M. and Li, P. 2011. "User level sentiment analysis incorporating social networks." Pp. 1397-1405 in Proceedings of the 17th ACM SIGKDD
international conference on Knowledge discovery and data mining. San Diego, California, USA:
- Pak, A. and P. Paroubek. 2010. "Twitter as a corpus for sentiment analysis and opinion mining." in Proceedings of the Seventh International Conference on Language Resources and Evaluation;
- Paltoglou, G. and Thelwall, M. 2010. "A study of information retrieval weighting schemes for sentiment analysis." Pp. 1386-1395 in Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics. Uppsala, Sweden: Association for Computational Linguistics;
- Somasundaran, S. and Wiebe, J. 2010. "Recognizing stances in ideological on-line debates." Pp. 116-124 in Proceedings of the NAACL HLT 2010 Workshop on Computational Approaches to Analysis and Generation of Emotion in Text. Los Angeles, California: Association for Computational Linguistics;
- Yessenalina, Ainur, Yisong Yue, and Claire Cardie. 2010. "Multi-level structured models for document-level sentiment classification." Pp. 1046-1056 in Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing. Cambridge, Massachusetts: Association for Computational Linguistics;
- Palau. R. M. and Moens, M. F. 2009. "Argumentation mining: the detection, classification and structure of arguments in text." Pp. 98-107 in Proceedings of the 12th International Conference on Artificial Intelligence and Law.
GRADING:
Annotated Bibliography (20%), [due end of the semester]
Discussions (40%),
Final Survey paper (40%) [due end of the semester].
Distributed: January, 2012