Summary of the paper
| Title | Extracting Product Features and Sentiments from Chinese Customer Reviews |
|---|---|
| Authors | Shu Zhang, Wenjie Jia, Yingju Xia, Yao Meng and Hao Yu |
| Abstract | With the growing interest in opinion mining from web data, more works arefocused on mining in English and Chinese reviews. Probing into the problem ofproduct opinion mining, this paper describes the details of our languageresources, and imports them into the task of extracting product feature andsentiment task. Different from the traditional unsupervised methods, asupervised method is utilized to identify product features, combining thedomain knowledge and lexical information. Nearest vicinity match and syntactictree based methods are proposed to identify the opinions regarding the productfeatures. Multi-level analysis module is proposed to determine the sentimentorientation of the opinions. With the experiments on the electronic reviews ofCOAE 2008, the validities of the product features identified by CRFs and thetwo opinion words identified methods are testified and compared. The resultsshow the resource is well utilized in this task and our proposed method isvalid. |
| Language | Semantics |
| Topics | Text mining, Information Extraction, Information Retrieval, Semantics |
Full paper  |
Extracting Product Features and Sentiments from Chinese Customer Reviews |
| Bibtex | @InProceedings{ZHANG10.583, author = {Shu Zhang, Wenjie Jia, Yingju Xia, Yao Meng and Hao Yu}, title = {Extracting Product Features and Sentiments from Chinese Customer Reviews}, booktitle = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10)}, year = {2010}, month = {may}, date = {19-21}, address = {Valletta, Malta}, editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios Piperidis, Mike Rosner, Daniel Tapias}, publisher = {European Language Resources Association (ELRA)}, isbn = {2-9517408-6-7}, language = {english} } |