Review Mining Using Lexical Knowledge and Modality Analysis

Review Mining Using Lexical Knowledge and Modality Analysis
Review Mining; Natural Laguage Processing; Social Media Analysis; lexical knowledge; modality analysis; salient word; collocation
Issue Date
International Universal Communication Symposium
The vast number of product and service reviews is an important source of information discovery. However, it is complicated to obtain valuable information from them because most of them are not easily readable by machine. In this paper, we present a method for mining Korean restaurant and movie reviews and extracting precious information. There can be various features on which the reviewers express their opinions. For each feature word, we identify the relevant opinion words, and obtain some valid feature-opinion pairs. For review mining, we first recognize domain knowledge, and then extract feature-opinion pairs by utilizing the domain knowledge. The performance of the knowledge recognition phase is very important, because the feature-opinion extraction phase is performed on the region identified at the recognition phase. In this study, in order to improve the performance of knowledge recognition, we use domain-salient words as lexical knowledge obtained by corpus comparison. In addition, we utilize likelihood ratio-based collocations gained from corpus. Experimental results show that the performance of feature-opinion extraction can be improved by utilizing modality analysis. We also compare the rating of the proposed method against the star rating. The result demonstrates that the proposed method considerably improves the performance of estimating user's rating.
Appears in Collections:
KIST Publication > Conference Paper
Files in This Item:
There are no files associated with this item.
RIS (EndNote)
XLS (Excel)


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.