Presentation 2016-06-18
An Evaluation of Feature Term Extraction Method based on Polarity Analysis from Customer Reviews
Tomofumi Yoshida, Daisuke Kitayama,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Our paper proposes a method, based on content-based recommendation, for extracting feature terms that can express product features from customer reviews on e-commerce sites. We define the features of a product as those features that reviewers considered them to be the advantages and disadvantages of a product. Therefore we extract them as features of the product that made a sufficiently strong impression on reviewers. The approach involves extracting opinion sentences from customer reviews, and recognizes each evaluated term as a candidate for product features. Using the positive opinion ratio of each candidate as the extent of how divided reviewers' opinions are, we extract the feature terms of the selected product by considering the feature score based on the positive opinion ratio. We conducted an experiment to evaluate the usefulness of extracted feature terms.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Customer reviews / text mining / extracting opinion expressions
Paper # DE2016-5
Date of Issue 2016-06-11 (DE)

Conference Information
Committee DE
Conference Date 2016/6/18(1days)
Place (in Japanese) (See Japanese page)
Place (in English) Rakuten Crimson House
Topics (in Japanese) (See Japanese page)
Topics (in English) Social Computing
Chair Masato Oguchi(Ochanomizu Univ.)
Vice Chair Makoto Onizuka(Osaka Univ.) / Masashi Toyoda(Univ. of Tokyo)
Secretary Makoto Onizuka(Kyushu Univ.) / Masashi Toyoda(Kogakuin Univ.)
Assistant Mayuki Ueda(Univ. of Marketing and Distrbution Science) / Shingo Otsuka(Kanagawa Inst. of Tech.)

Paper Information
Registration To Technical Committee on Data Engineering
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) An Evaluation of Feature Term Extraction Method based on Polarity Analysis from Customer Reviews
Sub Title (in English)
Keyword(1) Customer reviews
Keyword(2) text mining
Keyword(3) extracting opinion expressions
1st Author's Name Tomofumi Yoshida
1st Author's Affiliation Kogakuin University(Kogakuin Univ.)
2nd Author's Name Daisuke Kitayama
2nd Author's Affiliation Kogakuin University(Kogakuin Univ.)
Date 2016-06-18
Paper # DE2016-5
Volume (vol) vol.116
Number (no) DE-105
Page pp.pp.19-24(DE),
#Pages 6
Date of Issue 2016-06-11 (DE)