A Study on Classifications of Useful Customer Reviews by Applying Text Mining Approach

Abstract

Abstract Submitted：July 20, 2015 1 st Revision：September 20, 2015 Accepted：September 29, 2015*본 연구는 2013년 교육부의 재원으로 한국연구재단의 지원을 받아 수행된 연구이며(NRF-2013S1A5A2A01018177), 2014년도 가톨릭대학교의 교비연구비의 지원도 받았음. ** 가톨릭대학교 경영학부 Customer reviews are one of the important sources for purchase decision makings in online stores. Online stores have tried to provide useful reviews in product pages to custom ers. To assess the usefulness of customer reviews before other users have voted enough on the reviews, diverse as pects of reviews were utilized in prevous studies. Style and semantic information were utilized in many studies. This study aims to test diverse alogrithms and datasets for ide ntifying a proper classification method and threshold to classify useful reviews. In particular, most researches util ized ratio type helpfulness index as Amazon.com used. However, there is another type of usefulness index utilized in TripAdviser.com or Yelp.com, count type helpfulness index. There was no proper threshold to classify useful reviews yet fo r count type helpfulness index. This study used reivews and their usefulness votes on restaurnats from Yelp.com to devi se diverse datasets and applied text mining approaches to classify useful reviews. Random Forest, SVM, and GLMNET showed the greater values of accuracy than other approaches.