标题：Riding the tide of sentiment change: sentiment analysis with evolving online reviews
作者：Yang Liu;Xiaohui Yu;Aijun An;Xiangji Huang
作者机构：[Liu, Y] School of Computer Science and Technology, Shandong University, Jinan, 250101, China;[ Yu, X] School of Computer Science and Technology, Shan 更多
通讯作者地址：[Yu, XH]Shandong Univ, Sch Comp Sci & Technol, Jinan 250101, Peoples R China.
来源：World wide web
关键词：sentiment analysis;adaptive algorithm;opinion mining
摘要：The last decade has seen a rapid growth in the volume of online reviews. A great deal of research has been done in the area of opinion mining, aiming at analyzing the sentiments expressed in those reviews towards products and services. Most of the such work focuses on mining opinions from a collection of reviews posted during a particular period, and does not consider the change in sentiments when the collection of reviews evolve over time. In this paper, we fill in this gap, and study the problem of developing adaptive sentiment analysis models for online reviews. Given the success of latent semantic modeling techniques, we propose two adaptive methods to capture the evolving sentiments. As a case study, we also investigate the possibility of using the extracted adaptive patterns for sales prediction. Our proposal is evaluated on an IMDB dataset consisting of reviews of selected movies and their box office revenues. Experimental results show that the adaptive methods can capture sentiment changes arising from newly available reviews, which helps greatly improve the prediction accuracy.