基于话语标记理论的在线商品评分修正方法  

A Correction Method for Score Deviation of Online Product Reviews Based on Discourse Markers Theory

作　　者：王伟军[1,2,3] 宋艳秋[2,3] 张婷婷[2,3] 黄英辉[2,3] 陈博洋[2,3] 

机构地区：[1]上海外国语大学国际工商管理学院,上海200083 [2]华中师范大学信息管理学院,武汉430079 [3]华中师范大学青少年网络心理与行为教育部重点实验室,武汉430079

出　　处：《情报学报》2016年第4期358-368,共11页Journal of the China Society for Scientific and Technical Information

基　　金：国家自然科学基金项目(71271099;71571084;71471019);国家留学基金资助项目(201506775025)的研究成果之一

摘　　要：尽管在线商品评论是消费者购买决策的重要依据之一,然而现实中评论内容与评分间的不一致将对购买决策的制订形成干扰,折射出解决评论与评分真实性问题的重要性和现实性。当前关于评论与评分偏差的研究主要围绕语法、语义层面进行,矫正的效果和速度存在较大局限。本文则在语义与语用层面,通过引入语言学的话语标记理论,构建商品评论话语标记语库,设计包含可信度、评论立场、情感态度的评分修正体系,并采用改进后层次分析法得到各评价指标的权重,提出评论评分偏差的修正方法;最后,通过京东商城的真实评论数据修正结果验证了本方法的可行性和有效性,从而深化并拓展了对在线商品评论分析的研究。Online product reviews is an important information source which affects consumer purchasing decisions deeply, but the inconsistency between review content and score could bring troubles to the process of decisions-making. So solving reviews authenticity becomes significant and realistic. The current researches on correction of comments deviation are mainly from the perspective of grammatical or semantic level, thus there is a great limitation on the effect and speed of correction. Therefore, in the semantic and pragmatic level, this paper attempts to introduces one linguistics theory- Discourse Markers -to make a correction by analyzing the content of review. Firstly, this paper builds a library of discourse markers in the field of online product reviews and designs a correction system including credibility, position, emotional attitude. Then, this paper gets the weight of each index through improved analytic hierarchy process and proposes an algorithm to correct deviation of reviews scores. At last, the results of example verification of Jingdong mall show the correction method has better feasibility and validity, which deepens and expands the research of online product reviews.

关 键 词：在线商品评论 在线商品评分 评分偏差 话语标记 

分 类 号：F713.55[经济管理—市场营销]