一种基于主题提取和情感分析的图书评价方法  

A Book Evaluation Method Based on Topic Extraction and Sentiment Analysis

作　　者：刘敬涛 李秀霞 邵作运[2] Liu JingTao;Li Xiuxia;Shao Zuoyun(School of Communication Qufu Normal University,Qufu Shangdong 276800;Qufu Normal University Rizhao Campus Library,Rizhao Shangdong 276827)

机构地区：[1]曲阜师范大学传媒学院,山东曲阜276800 [2]曲阜师范大学日照校区图书馆,山东日照276827

出　　处：《情报探索》2022年第5期43-49,共7页Information Research

摘　　要：[目的/意义]提出一种基于评论主题提取和情感分析的图书评价新方法,不仅丰富了中文图书评价体系,也为其他学术成果的评价提供了一种可借鉴的思路。[方法/过程]首先,利用LDA主题模型提取图书评论的主题集;再对读者关注的主题进行NLP情感识别;然后利用模糊综合评价法实现图书的综合评价;最后以63本儿童文学图书为例进行实证研究,并通过替代计量评价方法的检验,证明了该方法的有效性。[结果/结论]该方法不仅缓解了当前图书评价方式和读者需求的错位问题,丰富了图书展示理念,也为识别优秀小众图书提供了方法借鉴。[Purpose/significance]This paper proposes a new book evaluation method based on review topic extraction and sentiment analysis which not only enriches the Chinese book evaluation system but also provides a referenceable idea for other academic achievement evaluation.[Method/process]Firstly LDA topic model is used to extract topic set of book reviews;then NLP emotion recognition is carried out on readers’attention topic;then fuzzy comprehensive evaluation method is used to realize books’comprehensive evaluation;finally 63 children literature books are taken as an example for empirical research and the validity of the method is proved by alternative measurement evaluation method test.[Result/conclusion]This study not only alleviates mismatch problem between current book evaluation methods and readers’needs enriches book display concept but also provides a method for identifying excellent minority books.

关 键 词：在线评论 主题提取 情感分析 替代计量 

分 类 号：G353[文化科学—情报学]