基于引用情感的论文学术影响力评价方法研究  

A Method to Evaluate the Academic Influence of Papers Based on Citation Sentiment

作　　者：耿树青 杨建林[1,2] 

机构地区：[1]南京大学信息管理学院,江苏南京210023 [2]江苏省数据工程与知识服务重点实验室,江苏南京210023

出　　处：《情报理论与实践》2018年第12期93-98,共6页Information Studies:Theory & Application

基　　金：江苏省社会科学基金重大项目"习近平总书记构建中国特色哲学社会科学重大命题研究"的成果;项目编号:16ZD004

摘　　要：[目的/意义]根据论文的被引次数来判断其学术影响力的高低,是目前最普遍的论文评价方法,但是被引次数指标忽视了引用内容的差异性,本研究试图加入引用情感这一因素,在被引次数评价指标基础上做出改进。[方法/过程]文章提出一种基于"被引次数—引用情感"CS指标的引用情感评价方法,利用层次分析法确定引用情感权重并给出CS指标的计算公式,通过实例验证新方法的可行性和现实效果。[结果/结论]实验结果表明,CS指标综合考虑了被引次数和引用情感两种因素,与单纯的被引次数指标相比,对论文学术影响力的评价更加全面,区分能力更强,未来可能成为一种单篇论文学术影响力的评价指标。[Purpose/significance]The most frequently used evaluation method of papers is to judge their academic influence by citations.However,this evaluation method ignores the difference of citation content,so this paper aims to make improvements on the citation frequencies by introducing the factor of citation sentiment.[Method/process]The paper proposes a method of citation sentiment evaluation based on "citation-sentiment"(CS)index.To verify the feasibility and effectiveness of the new method, the paper designs and implements an experiment by defining the citation sentiment weight based on Analytic Hierarchy Process and presenting the formula of CS index.[Result/conclusion]The experimental results show that the CS index considers both citation frequency and citation sentiment.Compared with simply using citation frequency,CS index makes a more comprehensive evaluation of the academic influence of papers and has a stronger ability to distinguish papers,which may be used as an evaluation index for the academic influence of a single paper in the future.

关 键 词：学术论文 学术评价 学术影响力 情感分析 被引次数 

分 类 号：G353.1[文化科学—情报学]