内容信息与引文信息融合的作者影响力评价研究  

The Evaluation Research on Author’s Influence by Integrating the Content Information and Citation Information

作　　者：李秀霞 邵作运[2] 

机构地区：[1]曲阜师范大学传媒学院,山东日照276826 [2]曲阜师范大学图书馆,山东日照276826

出　　处：《情报理论与实践》2020年第2期72-77,共6页Information Studies:Theory & Application

基　　金：国家社会科学基金项目“文献内容分析与引文分析融合的知识挖掘与发现研究”的成果之一,项目编号:16BTQ074

摘　　要：[目的/意义]为弥补现有作者影响力评价指标缺乏内容信息的不足,发现不同研究主题下高影响力的作者,文章给出一种基于主题内容的作者影响力评价方法。[方法/过程]以情报学领域近5年核心期刊的文献为样本,首先利用CTM模型提取样本文献的主题,获得文献作者对不同主题的贡献值;再利用K-means算法对样本文献分类,由此将文献对应的作者划分到特定主题类别下;然后,将作者在某特定主题类别的贡献值与作者发表文献的平均被引频次相结合,设计特定主题类别下作者影响力指标(Author Influence Index in Specific Topic,AII-ST);最后,根据AII-ST值对作者进行影响力排序。[结果/结论]本研究在方法上,通过CTM模型与K-means算法的结合实现了K-means算法初始聚类中心与聚类数目的双重优化;在应用中,作者评价指标AII-ST值能有效限定作者的比较范围,较好地反映作者的研究方向;新指标评价视角新颖、评价结果可靠。[Purpose/significance]Although the index for evaluating the author’s influence are constantly evolving,there is still a lack of evaluation of the author’s influence in particular topic.In order to find high-impact authors in different research subject content,this paper presents an evaluation method of author impact based on topical content.[Method/process]Firstly,CTM model was used to extract the topic of author’s literature and obtain the author’s support in a certain topic.Then K-means algorithm was used to classify the sample literature,accordingly,the author was classified into a specific topic category through the classification of literature.Next,we defined the author influence index in specific topic by integrating the author’s support for a particular topic with the average citation frequency of the author’s published literature.At last,the authors are ranked according to their AII-ST values.[Results/conclusion]The empirical results show that the combination of CTM and K-means achieves the double optimization of K-means algorithm simultaneously on initial clustering center and number of clusters.And the integration of content and citation effectively compensates for the lack of content information in the existing evaluation index of authors’influence.In conclusion,the AII-ST value can effectively limit the author’s comparative range.This study provides a new research perspective,and the evaluation result is reliable.

关 键 词：作者影响力 内容信息 引文信息 信息融合 AII-ST值 

分 类 号：G353.1[文化科学—情报学]