科研社交网站中基于相似兴趣的学者推荐研究  

Research on Scholar Recommendation Based on Similar Interest in Scientific Social-Networking Sites

作　　者：熊回香[1] 杨雪萍[1] 蒋武轩 陆颖颖[1] 

机构地区：[1]华中师范大学信息管理学院,湖北武汉430079

出　　处：《情报科学》2017年第9期3-11,共9页Information Science

基　　金：国家社会科学基金项目(12BTQ038)

摘　　要：【目的/意义】研究科研社交网站中的学者推荐有利于增强学术合作、提升科研人员学术交流,对科研工作具有深远意义。【方法/过程】从学者知识结构和学术行为网络两个维度出发,构建基于相似兴趣的学者推荐模型,挖掘分析学者知识结构特征、学者间合作网络、机构间合作网络关系,计算学者在这三个层面上的相似度并进行整合实现学者推荐。最后以百度学术学者主页数据为例验证模型的可用性与有效性。【结果/结论】结果表明:模型能够有效解决科研社交网站信息过载和不对称的问题,满足可操作性和推荐结果有效性。【Purpose/significance】Scholars recommendation in the social networking site is beneficial to enhance academic cooperation and scientific research personnel academic exchanges,it has far-reaching significance to scientific research work.【Method/process】Based on the two dimensions of scholar knowledge structure and academic behavior network,we construct the scholarship model based on similar interest,explore scholar knowledge structure,cooperative relationship and institutional neighborhood.Through the comb strategy to integrate the measured value of the scholars to calculate the similarity between the degree of interest for scholars to recommend,and take Baidu academic scholar data as an example to verify the effectiveness of recommendation.【Result/conclusion】The research shows that the model can effectively solve the problem of information overload and asymmetry in scientific research social website,and has the advantages of operability and recommendation.

关 键 词：科研社交网站 个性化推荐 语义挖掘 社交网络分析 

分 类 号：G252.0[文化科学—图书馆学]