计算机与现代化 ›› 2021, Vol. 0 ›› Issue (03): 94-100.

• 数据库与数据挖掘 • 上一篇    下一篇

AC-Rec:基于多维特征的科研合作者推荐方法

  

  1. (河海大学计算机与信息学院,江苏南京211100)
  • 出版日期:2020-03-30 发布日期:2021-03-24
  • 作者简介:邵孟巧(1994—),女,河北晋州人,硕士研究生,研究方向:数据挖掘,文本挖掘,E-mail: 275182611@qq.com; 吉顺慧(1987—),女,讲师,博士,研究方向:软件建模、分析、测试与验证,E-mail: shunhuiji@hhu.edu.cn; 张鹏程(1981—),男,教授,硕士生导师,博士,研究方向:软件工程,数据挖掘,E-mail: pchzhang@hhu.edu.cn。
  • 基金资助:
    中央高校基本科研业务费专项基金资助项目(2019B15414); 国家自然科学基金资助项目(61702159); 江苏省自然科学基金资助项目(BK20170893)

AC-Rec: Academic Collaborators Recommendation Method Based on Multi-features

  1. (School of Computer and Information, Hohai University, Nanjing 211100, China)
  • Online:2020-03-30 Published:2021-03-24

摘要: 社交网络平台科研工作者数量的急剧增多使得寻找与自己兴趣相近的科研合作者变得十分困难。本文提出一种在ResearchGate平台下基于多维特征的科研合作者推荐方法。该方法结合科研工作者之间论文的文本相似度、社交关联度和自身活跃度3个维度来度量关联关系,并利用多层感知机构建推荐模型进行Top-N推荐。其中文本相似度利用Doc2Vec文本深度表示模型来计算,社交关联度利用基于图的随机游走算法来计算。实验结果显示AC-Rec优于已有的基于ResearchGate的科研合作者推荐方法,当N为30时命中率达到53.90%,能够有效地推荐潜在的科研合作者。

关键词: ResearchGate, 推荐, 多层感知机, 文本相似度, 社交关联度

Abstract: The rapid increase in the number of researchers on social network platform makes it very difficult to find academic collaborators with similar interests. This paper proposes a recommendation method for academic collaborators based on multi-features under ResearchGate platform. This method combines the three features of paper text similarity, social relevance and self-activity to measure the relationship, and uses the multi-layer perception mechanism to build a recommendation model for top-N recommendation. The text similarity is calculated by the Doc2Vec text depth representation model, and the social relevance is calculated by graph-based random walk algorithm. The experimental results show that AC-Rec is better than the existing academic collaborators recommendation methods based on ResearchGate platform. When N is 30, the hit rate reaches 53.90%, which can effectively recommend potential academic collaborators.

Key words: ResearchGate, recommendation, multi-layer perceptron, text similarity, social relevance