基于动态网络表示学习的学者合作关系预测研究  

Prediction of Scholar Cooperation Relationship Based on Dynamic Network Representation Learning

作　　者：李一帆 王玙[1] LI Yi-fan;WANG Yu(School of Economics and Management,Xidian University,Xi'an 710071,China)

机构地区：[1]西安电子科技大学经济与管理学院,陕西西安710071

出　　处：《情报科学》2022年第6期115-123,共9页Information Science

基　　金：国家自然科学基金面上项目“知识社区的资源语义空间及其检索研究”(71573199)。

摘　　要：【目的/意义】随着学科交叉与学科融合的不断深入,科研工作越来越需要多个学者合作完成。识别潜在的合作关系,为学者推荐适合的合作对象,能有效提高科研效率。【方法/过程】基于动态网络表示学习模型对学者合作关系预测展开研究。首先,提出一种动态网络表示学习模型DynNE_Atten。其次,根据图书情报领域的文献数据构建动态科研合作网络和动态关键词共现网络,使用DynNE_Atten模型得到作者向量表示和关键词向量表示,同时提取作者单位特征。最后,融合作者合作、主题与单位特征,预测未来可能产生的合作。【结果/结论】实验结果表明,本文提出的动态网络表示学习模型在时序链路预测任务中只需要较少的输入数据,就能达到较高的准确性;相比于未融合特征的学者表示,融合模型在合作关系预测中展现出明显的优势。【创新/局限】提出了一种新的动态网络表示学习模型,并融合主题特征和作者单位特征进行科研合作预测,取得了较好的结果。目前模型在特征融合的方式上只考虑了数据层面的异构,并未考虑网络层面的异构。【Purpose/significance】With the continuous deepening of interdisciplinary and fusion of disciplines,scientific research work increasingly requires the cooperation of multiple scholars.Identifying potential cooperation relationships and recommending suitable partners for scholars can effectively improve the efficiency of scientific research.【Method/process】This study is based on the dynamic network representation learning model to study the cooperation relationship prediction of scholars.First,a dynamic network representation learning model DynNE_Atten is proposed.Secondly,use the data in the field of library and information to construct a dynamic scientific research cooperation network and a dynamic keyword co-occurrence network.And then obtain the author vector representation and keyword vector representation through the DynNE_Atten model.At the same time,we obtain affiliation units of authors.Finally,it integrates the characteristics of the author’s cooperation,theme and unit characteristics to predict the possible future cooperation.【Result/conclusion】The experimental results show that the dynamic network representation learning model proposed in this paper only needs fewer input samples in the time series link prediction task,and can achieve higher accuracy;compared with the scholars without fusion features.The fusion model shows obvious advantages in the prediction of cooperative relations.[Innovation/limitations] This study proposes a new dynamic network representation learning model,and then combines topic features and features of author’s affiliation to predictions scientific research cooperation,which has achieved good results.However,the method only considers the heterogeneity of data in the feature fusion method and doesn’t consider the heterogeneity of the network.

关 键 词：动态网络表示学习 合作关系预测 特征融合 主题特征 作者单位特征 时序链路预测 

分 类 号：G316[文化科学]