边信息嵌入的学术论文推荐算法研究

doi:10.3778/j.issn.1002-8331.2104-0143

摘要/Abstract

摘要： 为了解决论文推荐领域中的数据稀疏性问题，研究人员通常会引入论文的辅助信息进行改进。然而，目前的研究大多集中于辅助信息的语义关联性，没有考虑到不同辅助信息对论文的重要性也不同。同时，在论文的网络表示领域中，随机游走的方法忽略了论文属性对论文引用关系的影响。针对这两个问题，提出了一种基于引文辅助信息嵌入的推荐方法（CERec）。首先提取论文的多种质量因素构成影响力数值，将其作为论文权重来构造影响力网络。然后将论文的影响力与引文信息结合，利用论文的多种辅助信息进行图嵌入。最后通过论文嵌入向量的余弦相似度得到推荐结果。离线实验结果表明，结合辅助信息的方法优于不结合辅助信息的方法，同时CERec相较于目前比较流行的向量表示推荐算法在召回率和NDCG上平均提高了5.054%和5.246%。

关键词: 论文推荐, 影响力网络, 边信息, 图嵌入, 冷启动

Abstract: In order to solve the problem of data sparsity in the paper recommendation, researchers usually use side information of the paper for improvement. Most of the current research focuses on the semantic relevance of side information, and does not consider that the importance of different side information to the paper is also different. Random walk method ignores the influence of paper attributes on paper citation relationships. Considering the above challenges, this paper proposes an academic paper recommendation approach based on citation side information embedding（CERec）. Firstly, it extracts the various quality factors to form the influence value, and uses it as the paper weight to construct the influence network. Then, it combines the influence of the paper with the citation information, and embeds it with the side information. Finally, it calculates the cosine similarity of the embedding vector to get the recommended list. The experimental results demonstrate that the method combining side information is better than the method not combining side information. Compared with the current popular representation recommendation algorithms, CERec has improved the recall rate and NDCG by an average of 5.054% and 5.246%.

Key words: paper recommendation, influence network, side information, graph embedding, cold start

沈小烽, 刘柏嵩, 吴俊超, 钱江波. 边信息嵌入的学术论文推荐算法研究[J]. 计算机工程与应用, 2022, 58(22): 165-171.

SHEN Xiaofeng, LIU Baisong, WU Junchao, QIAN Jiangbo. Academic Paper Recommendation Based on?Side Information Embedding[J]. Computer Engineering and Applications, 2022, 58(22): 165-171.

参考文献

[1] STEINERT L，CHOUNTA I A，HOPPE H U.Where to begin? Using network analytics for the recommendation of scientific papers[C]//CYTED-RITOS International Workshop on Groupware，Yerevan，Sep 22-25，2015.Cham：Springer，2015：124-139.
[2] SAKIB N，AHMAD R B.A hybrid personalized scientific paper recommendation approach integratingpublic contextual metadata[J].IEEE Access，2021，9：83080-83091.
[3] ZHAO X，KANG H.A hybrid model based on LFM and BiGRU toward research paper recommendation[J].IEEE Access，2020，8：188628-188640.
[4] CUI P，WANG X，PEI J，et al.A survey on network embedding[J].IEEE Transactions on Knowledge and Data Engineering，2018，31（5）：833-852.
[5] YADAV P，REMALA N，PERVIN N.RecCite：a hybrid approach to recommend potential papers[C]//2019 IEEE International Conference on Big Data，Los Angeles，Dec 9-12，2019：2956-2964.
[6] LIU H W，KOU H Z.Keywords-driven and popularity-aware paper recommendation based on undirected paper citation graph[J].Complex，2020：2085638.
[7] TANNER W，AKBAS E，HASAN M.Paper recommendation based on citation relation[C]//2019 IEEE International Conference on Big Data，Los Angeles，Dec 9-12，2019：3053-3059.
[8] PAUDEL B，BERNSTEIN A.Random walks with erasure：diversifying personalized recommendations on social and information networks[J].arXiv：2102.09635，2021.
[9] YI L A，RW A，GN A.A personalized paper recommendation method considering diverse user preferences[J].Decision Support Systems，2021，146：113546.
[10] ALI Z，QI G，MUHAMMAD K.Paper recommendation based on heterogeneous network embedding[J].Knowledge-Based Systems，2020，210：106438.
[11] ZHAO Z，ZHANG X，ZHOU H，et al.HetNERec：heterogeneous network embedding based recommendation[J].Knowledge-Based Systems，2020，204：106218.
[12] XIE F，ZHENG A，CHEN L，et al.Attentive meta-graph embedding for item recommendation in heterogeneous information networks[J].Knowledge-Based Systems，2021，211：106524.
[13] WU H，ZHOU Q，NIE R，et al.Effective metric learning with co-occurrence embedding for collaborative recommendations[J].Neural Networks，2020，124：308-318.
[14] CHEN X，ZHAO H，ZHAO S，et al.Citation recommendation based on citation tendency[J].Scientometrics，2019，121（2）：937-956.
[15] ZHANG Y，MA Q.Citation recommendations considering content and structural context embedding[C]//2020 IEEE International Conference on Big Data and Smart Computing，Busan，Feb 19-22，2020：1-7.
[16] KONG X，MAO M，WANG W，et al.VOPRec：vector representation learning of papers with text information and structural identity for recommendation[J].IEEE Transactions on Emerging Topics in Computing，2021：9（1）：226-237.
[17] WANG J，HUANG P，ZHAO H，et al.Billion-scale commodity embedding for e-commerce recommendation in Alibaba[C]//24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining，London，Aug 19-23，2018：839-848.
[18] PEROZZI B，AL-RFOU R，SKIENA S.Deepwalk：online learning of social representations[C]//20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining，New York，Aug 24-27，2014：701-710.
[19] GROVER A，LESKOVEC J.Node2vec：scalable feature learning for networks[C]//22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining，San Francisco，Aug 13-17，2016：855-864.
[20] LE Q，MIKOLOV T.Distributed representations of sentences and documents[C]//31st International Conference on Machine Learning，Beijing，Jun 21-26，2014：1188-1196.
[21] HEKMATFAR T，HARATIZADEH S，GOLIAEI S.Embedding ranking-oriented recommender system graphs[J].Expert Systems with Applications，2021，181：115108.