随着社交媒体的发展,用户之间的关系网络对于社交媒体的分析有很大的帮助。因此,该文主要研究用户好友关系检测。以往的关于用户好友关系抽取的研究主要基于社交媒体上的结构化信息,比如其他好友关系,用户的不同属性等。但是,很多时候用户本身并没有大量的好友信息存在,同时也不一定有很多确定的属性。因此,我们希望基于用户发表的文本信息来对用户关系进行预测。不同于以往的潜在好友推荐算法,该文提出了一种基于注意力机制以及长短时记忆网络(long short-term memory,LSTM)的好友关系预测模型,将好友之间的评论分开处理,通过分析用户之间的评论来判断是否具备一定的好友关系。该模型将好友双方信息拼接后的结果作为输入,并将注意力机制应用于LSTM的输出。实验表明,用户之间的评论对于好友关系预测确实有较大的实际意义,该文提出的模型较之于多个基准系统的效果,取得了明显的提升。在不加入任何其它非文本特征的情况下,实验结果的准确率达到了77%。
Abstract
With the development of social media, the relationship network between users has greatly helped the analysis of social media. Focusing on predicting the user relationship based on the text information published by the user, this paper proposes a friendship prediction model based on attention mechanism and Long Short-Term Memory(LSTM), which separates the comments between friends, and determines whether there is a certain friend relationship by analyzing the users comments. This model takes as input the concatenated results of the two friends and applies the attention mechanism to the output of the LSTM. Experiment shows that the proposed model achieved an accuracy of 77% without adding any other non-text features.
关键词
好友判断 /
关系预测 /
社交网络 /
注意力机制
{{custom_keyword}} /
Key words
friend judgment /
relationship prediction /
social network /
attention mechanism
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Ramesh R.Sarukkai. Link prediction and path analysis using Markov chains[J]. Computer Networks, 2000, 33(1-6): 377-386.
[2] Liben-Nowell D, Kleinberg J. The link prediction problem for social networks[C]//Proceedings of the Wiley Subscription Services, Inc. A Wiley Company, 2003: 556-559.
[3] Taskar B, et al. Link prediction in relational data[C]//Proceedings of the International Conference on Neural Information Processing Systems. MIT Press, 2003: 659-666.
[4] Hasan Mohammad AI, et al. Link Prediction using Supervised Learning[C]//Proceedings of Sdm Workshop on Link Analysis Counterterrorism and Security, 2006, 30(9): 798-805.
[5] Menon A K, Elkan C. Link prediction via matrix factorization[C]//Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases. Springer-Verlag, 2011: 437-452.
[6] Sarwar B, et al. Item-based collaborative filtering recommendation algorithms[C]//Proceedings of the International World Wide Web Conference, 2001: 285-295.
[7] Linden G, Smith B, York J. Amazon.com Recommendations: Item-to-Item Collaborative Filtering[J]. IEEE Internet Computing, 2003, 7(1): 76-80.
[8] Liu Z, Shi C, Sun M.FolkDiffusion: A Graph-Based Tag Suggestion Method for Folksonomies[C]//Proceedings of the Information Retrieval Technology, Asia Information Retrieval Societies Conference, Airs 2010, DBLP, 2010: 231-240.
[9] Marlow C, Find me if you can: improving geographical prediction with social and spatial proximity[C]//Proceedings of International Conference on World Wide Web. ACM, 2010: 61-70.
[10] Tu H, Wang X. Mining users interest graph in social networks with topic based tag propagation[C]//Proceedings of Iet International Conference on Smart and Sustainable City. IET, 2014: 282-285.
[11] Qian X, et al. Personalized Recommendation Combining User Interest and Social Circle[J]. IEEE Transactions on Knowledge & Data Engineering, 2014, 26(7): 1763-1777.
[12] Elson D K, Dames N,Mckeown K R. Extracting social networks from literary fiction[C]//Proceedings of Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, 2010: 138-147.
[13] Qiu M, Liu Y, Jiang J. Mining User Relations from Online Discussions using Sentiment Analysis and Probabilistic Matrix Factorization[C]//Proceedings of NAACL. 2011.
[14] Shen D, Sun J T, Yang Q, et al. Latent Friend Mining from Blog Data[C]//Proceedings of International Conference on Data Mining. IEEE Computer Society, 2006: 552-561.
[15] Liu Z, Chen X, Sun M. Mining the interests of Chinese microbloggers via keyword extraction[J]. Frontiers of Computer Science, 2012, 6(1): 76-87.
[16] Xu J, et al. Open Relation Extraction from Chinese Microblog Text[C]//Proceedings of IEEE International Conference on Data Science in Cyberspace. IEEE, 2017: 673-677.
[17] 闫旸, 等. 面向文本标题的人物关系抽取[J]. 计算机应用, 2016, 36(3): 726-730.
[18] 赵亚辉, 刘瑞. 基于评论的隐式社交关系在推荐系统中的应用[J]. 计算机应用研究, 2016, 33(6): 1628-1632.
[19] 王中卿, 李寿山, 周国栋. 基于文本与社交信息的用户群组识别[J]. 软件学报, 2017, 28(9): 2468-2480.
[20] 黄宏程, 等. 用户兴趣相似性度量的关系预测算法[J]. 计算机科学与探索, 2017, 11(7): 1068-1079.
[21] 王啸岩, 袁景凌, 秦凤. 位置社交网络中基于评论文本的兴趣点推荐[J]. 计算机科学, 2017(12).
[22] 邱云飞, 等. 基于微博短文本的用户兴趣建模方法[J]. 计算机工程, 2014, 40(2): 275-279.
[23] Bahdanau D, Cho K, Bengio Y. Neural Machine Translation by Jointly Learning to Align and Translate[J]. arXiv: 1409.0473v2.2014.
[24] Kingma D P, Ba J. Adam: A Method for Stochastic Optimization[J]. arXiv: 1412.6980v8.2014.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(61331011,61672366)
{{custom_fund}}
PDF(933 KB)
