针对用户在社交网络应用中的影响力评价方法，以往的研究重点关注网络结构和转发行为对用户影响力的影响，基于用户发布内容和主题的影响力评估研究较少，且未考虑主题间的交互关系.为此提出了一种半监督的主题提取方法，通过在初始化过程中引入种子词并赋予不同的权重，更好地提取目标主题.此外，为了提高用户影响力评估的效果，该文考虑了不同主题之间的交互，将主题之间的相似性叠加于用户相似性的计算.在真实数据上的实验结果验证了所提方法的有效性.
Previous studies on user influence modeling in social networks mostly depend on user friendship network structures and retweeting behaviors. It lacks of the consideration of contents and topics of the tweets, which may also play important roles. In addition, taking the interaction among topics into account would facilitate a more accurate user influence modeling. In this paper, we propose a semi-supervised topic extraction method, which brings in a set of seed words during initialization and assigns these seed words higher weights than other words, to improve the effectiveness of topic extraction. To better model the user influence, we involve the interactions among topics, and combine the similarity of topics together with the similarity of users. Experimental results on real-world datasets demonstrate the effectiveness of our proposed methods.
[1] Weng J S, Lim E P, Jiang J, et al. TwitterRank:finding topic-sensitive influential Twitterers[C]//Proceedings of the 2010 ACM International Conference on Web Search and Data Mining, New York, USA, 2010:261-270.
[2] 毛佳昕,刘奕群,张敏,等.基于用户行为的微博用户社会影响力分析[J].计算机学报,2014, 37(4):791-800. Mao J X, Liu Y Q, Zhang M, et al. Social influence analysis for micro-blog user based on user behavior[J]. Chinese Journal of Computers, 2014, 37(4):791-800(in Chinese)
[3] 周东浩,韩文报. DiffRank:一种新型社会网络信息传播检测算法[J].计算机学报,2014, 37(4):884-893. Zhou D H, Han W B. DiffRank:a novel algorithm for information diffusion detection in social networks[J]. Chinese Journal of Computers, 2014, 37(4):884-893.(in Chinese)
[4] Wu J, Sha Y, Li R, et al. Identification of influential users based on topic-behavior influence tree in social networks[C]//Proceedings of the 6th Conference on Nature Language Processing and Chinese Computing, 2017:477-489.
[5] 刘威,张明新,安德智.面向微博话题的用户影响力分析算法[J].计算机应用,2019, 39(1):213-219. Liu W, Zhang M X, An D Z. User influence analysis algorithm for Weibo topics[J]. Journal of Computer Applications, 2019, 39(1):213-219.(in Chinese)
[6] Su S, Wang Y K, Zhang Z B, et al. Identifying and tracking topic-level influencers in the microblog streams[J]. Machine Learning, 2017, 107(3):551-578.
[7] Welcome to Guided LDA's documentation[CP/OL].[2019-10-17] https://guidedlda.readthedocs.io/en/latest/.
[8] Wang C, Cao L B, Wang M C, et al. Coupled nominal similarity in unsupervised learning[C]//Proceedings of the 20th ACM International Conference on Information and Knowledge Management. ACM, 2011:973-978.
[9] Zhang J, Liu B, Tang J, et al. Social influence locality for modeling retweeting behaviors[C]//Proceedings of the 23rd International Joint Conference on Artificial Intelligence (IJCAI013), Beijing, China, 2013:2761-2767.
[10] Zhao X W, Jiang J, Weng J S, et al. Comparing twitter and traditional media using topic models[C]//Advances in Information Retrieval-33rd European Conference on IR Research, ECIR 2011, Dublin, Ireland:Springer-Verlag, 2011:338-349.
[11] Hu M T, Hang G, Zhou J M, et al. A method for measuring social influence of micro-blog based on user operations[C]//Proceedings of the 2017 International Conference information Technology and Applications, Sydney, ICITA, 2017:82-87.
[12] Kempe D, Kleinberg J, Tardos A. Maximizing the spread of influence through a social network[C]//Proceedings of the 9th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Washington, USA, 2003:137-146.
[13] Pal A, Counts S. Identifying topical authorities in microblogs[C]//Proceedings of the 4th ACM International Conference on Web Search and Data Mining, Hong Kong, China, 2011:45-54.
[14] Pang X W, Wan B S, Li H F, et al. MR-LDA:an efficient topic model for classification of short text in big social data[J]. International Journal of Grid and High Performance Computing, 2016, 8(4):100-113.
[15] Gotez M, Leskovec J, Mcglohom M. Modeling blog dynamics[C]//Proceedings of the 2009 International Conference on Weblogs and Social Media, Menlo Park, CA:AAAI Press, 2009:26-33.
[16] Li Z, Li M, Ji W. Modelling the public opinion transmission on social networks under opinion leaders[C]//AEECE 2017:Proceedings of the 20173rd International Conference on Advances in Energy, Environment and Chemical Engineering, Bristol:IOP Publishing, 2017:012215.
[17] Chen Z, Taylor K. Modeling the spread of influence for independent cascade diffusion process in social networks[C]//Proceedings of the 2017 International Conference on Distributed Computing Systems Workshops. Piscataway, NJ, USA, 2017:151-156.
[18] Luarn P, Yang J C, Chiu Y P. The network effect on information dissemination on social network sites[J]. Computers in Human Behavior, 2014, 37(37):1-8.
[19] Bakshy E, Hofman J M, Mason W A, et al. Everyone's an influencer:quantifying influence on Twitter[C]//Proceedings of the 4th ACM International Conference on Web Search and Data Mining, Hong Kong, China, 2011:65-74.
[20] Heinz D C, Chang C I. Fully constrained least squares linear spectral mixture analysis method for material quantification in hyperspectral imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2001, 39(3):529-545.
[21] Zhang J, Tang J, Li J Z, et al. Who influenced you?Predicting retweet via social influence locality[J]. ACM Transactions on Knowledge Discovery from Data, 2015, 9(3):1-26.
