Expert finding which aims to identifying people with the relevant expertise or practices on a given topic query. In blogging services like Twitter, the expert analysis problem has gained big attention in social media. Twitter is a new type of media giving a publicly available way for users to publish 140-character short messages (i.e., tweets). However, earlier systems cannot be directly applied to twitter expert finding difficulty. They generally rely on the supposition that all the documents linked with the candidate experts receive implicit knowledge related to the expertise of individuals. Whereas it might not be directly allied with their expertise, i.e., who is not an expert, but may publish/re-tweet a substantial amount of tweets including the topic words. Recently, several attempts use the relations among users and twitter list for expert finding. Nevertheless, these strategies only partly utilize such relationships. To address these issues generate a probabilistic method to jointly exploit three types of relations (i.e., follower relation, user-list relation and list-list relation) for finding experts. LDA algorithm is applied to finding topic experts. LDA is based upon the concept of searching for a linear combination of variables (predictors) that best separates two classes (targets). Semi-supervised Graph-based Ranking approach (SSGR) to offline measure the global authority of users. Then, online compute the local relevance between users and the given query. Then order all of the users & find top-N users with the highest ranking scores. Therefore, the proposed method can jointly exploit the different types of relations among users and lists for improving the precision of finding experts on a given topic on Twitter.

Expert finding, Semi-supervised, Graph-based ranking approach, LDA, Sentiment Analysis, Hashtag, Twitter

[1] Wei Wei, Gao Cong, Chunyan Miao, Feida Zhu, and Guohui Li "Learning to Find Topic Experts in Twitter via Different Relations" IEEE transactions on knowledge and data engineering, vol.28, no 7, July 2016.
[2] S. Ghosh, N. Sharma, F. Benevenuto, N. Ganguly, and K. Gummadi, "Cognos: Crowdsourcing search for topic experts in microblogs," in Proc. 35th Int. ACM SIGIR Conf. Res. Develop. Inform. Retrieval, 2012, pp. 575–590.
[3] J. Weng, E.-P. Lim, J. Jiang, and Q. He, “Twitterrank: Finding topic-sensitive influential Twitterers,” in Proc. ACM Int. Conf. Web Search Data Mining, 2010, pp. 261–270.
[4] A. Pal and S. Count, "Identifying topical authorities in microblogs," in Proc. ACM Int. Conf. Web Search Data Mining, 2011, pp. 45–54.
[5] Z. Zhao, L.-J. Zhang, X.-F. He, and W. Ng, "Expert finding for question answering via graph regularized matrix completion," IEEE Trans. Knowl. Data Eng., vol. 27, no. 4, pp. Retrieval, 2012, pp. 575–590.
[6] A. Pal and J. A. Konstan, “Expert identification in community question answering: Exploring question selection bias,” in Proc. ACM Conf. Inf. Knowl. Manag., 2010, pp. 1505–1508.
[7] X. Liu, W. B. Croft, and M. Koll, "Finding experts in community-based question-answering services," in Proc. ACM Conf. Inf. Knowl. Manag., 2005, pp. 315–316.
[8] W. Wei, B. Gao, T.-Y. Liu, T.-F. Wang, H.-G. Li and H. Li. "A ranking approach on a large-scale graph with multidimensional heterogeneous information," IEEE Trans. Cybern., vol. Pp, no. 99, pp. 1–15, Apr. 2015.
[9] G. Demartini, D. E. Difallah, and P. Cudr_e-Mauroux, "Zencrowd: Leveraging probabilistic reasoning and crowdsourcing techniques for large-scale entity linking," in Proc. 21st Int. Conf. World Wide Web, 2012, pp. 469–478.
[10] J. Lehmann, C. Castillo, M. Llamas, and E. Zuckerman, “Finding news curators in Twitter,” in Proc. Int. Conf. World Wide Web, 2013, pp. 469–478.
[11] K. Balog, L. Azzopardi, and M. De Rijke, “Formal models for expert finding in enterprise corpora,” in Proc. 29th Int. ACM SIGIR Conf. Res. Develop. Inform. Retrieval, 2006, pp. 4
[12] A. Pal and J. A. Konstan, “Co-occurrence-based diffusion for expert search on the web,” IEEE Trans. Knowl. Data Eng., vol. 25, no. 5, pp. 1001–1014, May 2013.
[13] M. David and A. Andrew, "Expertise modeling for matching papers with reviewers," in Proc. ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining, 2007, pp. 500–509.
[14] H. Deng, I. King, and M.-R. Lyu, "Formal models for an expert finding on DBLP bibliography data," in Proc. Int. Conf. Data Mining, 2008, pp. 163–172.
[15] P. Serdyukov, H. Rode, and D. Hiemstra, “Modelling multi-step relevance propagation for expert finding,” in Proc. ACM Conf. Inf. Knowl. Manag., 2008, pp. 1133–1142.