Media Leaders Mining Based on Android News Apps

Sijia Wang; Miao Zhang

doi:10.18282/inm.v3i1.316

Sijia Wang Cyberspace Security School, Beijing University of Posts and Telecommunications, Beijing 100876, China
Miao Zhang Cyberspace Security School, Beijing University of Posts and Telecommunications, Beijing 100876, China

Article ID: 316

510 Views

DOI: https://doi.org/10.18282/inm.v3i1.316

Keywords: Media leaders, News apps, Reverse analysis, Traceability

Abstract

With the rapid development of the mobile Internet, the mobile news apps have become the most important way for the public to obtain news. As a new media carrier and communication platform,the mobile news apps can promote the rapid dissemination of information and the rapid spread of influence. Some media have a major influence on the direction of other media reports and the behavioral decisions of the public. These media can be regarded as media leaders. Media leaders are very important in the dissemination of news. By identifying media leaders, companies or governments can promote sales or guide public opinion separately. This article believes that media leaders mainly achieve their own influence by publishing news, so this article uses the news published by the mobile news apps as an entry point. This paper firstly solves the problem of data crawling in mobile news apps, and proposes a data crawling method based on reverse analysis, and obtains the data source. Then, reconstruct the reprinting path of the news, and carry out accurate traceability. Finally, cluster the news based on LDA, and propose an algorithm for mining media leaders from three aspects: influence, activity and preference. Experimental studies of data sets have shown that our algorithms can effectively identify media leaders.

References

Media Consulting. Quarterly Monitoring Report of China Mobile App Store. Available online: http://www.iimedia.cn/59804.html (accessed on 23 November 2017).

Centola D. The spread of behavior in an online social network experiment. Science. 2010; 329(5996): 1194-1197.

Kitsak M, Gallos L K, Havlin S, et al. Identification of influential spreaders in complex networks. Nature Physics. 2010; 6(11): 888-893.

Weng J, Lim E P, Jiang J, et al. Twitter Rank: finding topic-sensitive influential twitterers. 2010.

Agarwal N, Liu H, Tang L, et al. Identifying the influential bloggers in a community. 2008.

Li F, Du T C. Who is talking? An ontology-based opinion leader identification framework for word-of-mouth marketing in online social blogs. Decision Support Systems. 2011; 51(1): 190-197.

Fan X, Zhao J, Fang B, et al. Probability Model of Diffusion of Influence and Its Application to Research on Discovery of Opinion Leaders. chinese journal of computers. 2013; 36(2).

Wu Y, Ma L, Lin M, et al. opinion leader discovery algorithm based on user influence. minicomputer system. 2015; 36(3): 561-565.

Ding X, Hu Y, Zhao W, et al. Research on Characteristics of Internet Opinion Leaders. Engineering Science and Technology. 2010; 42(2): 145-149.

Li Y, Qiao Y, Liu Z, et al. Identifying opinion leader nodes in online social networks with a new closeness evaluation algorithm. Soft Computing. 2018; 22(2): 453-464.

Matsumura N, Ohsawa Y, Ishizuka M. Influence Diffusion Model in Text-Based Communication. Transactions of the Japanese Society for Artificial Intelligence. 2002; 17(3): 259-267.

Li T, Wang Y, Android, Reverse Analysis of Malicious Code, J. Information Security and Communication Secrecy. 2016; (4): 95-98.

Blei DM, Jordan MI, Ng AY. Hierarchical Bayesian Models for Applications in Information retrieval. Bayesian Statistics. 2003; 25-43.

Zou X, Sun J. LDA Thematic Model. Intelligent Computer and Applications. 2014; 4(5): 105-106.

Zhang Y, Fu X. Summary of data traceability technology. Minicomputer System. 2012; 33(9): 1917-1923.

Lu Y. Ranking of fuzzy analytic hierarchy process based on fuzzy consistent matrix. fuzzy systems and mathematics. 2016; 16(02): 79-85.

Chen P, Zhao R, Single S. Android Based on Combination of Static and Dynamic, Malicious Code Behavior Similarity Detection. Computer Application Research. 2018; 35(5).