Using Social Interactions Network Graph and Centrality to Identify Key Players
Alex Pongpech

Alex Pongpech, Big Data Engineering Graduate Program, Dhurakijpundit University, Thailand.
Manuscript received on January 1, 2021. | Revised Manuscript received on January 9, 2021. | Manuscript published on January 10, 2021. | PP: 10-15 | Volume-1 Issue-1, February 2021 | Retrieval Number:A1002011121/2021©LSP
Open Access | Ethics and Policies
© The Authors. Published by Lattice Science Publication (LSP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Topic on Trend has been made more popular recently with the published Food trend 2016 by Google. Prior to the social network era, difficulty in predicting and identifying trend are difficult at best. This is mainly due to difficulty of gathering data from the public to do the analysis. Given that graph can be utilized to modeled social network users and their relationships, and that graph algorithms are very mature. The possibility of utilizing graph algorithms to analyze social network users to help identifying trendsetters is worth investigating. In this paper, the aim is to applygraph theoryto model interactions on social network. The modelcan then be utilized to identifykeyplayers based on the Betweenness centrality and Page Rank centrality. Finally, based on Page Rank algorithm, vertexes ranking is implemented using python.
Keywords: Trend, Social Network, Graph, Centrality, Keyplayer, Page Rank.