Affiliations: Department of Computer Engineering, Zakir Husain College of Engineering and Technology, Aligarh Muslim University, Aligarh, UP, India
Correspondence:
[*]
Corresponding author. Bushra Siddique, Department of Computer Engineering, Zakir Hussain College of Engineering and Technology, Aligarh Muslim University, Aligarh, UP, India. Tel.: +918423519717; E-mail: [email protected].
Abstract: In the near past, microblogging services like Twitter have gained immense popularity. The vast breadth of user base is responsible for generating information on diverse aspects ranging from product launch to sports match. However, due to the exponentially increasing number of users on Twitter platform, the volume of content generated is tremendously high. In this paper we address the information overload problem of the Twitter and present a framework for event detection with hierarchical visualization specifically for sports events. We propose a novel Event Tree algorithm which detects and generates a hierarchy of events through recursive hierarchical clustering. The different levels of the hierarchy represent the events at different granularities of time and thus offer dual advantages. Firstly, it takes care of the users with varied level of interest in the particular sports event. Secondly, the users may get finer details for specific segments of the sport holdings as per their appeal. We test and report results of our framework for the Indian Premier League Twenty20 2016 season cricket match dataset.
