Soccer Events Summarization by Using Sentiment Analysis

In this paper, we propose a framework for automatic textual soccer summarization based on real-time sentiment analysis of Twitter events. The interaction of fans on Twitter is marked by the expression of their sentiments through their tweets, they can be positive or negative depending on the event in soccer games. Our framework analyzes the sentiments expressed on Twitter with the goal to detect and predict the team supported by each fan as well as actors (the team(s) and player(s) concerned(s)) and the details associated with each event. All this information is used to draw up a summary of soccer matches. The summary is constructed using machine learning and KDD process that allows the extraction of knowledge from data in the context of large databases. Through the realized experiments, we confirm that the results are promising and this work has allowed us to verify the feasibility and efficiency of soccer events summarization by using sentiment analysis in media streams.