Topic Classification Method for Analyzing Effect of eWOM on Consumer Game Sales

TL;DR

This paper presents a novel topic classification method using entropy-based feature selection and SVM to analyze tweet data, revealing insights into consumer needs for game software with a 0.63 F-measure.

Contribution

It introduces an entropy-based feature selection approach combined with SVM for classifying tweet data related to consumer game needs, enhancing analysis of eWOM impact.

Findings

Achieved a 0.63 F-measure in classification accuracy.

Demonstrated effectiveness of entropy-based feature selection.

Applied method to real tweet data for consumer insights.

Abstract

Electronic word-of-mouth (eWOM) has become an important resource for the analysis of marketing research. In this study, in order to analyze user needs for consumer game software, we focus on tweet data. And we proposed topic extraction method using entropy-based feature selection based feature expansion. We also applied it to the classification of the data extracted from tweet data by using SVM. As a result, we achieved a 0.63 F-measure.