Affiliations 

  • 1 School of Computer Sciences, Universiti Sains Malaysia (USM), 11800 Minden, Pulau Pinang, Malaysia
MyJurnal

Abstract

Personality represents the mixture of features and qualities that built an individual’s distinctive characters including thinking, feeling and behaving. Traditionally, self-assessment method via questionnaire is the most common means to identify personality. Since recommender systems and advertisement
campaigns have evolved rapidly, personality computing has become a popular research field to provide personalisation to users. Currently, researchers have utilised social media data for automatically predicting personality. However, it is complex to mine the social media data as they are noisy, free-format, and
of varying length and multimedia. This paper proposes a decision tree C4.5 algorithm to automatically predict personality based on Big Five model. The Big Five Inventory and ZeroR algorithm were included to be served as the baseline for performance evaluation. Experimental evaluation demonstrated that C4.5
performs better than ZeroR in terms of accuracy.
Keywords: Big Five, decision tree, personality, social media