[1J3] [General Session] 9. NLP / IR

[1J3-02] Classifying Personality of Comic Character Based on Egogram

〇Byeongseon Park¹, Kanae Ibayashi¹, Mitsunori Matsushita¹ (1. Kansai University)

Keywords:Comic Computing, Egogram, Personality Estimation

The aim of this research is to develop a comic search system based on the characteristics of characters appearing in comics. For that purpose, this paper examines classification of characters using the egogram, which is used to classify personality. In the proposed method,texts that express the comic character's characteristics are acquired from Web resources and semantic vectors are allocated based on the texts using the egogram. The resulting egogram pattern is used to estimate the typical properties. Our experiment revealed that the performance of classification was 55.0 %.