[4D3-GS-6] Language media processing: applications

[4D3-GS-6-04] Emotional Intensity Estimation based on Writer’s Personality Information

〇Haruya Suzuki¹, Kazuki Akiyama¹, Tomoyuki Kajiwara¹, Takashi Ninomiya¹, Noriko Takemura², Yuta Nakashima², Hajime Nagahara² (1. Ehime University, 2. Osaka University)

[[Online]]

Keywords:natural language processing, emotion analysis, personality assessment

Emotion analysis is a natural language processing task that predicts human emotional intensity from the text. Previous emotion analysis models cannot adequately estimate the writer's emotion (subjective emotion). In this study, we specialize our emotion analysis model to estimate the subjective emotional intensity by considering the writer's personality information. Experimental results on the emotional intensity estimation of Plutchik's eight basic emotions in Japanese showed that the proposed method improves the performance of the estimation of subjective emotional intensity.