JSAI2019

Presentation information

General Session

General Session » [GS] J-9 Natural language processing, information retrieval

[4M3-J-9] Natural language processing, information retrieval: inferring emotion and intension

Fri. Jun 7, 2019 2:00 PM - 3:20 PM Room M (Front-right room of 1F Exhibition hall)

Chair:Takayuki Nagai Reviewer:Jun Sugiura

2:40 PM - 3:00 PM

[4M3-J-9-03] Estimating the Degree of Difficulty to Extract Writer’s Emotion in Japanese Sentences

〇Sanae Yamashita1, Yasushi Kami1, Noriyuki Okumura2 (1. National Institute of Technology, Akashi College, 2. Otemae University)

Keywords:Emotion Estimation

Existing emotion estimation system always estimates some emotion from sentences. However, some sentences are difficult to estimate by humans. In order for the dialogue system to estimate emotion like humans, we think that it should also give results that "emotion estimation is difficult" as humans do. Therefore, we aim to construct a system to calculate the estimation difficulty level when estimating the author 's emotions in Japanese sentences. Emotion estimation difficulty was judged by combination of classification by classifier, whether there is negative expression, emotional expression or not. F1 value exceeded 80%.