[3A5-GS-6] Language media processing

[3A5-GS-6-05] Verification of Applicability of a Japanese Corpus containing Information on Social Situations to Machine Learning Models

〇Muxuan Liu^1,2, Tatsuya Ishigaki², Yui Uehara², Yusuke Miyao^3,2, Hiroya Takamura², Ichiro Kobayashi^1,2 (1. Ochanomizu University, 2. National Institute of Advanced Industrial Science and Technology , 3. Univ. of Tokyo)

Keywords:Social Situation, Multi-label Classification

This study proposes a straightforward way of capturing language use in social situations and showed that more accurate linguistic analysis is possible. Furthermore, using our corpus constructed based on Systemic Functional Linguistics, we achieved a highly accurate classification model based on the social situation in the text. Specifically, this study used a business email corpus to perform multi-label classification of annotation labels based on social context, created a classification model, and evaluated its performance. By measuring the accuracy of the classifier, we discussed the impact of corpus annotation labels on the performance of the model. The results of this study are expected to provide useful insights into the fields of social-situation-based linguistic analysis and natural language processing.