Relationship Between Personality Patterns and Harmfulness

This paper hypothesize that harmful utterances need to be judged in context of whole sentences, and extract features expressions using a general-purpose language model. Based on the extracted features, we propose method predict presence or absence categories. In addition, authors believe it is possible analyze users who incite others by combining this with research analyzing personality speaker from statements social networking sites. The results confirmed proposed can judge possibility comments higher accuracy than simple dictionary-based models distributed representations words. relationship between patterns was also an analysis based judgment