Sentiment-aware Interview Chatbot Based on Deep Learning Approach for Personality Detection from Text

• Item type: SIG Technical Reports(1)
• 公開日: 2022-03-07
• タイトル: Sentiment-aware Interview Chatbot Based on Deep Learning Approach for Personality Detection from Text
• タイトル / 言語: en
• タイトル: Sentiment-aware Interview Chatbot Based on Deep Learning Approach for Personality Detection from Text
• 言語: eng
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_18gh
• 資源タイプ: technical report
• 著者所属: Graduate School of Engineering, The University of Tokyo
• 著者所属: Information Technology Center, The University of Tokyo
• 著者所属(英): en
• 著者所属(英): Graduate School of Engineering, The University of Tokyo
• 著者所属(英): en
• 著者所属(英): Information Technology Center, The University of Tokyo
• 著者名: Haoyue, Tan; Takefumi, Ogawa
• 著者名(英): Haoyue, Tan; Takefumi, Ogawa
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: Chatbots have become a new focus on human-computer interaction (HCI) and are already widely used in some services like booking assistants and customer services. The development of natural language processing (NLP) techniques enables chatbots to understand users' intent correctly and respond human-likely, leading to their fulfillment to more complicated tasks like interviews. This research built a sentiment-aware chatbot providing users a more engaging conversational experience while detecting users' MBTI personality type from input text. This research use language model BERT to extract features and generate sentence-level embeddings of raw text. Compared to traditional methods of training machine learning algorithms with psychological lexicons, this method significantly improved overall accuracy.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: Chatbots have become a new focus on human-computer interaction (HCI) and are already widely used in some services like booking assistants and customer services. The development of natural language processing (NLP) techniques enables chatbots to understand users' intent correctly and respond human-likely, leading to their fulfillment to more complicated tasks like interviews. This research built a sentiment-aware chatbot providing users a more engaging conversational experience while detecting users' MBTI personality type from input text. This research use language model BERT to extract features and generate sentence-level embeddings of raw text. Compared to traditional methods of training machine learning algorithms with psychological lexicons, this method significantly improved overall accuracy.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AA1155524X
• 書誌情報: 研究報告グループウェアとネットワークサービス（GN）; 巻 2022-GN-116, 号 15, p. 1-8, 発行日 2022-03-07
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 2188-8744
• Notice: SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc.
• 出版者 / 言語: ja
• 出版者: 情報処理学会