議論支援システムAIR-VASにおけるシーン分割を用いた刺激情報生成機構の導入

Translated Abstract

In today's rapidly progressing information age, the diversi cation of individual values has led to prominent social issues arising from value conicts. We address this challenge by developing AIR-VAS, a discussion support system designed to promote mutual understanding and synergy among groups with diverse values. The core function of AIR-VAS is to facilitate awareness of others' values during group discussions. It achieves this by recognizing and sharing other group's characteristic opinions, enabling participants to explore new perspectives and dimensions to the discussion topic. This paper introduces a method for discussion scene segmentation based on sentence vectors that capture textual semantics using neural language models. By integrating the mechanism of selecting stimulus information based on scene segmentation into the system, we enhance the effectiveness of awareness support. Our experimental results demonstrate how unique ideas selected based on sentence vector distances promote diverse idea generation, providing valuable insights into fostering synergy among individuals with differing values in group discussions.

References

• [1]   Jane , Emma A. : Flaming? What aming? The pitfalls and potentials of researching online hostility. Ethics and Information Technology, Vol. 17, No. 1, pp. 65-87 (2015).
• [2]   Pariser,  E. : The Filter Bubble: What the Internet Is Hiding from You, In Penguin Press, (2011).
• [3]  吉添衛, 服部宏充, 江間有沙, 大澤博隆, 神崎宣次, 久木田水生, 小川祐樹: グループディスカッションにおける可視化情報提示に基づく気づき支援, ヒューマンインタフェース学会論文誌, 23巻, 4号, pp. 501-512 (2021).
• [4]   Yoshizoe,  M. and  Hattori,  H. : Awareness Support with Mutual Stimulation among People to Enrich Group Discussion in AIR-VAS, WCCE 2022. IFIP Advances in Information and Communication Technology, Springer, vol. 685, pp. 379-388 (2023)
• [5]   Rada,  M. and  Tarau,  P. : Textrank: Bringing order into text., Proceedings of the 2004 conference on empirical methods in natural language processing, pp. 404-411 (2004).
• [6]   Blei , David M.,  Andrew  Y.  Ng , and Michael I.  Jordan . : Latent dirichlet allocation, Journal of machine Learning research, 3.Jan, pp. 993-1022 (2003)
• [7]   Haghighi,  A. and  Vanderwende,  L. : Exploring content models for multi-document summarization, Proceedings of human language technologies: The 2009 annual conference of the North American Chapter of the Association for Computational Linguistics, pp. 362-370 (2009).
• [8]   Tian,  S.,  Zhang,  X.  Amy  and  Karger,  D. : A System for Interleaving Discussion and Summarization in Online Collaboration, In Proceedings of the ACM on Human-Computer Interaction. Vol. 4, CSCW3, Article 241, pp. 1-27 (2020).
• [9]   Zhang,  X.  Amy  and  Cranshaw,  J. : Making Sense of Group Chat through Collaborative Tagging and Summarization, Proceedings of the ACM on Human-Computer Interaction, Vol. 2, Issue CSCW, Article 196, pp. 1-27 (2018).
• [10]   Hearst , Marti A. : TextTiling: A quantitative approach to discourse segmentation, Technical report, University of California, Berkeley, Sequoia, (1993).
• [11]   Hearst , Marti A. : TextTiling: Segmenting text into multi-paragraph subtopic passages, Computational linguistics, Vol. 23, Issue. 1, pp. 33-64 (1997).
• [12]   Riedl,  M. and  Biemann,  C. : Topictiling: a text segmentation algorithm based on lda, Proceedings of ACL 2012 Student Research Workshop. Association for Computational Linguistics, (2012).
• [13]   Mikolov,  T.,  Chen,  K.,  Corrado,  G. and  Dean,  J.: Efficient Estimation of Word Representations in Vector Space, ICLR 2013, (2013).
• [14]   Bojanowski,  P.,  Grave,  E.,  Joulin,  A. and  Mikolov,  T. : Enriching Word Vectors with Subword Information, Transactions of the Association for Computational Linguistics, Vol. 5, pp. 135-146 (2017).
• [15]   Devlin,  J.,  Chang,  M.-W.,  Lee,  K. and  Toutanova,  K.: BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding, In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Vol. 1, pp. 4171-4186 (2019).
• [16]   Vaswani,  A.,  Shazeer,  N.,  Parmar,  N.,  Uszkoreit,  J.,  Jones,  L.,  Aidan,  N.  Gomez ,  Kaiser,  L. and  Polosukhin,  I. : Attention is all you need, In Advances in Neural Information Processing Systems30 (NIPS 2017), pp. 6000-6010 (2017).
• [17]   Reimers,  N. and  Gurevych,  I. : Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks, Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing, pp. 3982-3992 (2019).
• [18]  福田清人, 森直樹, 松本啓之亮, 岡田真: ストーリー解析のための文の分散表現に基づく小説の自動セグメンテーション手法の提案, 芸術科学会論文誌, Vol. 18, No. 5, pp. 63-75 (2019).
• [19]   Badjatiya,  P.,  Kurisinkel,  J.  Litton ,  Gupta,  M. and  Varma,  V. : Attention-based Neural Text Segmentation, The 40th European Conference on Information Retrieval, pp. 180-193 (2018).
• [20]  工藤拓, 山本薫, 松本裕治：Conditional RandomFieldsを用いた日本語形態素解析, 情報処理学会自然言語処理研究会, SIGNL-161, pp. 89-96 (2004).
• [21]  國府久嗣, 山崎治子, 野坂政司: 内容推測に適したキーワード抽出のための日本語ストップワード, 日本感性工学会論文誌, Vol. 12, No. 4, pp. 511-518 (2013).