Recognizing a Participant Behavior in a Multi-party Conversation: Detection of a Participant That Returns to a Discussion That Is Already Over
In this paper, we discuss a task to recognize a participant’s behavior in a multi-party conversation. We focus on a detection task of a participant that returns to a discussion that is already over; we call the participant “BDH (Beat a Dead Horse) participant.” The target corpus contains 17 conversations about a topic with three participants, and one of three participants is the BDH participant. To detect the BDH participant, we apply machine learning methods. We compare three machine learning methods; naive bayes, decision tree, and support vector machines. In addition, we introduce a selection model based on the task setting. The experimental result shows the effectiveness of SVMs with our selection model.
F. Nihei, Y. Hayashi, and Y. Nakano. Detecting discussion state shifts in group discussions. The 28th Annual Conference the Japanese Society for Artificial Intelligence, 2014.
R. Kirikihira and K. Shimada. Discussion map with an assistant function for decisionmaking: A tool for supporting consensus-building. In International Conference on Collaboration Technologies, pages 3–18, 2018.
K. Okamoto, S. Matsubara, and K. Nagao. Automatic evaluation of statements in meetings based on acoustic and linguistic features. In The 78th National Convention of IPSJ, number 1, pages 521–522, 2016.
T. Kodani, K. Keki, T. Matsui, and T. Okamoto. Development of discussion supporting system based on the “value of favorable words’ influence”. In Transactions of the Japanese Society for Artificial Intelligence, volume 19, pages 95–104, 2004.
E. Mizukami, L. Liu, and M. Ikuyo. An analysis of participants’ behavior in the transition from a stagnant phase of discussion in group discussions. SIG-SLUD, B5(03):50–55, 2018.
S. Yonemitsu and K. Shimada. Don’t beat a dead horse: Recognizing a person who returns to a done-deal in a multi-party conversation. In Proceedings of the 8th International Conference on Smart Computing and Artificial Intelligence, 2020.
KD. Benne and P. Sheats. Functional roles of group members. In Journal of social issues, volume 4, pages 41–49, 1948.
W. Li, Y. Li, and Q. He. Estimating key speaker in meeting speech based on multiple features optimization. In International Journal of Signal Processing, Image Processing and Pattern Recognition, volume 8, pages 31–40, 2015.
H. Hung, Y. Huang, G. Friedland, and D. Gatica-Perez. Estimating the dominant person in multi-party conversations using speaker diarization strategies. In 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, pages 2197–2200, 2008.
D. Sanchez-Cortes, O. Aran, MS. Mast, and D. Gatica-Perez. A nonverbal behavior approach to identify emergent leaders in small groups. In IEEE Transactions on Multimedia, volume 14, pages 816–832, 2011.
R. Rienks and D. Heylen. Dominance detection in meetings using easily obtainable features. In International Workshop on Machine Learning for Multimodal Interaction, pages 76–86, 2005.
T. Shiota, T. Yamamura, and K. Shimada. Analysis of facilitators’ behaviors in multiparty conversations for constructing a digital facilitator system. In International Conference on Collaboration Technologies, pages 145–158, 2018.
PM Muller and A Bulling. Emergent leadership detection across datasets. In 2019 International Conference on Multimodal Interaction, pages 274–278, 2019.
C Beyan, F Capozzi, C Becchio, and V Murino. Prediction of the leadership style of an emergent leader using audio and visual nonverbal features. volume 20, pages 441–456. IEEE, 2017.
Q. Zhang, H. Hung, S. Kimura, S. Okada, N. Ohata, and K. Kuwahara. Analysis on the participants’ functional roles and their transitions in group discussion. In The transaction of Human Interface Society, volume 20, pages 31–44, 2018.
J Cheng, C Danescu-Niculescu-Mizil, and J Leskovec. Antisocial behavior in online discussion communities. In Proceedings of the International AAAI Conference on Web and Social Media, volume 9, 2015.
CW Seah, HL Chieu, KMA Chai, LN Teow, and LW Yeong. Troll detection by domain-adapting sentiment analysis. In 2015 18th International Conference on Information Fusion (Fusion), pages 792–799, 2015.
J Cheng, M Bernstein, C Danescu-Niculescu-Mizil, and J Leskovec. Anyone can become a troll: Causes of trolling behavior in online discussions. In Proceedings of the 2017 ACM conference on computer supported cooperative work and social computing, pages 1217–1230, 2017.
H. Takamura, T. Inui, and M. Okumura. Extracting semantic orientations of words using spin model. In Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL2005), pages 133–140, 2005.
S. Hochreiter and J. Schmidhuber. Long short-term memory. Neural Computation, 9(8):1735–1780, 1997.
J. Devlin, M-W. Chang, K. Lee, and K. Toutanova. 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, Volume 1 (Long and Short Papers), pages 4171–4186. Association for Computational Linguistics, 2019.
T. Sembokuya and K. Shimada. Timing prediction of facilitating utterance in multiparty conversation. In Computational Linguistics, Communications in Computer and Information Science, volume 1215, pages 267–279, 2020.
T. Shiota, K. Honda, K. Shimada, and T. Saitoh. Leader identification using multimodal information in multi-party conversations. In Proceedings of the International Conference on Asian Language Processing (IALP), pages 7–12, 2020.
T. Shiota and K. Shimada. The discussion corpus toward argumentation quality assessment in multi-party conversation. In Proceedings of the 9th International Conference on Learning Technologies and Learning Environments, 2020.