Yun-Shao Lin
Skip Abstract Section
Abstract
A small group is a fundamental interaction unit for achieving a shared goal. Group performance can be automatically predicted using computational methods to analyze members’ verbal behavior in task-oriented interactions, as has been proven in several recent works. Most of the prior works focus on lower-level verbal behaviors, such as acoustics and turn-taking patterns, using either hand-crafted features or even advanced end-to-end methods. However, higher-level group-based communicative functions used between group members during conversations have not yet been considered. In this work, we propose a two-stage training framework that effectively integrates the communication function, as defined using Bales’s interaction process analysis (IPA) coding system, with the embedding learned from the low-level features in order to improve the group performance prediction. Our result shows a significant improvement compared to the state-of-the-art methods (4.241 MSE and 0.341 Pearson’s correlation on NTUBA-task1 and 3.794 MSE and 0.291 Pearson’s correlation on NTUBA-task2) on the National Taiwan University Business Administration (NTUBA) small-group interaction database. Furthermore, based on the design of IPA, our computational framework can provide a time-grained analysis of the group communication process and interpret the beneficial communicative behaviors for achieving better group performance.
- [1] . 2016. Predicting the performance in decision-making tasks: From individual cues to group interaction. IEEE Transactions on Multimedia 18, 4 (2016), 643–658.Google Scholar
Digital Library
- [2] . 1950. Interaction process analysis; a method for the study of small groups. (1950).Google Scholar
- [3] . 2020. BlazePose: On-device real-time body pose tracking. arXiv preprint arXiv:2006.10204 (2020).Google Scholar
- [4] . 2019. Blazeface: Sub-millisecond neural face detection on mobile gpus. arXiv preprint arXiv:1907.05047 (2019).Google Scholar
- [5] . 2019. The unobtrusive group interaction (UGI) corpus. In Proceedings of the 10th ACM Multimedia Systems Conference (MMSys’19). Association for Computing Machinery, New York, NY, 249–254.Google Scholar
- [6] . 1988. An integration of process and decision scheme explanations of group problem solving performance. Organizational Behavior and Human Decision Processes 42, 2 (1988), 234–249.Google ScholarCross Ref
- [7] . 2018. The group affect and performance (GAP) corpus. In Proceedings of the ICMI 2018 Workshop on Group Interaction Frontiers in Technology (GIFT’18).Google ScholarDigital Library
- [8] . 2012. ISO 24617-2: A semantically-based standard for dialogue annotation. In LREC. 430–437.Google Scholar
- [9] . 2010. Emotional intelligence and learning in teams. Journal of Workplace Learning 22 (2010), 125–145.Google ScholarCross Ref
- [10] . 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018).Google Scholar
- [11] . 2007. The impact of increased awareness while face-to-face. Human–Computer Interaction 22, 1–2 (2007), 47–96.Google ScholarDigital Library
- [12] . 2007. Linguistic correlates of team performance: Toward a tool for monitoring team functioning during space missions. Aviation, Space, and Environmental Medicine 78, 5 (2007), B86–B95.Google Scholar
- [13] . 1984. Dyads and triads at 35,000 feet: Factors affecting group process and aircrew performance.American Psychologist 39, 8 (1984), 885.Google ScholarCross Ref
- [14] . 1981. 5. Information transfer within the cockpit: Problems in mTRACOCKPlT communications. C. E. Billings: Ames Research Center. E. S. Cheaney: Battelle’s Columbus Division, Mountain View, California.63.Google Scholar
- [15] . 1987. Organizational behavior: Group structure, process, and effectiveness. Journal of Management 13, 2 (1987), 237–257.Google ScholarCross Ref
- [16] . 2010. Language style matching as a predictor of social dynamics in small groups. Communication Research 37, 1 (2010), 3–19.Google ScholarCross Ref
- [17] . 2007. Communication behaviour during management and design team meetings: A comparison of group interaction. Construction Management and Economics 25, 11 (2007), 1197–1213.Google ScholarCross Ref
- [18] . 2009. Informal interaction in construction progress meetings. Construction Management and Economics 27, 10 (2009), 983–993.Google ScholarCross Ref
- [19] . 2001. Project performance and management and design team communication. In Proceedings of the Association of Researchers in Construction Management, 17th Annual Conference. 5–7.Google Scholar
- [20] . 2010. Group behavior and performance. In Handbook of Social Psychology, S. T. Fiske, D. T. Gilbert, and G. Lindzey (Eds.). John Wiley & Sons, Inc., 1208–1251.Google Scholar
- [21] . 1975. Group tasks, group interaction process, and group performance effectiveness: A review and proposed integration. In Advances in Experimental Social Psychology. Vol. 8. Elsevier, 45–99.Google Scholar
- [22] . 1986. Experiments in group decision making communication process and outcome in face-to-face versus computerized conferences. Human Communication Research 13, 2 (1986), 225–252.Google ScholarCross Ref
- [23] . 2018. Analyzing gaze behavior and dialogue act during turn-taking for estimating empathy skill level. In Proceedings of the 20th ACM International Conference on Multimodal Interaction. 31–39.Google ScholarDigital Library
- [24] . 2019. Estimating interpersonal reactivity scores using gaze behavior and dialogue act during turn-changing. In International Conference on Human-computer Interaction. Springer, 45–53.Google ScholarDigital Library
- [25] . 2019. Real-time facial surface geometry from monocular video on mobile GPUs. arXiv preprint arXiv:1907.06724 (2019).Google Scholar
- [26] . 2020. Group performance prediction with limited context. In Companion Publication of the 2020 International Conference on Multimodal Interaction. 191–195.Google ScholarDigital Library
- [27] . 2019. Analyzing verbal and nonverbal features for predicting group performance. arXiv preprint arXiv:1907.01369 (2019).Google Scholar
- [28] . 2018. Supervised autoencoders: Improving generalization performance with unsupervised regularizers. In Advances in Neural Information Processing Systems, , , , , , and (Eds.), Vol. 31. Curran Associates, Inc.Google Scholar
- [29] . 2009. Automated Language-based Feedback for Teamwork Behaviors. Cornell University.Google Scholar
- [30] . 2019. Interaction process label recognition in group discussion. In 2019 International Conference on Multimodal Interaction. 426–434.Google ScholarDigital Library
- [31] . 2018. Using interlocutor-modulated attention BLSTM to predict personality traits in small group interaction. In Proceedings of the 2018 on International Conference on Multimodal Interaction. ACM, 163–169.Google ScholarDigital Library
- [32] . 2020. Predicting performance outcome with a conversational graph convolutional network for small group interactions. In 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP’20). IEEE, 8044–8048.Google ScholarCross Ref
- [33] . 2020. Who speaks next? Turn change and next speaker prediction in multimodal multiparty interaction. In 2020 IEEE 32nd International Conference on Tools with Artificial Intelligence (ICTAI’20). IEEE, 349–354.Google ScholarCross Ref
- [34] . 2004. Automated Team Discourse Annotation and Performance Prediction Using LSA.
Technical Report . New Mexico State Univ. Las Cruces.Google ScholarCross Ref - [35] . 1984. Groups: Interaction and Performance. Vol. 14. Prentice-Hall, Englewood Cliffs, NJ.Google Scholar
- [36] . 2018. Predicting group performance in task-based interaction. In Proceedings of the 2018 on International Conference on Multimodal Interaction. ACM, 14–20.Google ScholarDigital Library
- [37] . 2012. Social visualization and negotiation: Effects of feedback configuration and status. In Proceedings of the ACM 2012 Conference on Computer Supported Cooperative Work. 1081–1090.Google ScholarDigital Library
- [38] . 2013. Team learning: Collective reflection processes in teacher teams. Journal of Workplace Learning 25, 5 (2013), 296–309.Google ScholarCross Ref
- [39] . 2016. Estimating communication skills using dialogue acts and nonverbal features in multiple discussion datasets. In Proceedings of the 18th ACM International Conference on Multimodal Interaction. 169–176.Google ScholarDigital Library
- [40] . 1994. Group performance in computer-mediated and face-to-face communication media. Management Communication Quarterly 7, 3 (1994), 256–281.Google ScholarCross Ref
- [41] . 2007. A multimodal annotated corpus of consensus decision making meetings. Language Resources and Evaluation 41, 3–4 (2007), 409–429.Google ScholarCross Ref
- [42] . 2014. Alignment and task success in spoken dialogue. Journal of Memory and Language 76 (2014), 29–46.Google ScholarCross Ref
- [43] . 1956. Work group structure, communication, and group performance. Sociometry 19, 2 (1956), 105–113.Google ScholarCross Ref
- [44] . 2012. A nonverbal behavior approach to identify emergent leaders in small groups. IEEE Transactions on Multimedia 14, 3 (2012), 816–832.Google ScholarDigital Library
- [45] . 2006. The effects of leadership style and team process on performance and innovation in functionally heterogeneous teams. Journal of Management 32, 1 (2006), 132–157.Google ScholarCross Ref
- [46] . 2020. Multimodal, multiparty modeling of collaborative problem solving performance. In Proceedings of the 2020 International Conference on Multimodal Interaction. 423–432.Google ScholarDigital Library
- [47] . 2013. Improving teamwork using real-time language feedback. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. 459–468.Google ScholarDigital Library
- [48] . 1995. Communication enhances small group performance if it conforms to task requirements: The concept of ideal communication cycles. Basic and Applied Social Psychology 17, 3 (1995), 371–393.Google ScholarCross Ref
- [49] . 2002. Ideal cycles of communication (or cognitions) in triads, dyads, and individuals. Small Group Research 33, 6 (2002), 615–643.Google ScholarCross Ref
- [50] . 2017. Attention is all you need. In Advances in Neural Information Processing Systems. 5998–6008.Google Scholar
- [51] . 2000. Reflexivity, revolution and innovation in work teams. In Product Development Teams. Jai Press, 1–29.Google Scholar
- [52] . 2005. The Handbook of Group Research and Practice. Sage.Google ScholarCross Ref
- [53] . 2011. Two-dimensional structure of team process improvement: Team reflection and team adaptation. Small Group Research 42, 1 (2011), 32–54.Google ScholarCross Ref
- [54] . 2010. Evidence for a collective intelligence factor in the performance of human groups. Science 330, 6004 (2010), 686–688.Google ScholarCross Ref
- [55] . 2019. Predicting group performances using a personality composite-network architecture during collaborative task. In Proc. Interspeech 2019, 1676–1680.Google ScholarCross Ref
Index Terms
- An Interaction-process-guided Framework for Small-group Performance Prediction
Recommendations
Predicting Group Performance in Task-Based Interaction
ICMI '18: Proceedings of the 20th ACM International Conference on Multimodal InteractionWe address the problem of automatically predicting group performance on a task, using multimodal features derived from the group conversation. These include acoustic features extracted from the speech signal, and linguistic features derived from the ...
Using Interlocutor-Modulated Attention BLSTM to Predict Personality Traits in Small Group Interaction
ICMI '18: Proceedings of the 20th ACM International Conference on Multimodal InteractionSmall group interaction occurs often in workplace and education settings. Its dynamic progression is an essential factor in dictating the final group performance outcomes. The personality of each individual within the group is reflected in his/her ...
Greta: an Interactive Expressive Embodied Conversational Agent
AAMAS '15: Proceedings of the 2015 International Conference on Autonomous Agents and Multiagent SystemsGreta is an interactive Embodied Conversational Agent platform. It is endowed with socio-emotional and communicative behaviors. Through its behaviors, the agent can sustain a conversation as well as show various attitudes and levels of engagement. ...
Comments