Multimodal, Multiparty Modeling of Collaborative Problem Solving Performance
Multimodal, Multiparty Modeling of Collaborative Problem Solving Performance
复制标题
DOI：
10.1145/3382507.3418877
复制
发表时间：
2020-10
期刊：
影响因子：
--
通讯作者：
Shree Krishna Subburaj;Angela E. B. Stewart;A. Rao;S. D’Mello
中科院分区：
文献类型：
--
作者：
Shree Krishna Subburaj;Angela E. B. Stewart;A. Rao;S. D’Mello
对多方交互中的团队现象进行建模本质上需要结合来自多个团队成员的信号，通常是通过加权策略。在这里，我们探讨了这样一个假设：来自各个队友的战略权重信号将优于同等权重基线。因此，我们探索了基于角色、特质和行为的团队成员行为信号权重。我们分析了 101 个在教育物理游戏中参与计算机介导的协作问题解决 (CPS) 的三人组的数据。我们研究了机器学习模型的准确性，这些模型在面部表情、声学韵律、眼睛注视和任务上下文信息上进行训练，在游戏关卡结束前一分钟计算，以预测解决该关卡的成功。三名队友的特征权重相等的单峰模型的 AUROC 范围为 0.54 到 0.67，而凝视、面部和任务上下文特征的组合则实现了 0.73 的 AUROC。各种多方加权策略并未优于等权重基线。然而，我们最好的非语言模型 (AUROC = .73) 优于基于语言的模型 (AUROC = .67)，并且将两者结合起来有一些优势 (AUROC = .75)。最后，旨在从级别开始就以分钟为基础前瞻性预测性能的模型实现了较低但仍高于概率的 AUROC 0.60。我们讨论团队绩效和其他团队结构的多方建模的含义。
Modeling team phenomena from multiparty interactions inherently requires combining signals from multiple teammates, often by weighting strategies. Here, we explored the hypothesis that strategic weighting signals from individual teammates would outperform an equal weighting baseline. Accordingly, we explored role-, trait-, and behavior-based weighting of behavioral signals across team members. We analyzed data from 101 triads engaged in computer-mediated collaborative problem solving (CPS) in an educational physics game. We investigated the accuracy of machine-learned models trained on facial expressions, acoustic-prosodics, eye gaze, and task context information, computed one-minute prior to the end of a game level, at predicting success at solving that level. AUROCs for unimodal models that equally weighted features from the three teammates ranged from .54 to .67, whereas a combination of gaze, face, and task context features, achieved an AUROC of .73. The various multiparty weighting strategies did not outperform an equal-weighting baseline. However, our best nonverbal model (AUROC = .73) outperformed a language-based model (AUROC = .67), and there were some advantages to combining the two (AUROC = .75). Finally, models aimed at prospectively predicting performance on a minute-by-minute basis from the start of the level achieved a lower, but still above-chance, AUROC of .60. We discuss implications for multiparty modeling of team performance and other team constructs.