Socially-Aware Virtual Agents: Automatically Assessing Dyadic Rapport from Temporal Patterns of Behavior
Socially-Aware Virtual Agents: Automatically Assessing Dyadic Rapport from Temporal Patterns of Behavior
复制标题
具有社交意识的虚拟代理：根据行为的时间模式自动评估二元融洽关系
DOI：
--
复制
发表时间：
2016
期刊：
影响因子：
--
通讯作者：
Justine Cassell
中科院分区：
文献类型：
--
作者：
Ran Zhao;Tanmay Sinha;A. Black;Justine Cassell
这项工作的重点是通过数据驱动发现暂时同时发生和偶然发生的行为模式，这些行为模式标志着人际融洽程度的高低。我们挖掘了一个互惠的同伴辅导语料库，对非语言行为（例如眼神和微笑）、对话策略（例如自我表露和违反社会规范）以及融洽关系（在 30 年代的薄片中）进行了可靠注释。然后，我们对对话者行为序列的时间特征如何预测融洽关系的增加和减少，以及这种融洽管理在朋友和陌生人中的不同表现进行了细致的调查。我们通过涉及学习的时间关联规则的两步融合的预测模型来预测与我们的基本事实的融洽关系，从而验证了发现的行为模式。我们的框架的性能明显优于不编码行为特征之间的时间信息的基线线性回归方法。讨论了对理解人类行为和社会代理设计的影响。
This work focuses on data-driven discovery of the temporally co-occurring and contingent behavioral patterns that signal high and low interpersonal rapport. We mined a reciprocal peer tutoring corpus reliably annotated for nonverbals like eye gaze and smiles, conversational strategies like self-disclosure and social norm violation, and for rapport (in 30 s thin slices). We then performed a fine-grained investigation of how the temporal profiles of sequences of interlocutor behaviors predict increases and decreases of rapport, and how this rapport management manifests differently in friends and strangers. We validated the discovered behavioral patterns by predicting rapport against our ground truth via a forecasting model involving two-step fusion of learned temporal associated rules. Our framework performs significantly better than a baseline linear regression method that does not encode temporal information among behavioral features. Implications for the understanding of human behavior and social agent design are discussed.