An Affective Agent for Studying Composite Emotions

Using an affective agent to estimate humans’ composite emotions is important for creating believable interactions in human-agent collectives. However, there is a lack of suitable platforms for building large scale datasets on this topic to help researchers improve the accuracy of estimations. In this paper, we design and implement an affective agent architecture, which uses explicit emotion appraisals and a historical group emotion dataset to estimate a user’s hidden emotion compositions. The historical group emotion data are based on web users’ self-reported emotion labels of their feelings when reading news articles on sina.com.cn between 1 January to 30 June, 2013. Experiment results show that the artificially generated composite emotions of the agent are highly similar to real users’ composite emotions. Categories and Subject Descriptors I.2.11 [Artificial Intelligence]: Distributed Artificial Intelligence - Intelligent Agents Keywords Affective agent; composite emot...

• Type: Journal
• Year: 2015
• Where: ATAL
• Authors: Jun Lin, Han Yu, Chunyan Miao, Zhiqi Shen
• Keywords: ATAL 2015, Intelligent Agents