Issue No. 04 - April (2012 vol. 24)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TKDE.2010.224
Zhiwen Yu , Northwestern Polytechnical University, Xi An
Zhiyong Yu , Fuzhou University, Fuzhou
Xingshe Zhou , Northwestern Polytechnical University, Xi An
Christian Becker , Mannheim University, Mannheim
Yuichi Nakamura , Kyoto University, Kyoto
Discovering semantic knowledge is significant for understanding and interpreting how people interact in a meeting discussion. In this paper, we propose a mining method to extract frequent patterns of human interaction based on the captured content of face-to-face meetings. Human interactions, such as proposing an idea, giving comments, and expressing a positive opinion, indicate user intention toward a topic or role in a discussion. Human interaction flow in a discussion session is represented as a tree. Tree-based interaction mining algorithms are designed to analyze the structures of the trees and to extract interaction flow patterns. The experimental results show that we can successfully extract several interesting patterns that are useful for the interpretation of human behavior in meeting discussions, such as determining frequent interactions, typical interaction flows, and relationships between different types of interactions.
Human interaction, interaction flow, interaction pattern, meeting, tree-based mining.
Z. Yu, C. Becker, Y. Nakamura, Z. Yu and X. Zhou, "Tree-Based Mining for Discovering Patterns of Human Interaction in Meetings," in IEEE Transactions on Knowledge & Data Engineering, vol. 24, no. , pp. 759-768, 2010.