Абстрактный

Discovering Patterns of Human Interaction in Meetings Using Tree-Based Mining

S.Abarna

Mining frequent tree patterns is an important research problem with broad applications in bioinformatics, digital library, e-commerce, and so on. Previous studies highly suggested that pattern-growth methods are efficient in frequent pattern mining. Multimedia records of meetings contain a rich amount of project information. However, finding detailed information in a meeting record can be difficult because there is no structural information other than time to aid navigation. In this paper we survey and discuss various ways of indexing meeting records by categorizing existing approaches along multiple dimensions. In particular, a survey of users who watch meeting recordings on a regular basis revealed that it is also useful to provide (1) speaker-related information, including who the speaker is talking to, looking at, and being interrupted by, and (2) more control of the interface, including changing the relative sizes of the speaker and context views and navigating within the context view. A novel probabilistic framework is proposed for analyzing crossmodal nonverbal interactions in multiparty face-to-face conversations.