A new framework for mining frequent interaction patterns from meeting databases

Meetings play an important role in workplace dynamics in modern life since their atomic components represent the interactions among human beings. Semantic knowledge can be acquired by discovering interaction patterns from these meetings. A recent method represents meeting interactions using tree data structure and mines interaction patterns from it. However, such a tree based method may not be able to capture all kinds of triggering relations among interactions and distinguish same interaction from different participants of different ranks. Hence, it is not suitable to find all interaction patterns such as those about correlated interactions. In this paper, we propose a new framework for mining interaction patterns from meetings using an alternative data structure, namely, weighted interaction flow directed acyclic graph (WIFDAG). Specifically, a WIFDAG captures both temporal and triggering relations among interactions in meetings. Additionally, to distinguish participants from different ranks, we assign weights to nodes in the WIFDAGs. Moreover, we also propose an algorithm called WDAGMeet for mining weighted frequent interaction patterns from meetings represented by the proposed framework. Extensive experimental results are shown to signify the effectiveness of the proposed framework and the mining algorithm built on that framework for mining frequent interaction patterns from meetings.