Conversation clusters: grouping conversation topics through human-computer dialog

Conversation Clusters explores the use of visualization to highlight salient moments of live conversation while archiving a meeting. Cheaper storage and easy access to recording devices allows extensive archival. However, as the size of the archive grows, retrieving the desired moments becomes increasingly difficult. We approach this problem from a socio-technical perspective and utilize human intuition aided by computer memory. We present computationally detected topics of conversation as visual summaries of discussion and as reference points into the archive. To further bootstrap the system, humans can participate in a dialog with the visualization of the clustering process and shape the development of clustering models. Author Keywords Clustering, Meeting Archival, Visualization ACM Classification Keywords H5.3 [Information interfaces and presentation]: Group and Organizational Interfaces - Synchronous interaction, Computer supported cooperative work.

• Type: Conference
• Year: 2009
• Where: CHI
• Authors: Tony Bergstrom, Karrie Karahalios
• Keywords: CHI 2009, Clustering Process, Conversation Clusters, Human Computer Interaction, Visualization ACM Classification