Context-based Message Expansion for Disentanglement of Interleaved Text Conversations

Computational processing of text exchanged in interactive venues in which participants engage in simultaneous conversations can benefit from techniques for automatically grouping overlapping sequences of messages into separate conversations, a problem known as “disentanglement.” While previous methods exploit both lexical and non-lexical information that exists in conversations for this task, the inter-dependency between the meaning of a message and its temporal and social contexts is largely ignored. Our approach exploits contextual properties (both explicit and hidden) to probabilistically expand each message to provide a more accurate message representation. Extensive experimental evaluations show our approach outperforms the best previously known technique.