How might we understand a dialogue as a whole? How might we explore how conversations flow thematically across time?
Using natural language processing and machine learning, we discover emergent themes and patterns within our dialogue data set. We map out each person's contribution in a two dimensional map, those most similar to one another being closest together. By chaining each contribution together and analyzing the dialogue as a whole, we see how the chain of thought within one conversation can bounce around over time.
Conversation Chains invites us to dynamically explore these conversations in a data set, be they organized by time or by topic, and listen to those voices and discussions as the conversation's chain of thought evolves.
