Fine-Grained Analysis of Team Collaborative Dialogue
This work addresses the understudied domain of natural language analysis for team collaborative dialogue, focusing on software development, but it is incremental as it builds on prior methods like LSA.
The paper tackled the problem of generating fine-grained descriptions of team dynamics and individual performance from collaborative chat dialogues, particularly in software development using Slack chats, by developing a hierarchical labeling scheme and descriptive metrics, with initial results using a transformer + CRF architecture.
Natural language analysis of human collaborative chat dialogues is an understudied domain with many unique challenges: a large number of dialogue act labels, underspecified and dynamic tasks, interleaved topics, and long-range contextual dependence. While prior work has studied broad metrics of team dialogue and associated performance using methods such as LSA, there has been little effort in generating fine-grained descriptions of team dynamics and individual performance from dialogue. We describe initial work towards developing an explainable analytics tool in the software development domain using Slack chats mined from our organization, including generation of a novel, hierarchical labeling scheme; design of descriptive metrics based on the frequency of occurrence of dialogue acts; and initial results using a transformer + CRF architecture to incorporate long-range context.