What Decisions Have You Made?: Automatic Decision Detection in Meeting Conversations

This study addresses the problem of au-tomatically detecting decisions in conver-sational speech. We formulate the prob-lem as classifying decision-making units at two levels of granularity: dialogue acts and topic segments. We conduct an em-pirical analysis to determine the charac-teristic features of decision-making dia-logue acts, and train MaxEnt models using these features for the classification tasks. We find that models that combine lexi-cal, prosodic, and topical features yield the best results on both tasks, achieving 64 % and 83 % overall accuracy, respec-tively. The study also provides a quanti-tative analysis of the relative importance of the feature types.