Event

It's Not You, it's Me: Automatically Extracting Social Meaning from Speed Dates

Dan Jurafsky

Stanford

Tuesday, July 14, 2009
12:30

Automatically detecting human social intentions from spoken conversation is an important task for social computing and for dialogue systems. We describe a system for detecting elements of interactional style: whether a speaker is awkward, friendly, or flirtatious. We create and use a new spoken corpus of 991 4-minute speed-dates. Participants rated themelves and each other for these elements of style. Using rich dialogue, lexical, disfluency, and prosodic features, we are able to detect flirtatious, awkward, and friendly styles in noisy natural conversational data with above 70% accuracy, significantly outperforming not only the baseline but also the human interlocutors. We find that features like rate of speech, pitch range, energy, and the use of questions help detect flirtatious speakers, collaborative conversational style (laughter, collaborative completions, questions, and second person pronouns) help in detecting friendly speakers, and disfluencies help in detecting awkward speakers. In analyzing why our system outperforms humans, we show that humans are very poor perceivers of flirtatiousness or friendliness in others, instead often projecting their own intended behavior onto their interlocutors. This talk describes joint work with Dan McFarland (School of Education) and Rajesh Ranganath (Computer Science Department).