OUR EVENTS

The Center for Technology and Social Behavior hosts a monthly speaker series that brings internationally renowned speakers to Northwestern University to meet with our researchers and present on a topic relevant to technology and social behavior. This year's lineup includes a brilliant collection of guests from around the world. You can also visit our CTSB Speaker Series Google Calendar for a complete listing of times and locations.

CTSB Lecture Series

Oct 27, 2009, 12pm
Barbara Rogoff, UC Santa Cruz
Cultural Aspects of Learning: Observation, Collaboration, and Multimodal Conversation
Frances Searle 1-483

Oct 29, 2009, 4pm
Dan Jurafsky, Stanford University
It's Not You, it's Me: Automatically Extracting Social Meaning from Speed Dates
Frances Searle 1-421

Nov 12, 2009, 4pm
Shinobu Kitayama, University of Michigan
The Social Self and the Social Brain: A Perspective of Cultural Neuroscience
Frances Searle 1-421

Dec 10, 2009, 4pm
Cynthia Breazeal, MIT Media Lab
Robots as Social Learners
Ford 1.350 (ITW)

Jan 21, 2010, 4pm
Pamela Hinds, Stanford University
Situated Knowing Who: Why Site Visits Matter in Global Work

Feb 18, 2010, 4pm
Fernanda Viégas, IBM Research
Visualizing the Inner Lives of Texts

Mar 11, 2010, 4pm
Elizabeth Churchill, Yahoo! Research
TBD

Apr 29, 2010, 4pm
Matthew Kam, Carnegie Mellon University
MILLEE: Mobile and Immersive Learning for Literacy in Emerging Economies

May 13, 2010, 4pm
Jenna Burrell, UC Berkeley
Evaluating Shared Access: Social Equality and the Circulation of Mobile Phones in Rural Uganda

Dan Jurafsky
Stanford University

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

Abstract:
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).

Co-sponsored with the Cognitive Science Speaker Series