First page Back Continue Last page Overview Graphics
Relationship Inference : Previous Work
Relationship Inference / Conversation Analysis
- Human Monitoring: (Drew, Heritage, Zimmerman)
- Speech Features: Conversation Scene Analysis (Basu 02)
Social Network Inference
- Surveys: Traditional Social Network Analysis
- IR Sensors: ShortCuts (Choudhury02, Carley99)
- Affiliation Networks
- Email Lists, Board of Directions, Movies, Journals, Projects
- Theoretical: Small World / Complex Networks
- Kleinberg: Local Information
- Problems within Social Navigation Models
There has been significant work done in human-monitored conversation analysis and sumit basu began work to automatically infer different relationships based on speech features such as pitch, speaking rate, energy and duration. And I’m attempting to build on that work in my own thesis.
Likewise there have been much work on inferring network structure – from surveys to IR sensors, to even looking at affiliation networks from journal co-authorship to movies.
The theoretical community have been relying on these data sets simply because there really isn’t a lot out of other data to by which to test their models. In one of Watt’s recent papers, he even so far as to bring back Milgram’s actual results for a comparison to his own models. – We’re living in the 21st century, there has got to be a better way to collect data on human behavior.
According to Don Zimmerman and Deidre Boden, multi-party situations tend to break down into two-party, or dyadic, talk (Zimmerman & Boden, 1991).