Date: Wednesday, Jan 16th
Room: GHC 6501
Whether it's making music, movies, or encyclopedias, collaborative projects in online communities are becoming more common. Yet we know little about how these creative teams form, and what leads to their ultimate success. In this talk, I will discuss a recent study of an online songwriting community called February Album Writing Month (FAWM.ORG). By analyzing four years of longitudinal behavioral data using a novel path-based regression method --- which performs random walks on the social network itself --- we can both (1) accurately predict collabs that will form, and (2) gain insight into factors affect how online collabs form, contributing to theory as well. Combined with a large-scale survey of community members, we find that communication, compatible but complementary interests, and slight differences in social status are major contributors to collab formation; and that an equitable division of labor is a key factor in its success.
[This research is joint work with Steven Dow.]
Burr Settles is a Data Scientist and Software Engineer at Duolingo, a crowdsourcing ecosystem that combines foreign language education and translation. He also runs the website FAWM.ORG, an annual songwriting challenge for musicians worldwide. Previously, he was a postdoc in the Machine Learning Department at Carnegie Mellon, and earned a PhD in Computer Sciences from the University of Wisconsin-Madison. His research focuses on interactive machine learning that resembles a "dialogue" between computers and humans, with applications in natural language processing, biology, and social computing. He recently organized workshops at the ICML and NAACL conferences on such learning strategies. His book Active Learning (a short introduction to the field) was published in 2012 by Morgan & Claypool. In his spare time, Burr also plays guitar in the Pittsburgh pop band Delicious Pastries.