Abstract

A major challenge for designing future social media sites allowing a broader range of user actions is the difficulty of extrapolating from experience with current sites without first distinguishing correlations from underlying causal mechanisms leading to successful communities. The growing availability of data on user activities provides new opportunities to uncover correlations among user activity, contributed content and links among users. However, such correlations do not necessarily translate into methods for predicting outcomes or improving the productivity of the user communities that arise around social media. Instead, mechanistic models and intervention experiments provide a stronger basis for establishing causal mechanisms underlying the development of social media. In particular, stochastic models of large communities are well-suited to account for the large variation in user behavior, quality of contributed content, and effect of current events. Such models readily incorporate the structure of the web site, especially how content is presented to users, and thereby indicate the likely effects of design choices for new sites. We describe the ingredients of this approach, illustrate its use on Digg, a crowdsourced web site rating stories on current events [Note: mention any other examples], and its application to developing future social media.

Date

March 24, 2011

Authors

Kristina Lerman, Aram Galstyan, Greg Ver Steeg, T Hogg

Journal

5th International AAAI Conference on Weblogs and Social Media (ICWSM), Barcelona, Spain