Online deliberation seeks to improve group decision making by accessing diverse expertise and experience, informing and marshaling evidence in a fruitful exchange of ideas. Successful deliberation environments can bring great benefits, such as broadening participation, tapping a greater range of knowledge, testing ideas against each other, and fostering appreciation of other views. However, for large and complex problem spaces that generate extensive discussion, it is difficult for would-be participants to find where they could best make a contribution, to understand how various contributions fit together, or to grasp the contingencies between needs and contributions.
To address this problem, this project will develop and test a system that provides a personalized view of a large information space that reveals the shape and foci of contributions in a way that reflects the goals, expertise, and interests of each user. The system will allow participants to see how their goals and interests match current themes and to find groups of people and related sets of contributions that would be of interest. To do this, the research will integrate insights from sociolinguistics with state-of-the-art latent variable modeling techniques from the field of language technologies to extend prior work in the areas of perspective and stance modeling in order to identify the necessary structure in textual data to enable personalized information extraction, summarization, and presentation.
The project includes archival data analysis to develop algorithms and data representations, experiments to test the value to users of various ways of representing topics and social networks, a staged series of deployments for formative and summative evaluation, and the development of tool architecture and user interfaces to support experimentation and deployment. Through these activities, the investigators will systematically explore the effects of design decisions on participation, navigability and the nature of the deliberation.
