Identifying, Annotating, and Filtering Arguments and Opinions in Open Collaboration Systems

Download the thesis or slides.

My Ph.D. thesis, “Identifying, Annotating, and Filtering Arguments and Opinions in Open Collaboration Systems” (2013, National University of Ireland, Galway - Digital Enterprise Research Institute), addresses the problem of analysing, integrating, and reconciling information in online discussions.

The World Wide Web enables large-scale collaboration, even between groups of individuals previously unknown to one another. These online collaborations produce tangible outputs, such as encyclopedias, electronic books, maps and open source software packages. In such open collaborations systems, decisions are made through open discussions, based on the written arguments and opinions that individuals contribute. The goal of this thesis is to help people make sense of written arguments in these types of decision-making discussions.

In this thesis, we develop a 4-step procedure for sense-making in argumentative discussions. We test our procedure through studying a real-world use case: information quality discussions in Wikipedia concerning whether a particular topic should be covered in the encyclopedia. We characterize the workflow and information needs of participants and decision-makers, structure arguments to support human reasoning, and create a task-based interface that supports consensus-finding for deletion discussions in the English-language Wikipedia. In a user-based evaluation, our interface provides statistically significant improvements over the native Wikipedia discussion interface in terms of perceived usefulness, perceived ease of use, and information completeness. In a pilot study, 16 of 19 participants (84%) preferred our argumentation support interface over the native Wikipedia discussion interface.

Supplementary materials: Best link to this page: http://purl.org/jsphd
Back to academic homepage