Abstract

Social media facilitate interaction and information dissemination among an unprecedented number of participants. Why do users contribute, and why do they contribute to a specific venue? Does the information they receive cover all relevant points of view, or is it biased? The substantial and increasing importance of online communication makes these questions more pressing, but also puts answers within reach of automated methods. I investigate scalable algorithms for understanding two classes of incentives which arise in collective intelligence processes. Product incentives exist when contributors have a stake in the information delivered to other users. I investigate product-relevant user behavior changes, algorithms for characterizing the topics and points of view presented in peer-produced content, and the results of a field experiment with a prediction market framework having associated product incentives. Process incentives exist when users find contributing to be intrinsically rewarding. Algorithms which are aware of process incentives predict the effect of feedback on where users will make contributions, and can learn about the structure of a conversation by observing when users choose to participate in it. Learning from large-scale social interactions allows us to monitor the quality of information and the health of venues, but also provides fresh insights into human behavior.

Committee Chair

Sanmay Das

Committee Members

Yoram Bachrach, Roman Garnett, Roch Guerin, Yulia Nevskaya,

Comments

Permanent URL: https://doi.org/10.7936/K7DB803S

Degree

Doctor of Philosophy (PhD)

Author's Department

Computer Science & Engineering

Author's School

McKelvey School of Engineering

Document Type

Dissertation

Date of Award

Spring 5-15-2016

Language

English (en)

Author's ORCID

https://orcid.org/0000-0002-3155-7245

Download

Share

COinS