Dissertation Title: Learning Human Beliefs with Language Models
Media plays an important role in shaping people's beliefs and behaviors. Mass media and social media reflect and form public opinion, which can ultimately lead to positive outcomes such as civil engagement with opposing tribes, but also negative outcomes such as non-adherence to health-beneficial social guidelines. Understanding viewpoints expressed online, and the relationship between media content and beliefs, is increasingly pertinent today in a world of constant connectivity and "alternate realities”.
This dissertation introduces new deep, neural language model -based approaches for capturing beliefs reflected in and formed by media. In part one of this dissertation, we introduce a model for automatically summarizing multiple documents about the same subject. Summaries can help people with information overload, hear the most salient viewpoints from people in different communities, and help journalists with downstream writing tasks. In contrast to typical approaches that require large, labeled datasets, our method was the first unsupervised model for abstractive multi-document summarization.
In part two of the dissertation, motivated by the effects of information in the COVID-19 pandemic, we introduce an approach for using "media diet models", which can act as proxies for human media consumption. By probing these models, we can predict public opinion as measured by nationally representative surveys. We validate our method in two domains: attitudes towards COVID-19 and consumer confidence. We find that it is robust and has predictive power across mediums and outlets, is sensitive to how closely people are following the news, and has intuitive differences in performance across question types. These results both provide insight into a driving force of human belief formation and suggest practical implications for pollsters, public health officials, and policymakers moving forward.
Professor of Media Arts and Sciences
MIT Media Lab
MIT EECS & CSAIL
Professor of Government