Simulating Audiences: Automating Analysis of Values, Attitudes, and Sentiment

Current events such as the Park51 Project in downtown Manhattan create "critical discourse moments," explosions of discourse around a topic that can be exploited for data gathering. Policymakers have a need to understand the dynamics of public discussion in real time. Human values, which are cognitively related to attitudes and serve as reference points in moral argument, are important indicators of what\´s at stake in a public controversy. This work shows that it is possible to link values data with reader behavior to infer values implicit in a topical corpus, and that it is possible to automate this process using machine learning.