Automatic Bill Recommendation for Statehouse Journalists.

AI4Reporters is a project designed to produce automated electronic tip sheets for news reporters covering the statehouses (state level legislatures) in the United States. The project aims to capture the most important information that occurred in a bill discussion to allow reporters to quickly decide if they want to pursue a story on the subject. In this paper, we present, discuss and evaluate a module for the tip sheets that is designed to recommend additional bills to investigate for the reporter that receives the tip sheet. Similar in concept to movie recommendations, this module is designed to find other bills with their own meetings and discussions, that are most relevant to the discussion captured in the given tip sheet. Specifically we present similarity algorithms along three dimensions that our investigation suggests are distinct reasons for journalists to be interested in a recommendation. These include similarity in content, individuals or geographical locations. We validate the system by fielding a user study of 29 subjects for hour-long surveys resulting in 870 decisions being captured. We find that between 63.4% and 82.8% of the human selections are in agreement with our system’s recommendations.