Automated Warranting Detection Codebook

The Automated Warranting Detection Codebook captures the process of detecting discourse patterns with machine learning and orientates rhetoricians to machine learning applications. I worked with statistical computing language R to conduct feature identification on a corpus of drug funding profiles and disclosures for warranting, a mode of argumentation designed to lend support to evidence not entirely trusted by the audience. We sought to determine how funding profiles and attendant conflicts of interest change discourse patterns in biomedical publishing. Our analysis and co-written article contribute to ongoing inquiry on the effects of conflicts of interest on both medical discourse and outcomes.