This repository contains the full code and data for Study 2 of our research on how satirical manipulation of news articles impacts reader engagement and comprehension.
Study 2 tests whether satirical rewrites (done by Large Language Models) of traditionally avoided news topics (e.g., politics, finance, climate) increase reader preference and emotional engagement compared to standard news formats.
Participants are presented with two versions of each article (objective vs. satirical) and asked to choose their preferred version and answer follow-up questions.
Each participant is also assigned to either a transparent or non-transparent condition releated to the disclosure of AI-usage.
app/— Flask app code for serving the prototypetemplates/— HTML templates for pre/post-questionnaires and article pagesstatic/— CSS, JS, and imagesarticles.csv— Article dataset with satirical and standard versions
Note: To run all the scripts in the repository one would need access to both a NewsCatcher API key and a OpenAI API key. This is only needed if you want to test with fresh rewritten articles.
Releated to paper: Using Large Language Models to 'Lighten the Mood': Satirically Reframing News Recommendations to Reduce News Avoidance.
pip install -r requirements.txt
python app.py