The COVID That Wasn't: Counterfactual Journalism Using GPT
This work addresses researchers seeking to simulate large-scale cultural processes using text generation, but it is incremental as it applies an existing method to new data for analysis.
The paper tackled the problem of assessing human interpretations of real-world events by using a pre-2020 language model to generate counterfactual news articles about COVID-19 based on actual headlines, finding that the generated articles were considerably more negative and had significantly lower reliance on geopolitical framing compared to 5,082 real CBC News articles.
In this paper, we explore the use of large language models to assess human interpretations of real world events. To do so, we use a language model trained prior to 2020 to artificially generate news articles concerning COVID-19 given the headlines of actual articles written during the pandemic. We then compare stylistic qualities of our artificially generated corpus with a news corpus, in this case 5,082 articles produced by CBC News between January 23 and May 5, 2020. We find our artificially generated articles exhibits a considerably more negative attitude towards COVID and a significantly lower reliance on geopolitical framing. Our methods and results hold importance for researchers seeking to simulate large scale cultural processes via recent breakthroughs in text generation.