From Toxicity in Online Comments to Incivility in American News: Proceed with Caution
This paper addresses the problem of accurately quantifying incivility in news for political scientists, showing that existing toxicity models are insufficient and can lead to incorrect conclusions.
This paper investigates the applicability of the Jigsaw Perspective API, a toxicity model, for detecting incivility in American news. It demonstrates that this model is inadequate for the task, highlighting the need to address spurious correlations between identity descriptors and incivility.
The ability to quantify incivility online, in news and in congressional debates, is of great interest to political scientists. Computational tools for detecting online incivility for English are now fairly accessible and potentially could be applied more broadly. We test the Jigsaw Perspective API for its ability to detect the degree of incivility on a corpus that we developed, consisting of manual annotations of civility in American news. We demonstrate that toxicity models, as exemplified by Perspective, are inadequate for the analysis of incivility in news. We carry out error analysis that points to the need to develop methods to remove spurious correlations between words often mentioned in the news, especially identity descriptors and incivility. Without such improvements, applying Perspective or similar models on news is likely to lead to wrong conclusions, that are not aligned with the human perception of incivility.