Do All Good Actors Look The Same? Exploring News Veracity Detection Across The U.S. and The U.K
This highlights a critical limitation for researchers and practitioners in misinformation detection, as it is incremental in testing existing methods across new cultural contexts.
The paper tackled the problem of text-based news veracity detection not generalizing across countries and cultures, showing that classifiers perform poorly when trained on U.S. data and tested on U.K. data, and vice versa, with specific issues in classifying unseen unreliable sources.
A major concern with text-based news veracity detection methods is that they may not generalize across countries and cultures. In this short paper, we explicitly test news veracity models across news data from the United States and the United Kingdom, demonstrating there is reason for concern of generalizabilty. Through a series of testing scenarios, we show that text-based classifiers perform poorly when trained on one country's news data and tested on another. Furthermore, these same models have trouble classifying unseen, unreliable news sources. In conclusion, we discuss implications of these results and avenues for future work.