Context in Informational Bias Detection
This work addresses the problem of accurately detecting informational bias in news articles, which is important for readers to identify subtle opinion-swaying information.
This paper explores the role of four types of context in detecting informational bias in English news articles, finding that integrating event context improves classification performance over a strong baseline. The best-performing context-inclusive model shows improved performance on longer sentences and articles from politically centrist sources.
Informational bias is bias conveyed through sentences or clauses that provide tangential, speculative or background information that can sway readers' opinions towards entities. By nature, informational bias is context-dependent, but previous work on informational bias detection has not explored the role of context beyond the sentence. In this paper, we explore four kinds of context for informational bias in English news articles: neighboring sentences, the full article, articles on the same event from other news publishers, and articles from the same domain (but potentially different events). We find that integrating event context improves classification performance over a very strong baseline. In addition, we perform the first error analysis of models on this task. We find that the best-performing context-inclusive model outperforms the baseline on longer sentences, and sentences from politically centrist articles.