Multi-Label and Multilingual News Framing Analysis


News framing refers to the strategy in which aspects of certain issues are highlighted in the news to promote a particular interpretation. In NLP, although recent works have studied framing in English news, few have studied how the analysis can be extended to other languages and in a multi-label setting. In this work, we explore multilingual transfer learning to detect multiple frames from just the news headline in a genuinely low-resource setting where there are few/no frame annotations in the target language. We propose a novel method that can leverage very basic resources consisting of a dictionary and few annotations in a target language to detect frames in the language. Our method performs comparably or better than translating the entire target language headline to the source language for which we have annotated data. This opens up an exciting new capability of scaling up frame analysis to many languages, even those without existing translation technologies. Lastly, we apply our method to detect frames on the issue of U.S. gun violence in multiple languages and obtain interesting insights on the relationship between different frames of the same issue across different countries with different languages.

In Association of Computational Linguistics 2020