Media profiling offers valuable insights to enhance the objectivity and reliability of news coverage by providing comprehensive analysis, but the diversity in languages posed significant challenges to our identification of factuality and political bias of non-English sources. The limitation of existing media analysis research is its concentration on a singular high-resource language, and it hardly extends to languages beyond English. To address this, we introduce xMP, a dataset for zero-shot cross-lingual media profiling tasks. xMP’s cross-lingual test set encompasses 34 non-English languages and 18 language families, extending media profiling beyond English resources and allowing us to assess cross-lingual media profiling model performance. Additionally, we propose a method, named R-KAT, to enhance the model’s zero-shot cross-lingual transfer learning capability by building virtual multilingual embedding. Our experiments illustrate that our method improves the transferability of models in cross-lingual media profiling tasks. Additionally, we further discuss the performance of our method for different target languages. Our dataset and code are publicly available.

News media profiling is helpful in preventing the spread of fake news at the source and maintaining a good media and news ecosystem. Most previous works only extract features and evaluate media from one dimension independently, ignoring the interconnections between different aspects. This paper proposes a novel news media bias and factuality profiling framework assisted by correlated features. This framework models the relationship and interaction between media bias and factuality, utilizing this relationship to assist in the prediction of profiling results. Our approach extracts features independently while aligning and fusing them through recursive convolution and attention mechanisms, thus harnessing multi-scale interactive information across different dimensions and levels. This method improves the effectiveness of news media evaluation. Experimental results indicate that our proposed framework significantly outperforms existing methods, achieving the best performance in Accuracy and F1 score, improving by at least 1% compared to other methods. This paper further analyzes and discusses based on the experimental results.