Classification of news spreading barriers
This addresses the problem of understanding why some news events remain regionally limited, which is relevant for media analysts and researchers, though it appears incremental as it builds on existing classification methods with semantic enhancements.
The paper tackles the problem of classifying news-spreading barriers (e.g., political, geographical) by proposing an approach that infers semantics through Wikipedia concepts, using news articles annotated via publisher metadata. The results show this method outperforms classical text classification, deep learning, and transformer-based approaches in performance.
News media is one of the most effective mechanisms for spreading information internationally, and many events from different areas are internationally relevant. However, news coverage for some news events is limited to a specific geographical region because of information spreading barriers, which can be political, geographical, economic, cultural, or linguistic. In this paper, we propose an approach to barrier classification where we infer the semantics of news articles through Wikipedia concepts. To that end, we collected news articles and annotated them for different kinds of barriers using the metadata of news publishers. Then, we utilize the Wikipedia concepts along with the body text of news articles as features to infer the news-spreading barriers. We compare our approach to the classical text classification methods, deep learning, and transformer-based methods. The results show that the proposed approach using Wikipedia concepts based semantic knowledge offers better performance than the usual for classifying the news-spreading barriers.