arXiv:2404.01336v1 Announce Type: cross
Abstract: Existing benchmarks for fake news detection have significantly contributed to the advancement of models in assessing the authenticity of news content. However, these benchmarks typically focus solely on news pertaining to a single semantic topic or originating from a single platform, thereby failing to capture the diversity of multi-domain news in real scenarios. In order to understand fake news across various domains, the external knowledge and fine-grained annotations are indispensable to provide precise evidence and uncover the diverse underlying strategies for fabrication, which are also ignored by existing benchmarks. To address this gap, we introduce a novel multi-domain knowledge-enhanced benchmark with fine-grained annotations, named textbf{FineFake}. FineFake encompasses 16,909 data samples spanning six semantic topics and eight platforms. Each news item is enriched with multi-modal content, potential social context, semi-manually verified common knowledge, and fine-grained annotations that surpass conventional binary labels. Furthermore, we formulate three challenging tasks based on FineFake and propose a knowledge-enhanced domain adaptation network. Extensive experiments are conducted on FineFake under various scenarios, providing accurate and reliable benchmarks for future endeavors. The entire FineFake project is publicly accessible as an open-source repository at url{}.

Introducing FineFake: A Multi-Domain Knowledge-Enhanced Benchmark for Fake News Detection

Fake news has become a pervasive issue in today’s information landscape. As the spread of misinformation continues to grow, it is crucial to develop effective methods for detecting and combating fabricated news content. Existing benchmarks for fake news detection have made significant progress in this area, but they often fall short in capturing the diversity of multi-domain news.

This is where FineFake comes in. FineFake is a groundbreaking multi-domain knowledge-enhanced benchmark that goes beyond existing benchmarks by encompassing a wide range of semantic topics and platforms. With 16,909 data samples spanning six semantic topics and eight platforms, FineFake provides a comprehensive view of fake news across various domains.

What sets FineFake apart is its inclusion of external knowledge and fine-grained annotations. These additional layers of information enable us to provide precise evidence and uncover the diverse underlying strategies employed in fabricating news. By going beyond conventional binary labels, FineFake offers a deeper understanding of the complexity of fake news.

Notably, FineFake enriches each news item with multi-modal content, potential social context, and semi-manually verified common knowledge. This multidisciplinary approach allows us to analyze the news from multiple perspectives, taking into account both textual and visual elements. By including these diverse elements, FineFake reflects the multi-dimensional nature of multimedia information systems.

The release of FineFake also comes with three challenging tasks formulated based on the benchmark. These tasks provide a roadmap for future research and development in the field of fake news detection. To tackle these tasks, the authors propose a knowledge-enhanced domain adaptation network, which leverages the external knowledge integrated into FineFake. This approach highlights the importance of incorporating knowledge from different domains to effectively detect fake news.

In order to ensure the reliability and accuracy of the benchmark, extensive experiments have been conducted on FineFake under various scenarios. The results demonstrate its effectiveness and the potential it holds for future endeavors in fake news detection.

As a multidisciplinary benchmark, FineFake is not only relevant to the field of fake news detection but also closely connected to other areas such as multimedia information systems, animations, artificial reality, augmented reality, and virtual realities. The inclusion of multi-modal content aligns with the multimedia nature of these fields, while the knowledge-enhanced approach relates to the advancement of artificial reality and augmented reality technologies.

In conclusion, FineFake represents a significant step forward in the fight against fake news. By capturing the multi-domain nature of fake news and providing fine-grained annotations, FineFake opens up new possibilities for understanding and combating misinformation in our increasingly complex information ecosystem. It serves as a valuable resource and benchmark for researchers and practitioners alike, paving the way for future advancements in the field.


Suggested Readings:

Read the original article