تعداد نشریات | 31 |
تعداد شمارهها | 505 |
تعداد مقالات | 4,887 |
تعداد مشاهده مقاله | 7,531,256 |
تعداد دریافت فایل اصل مقاله | 5,613,371 |
Synergistic Content Understanding: Misinformation Detection through Contrastive Regularization and Embedding-Space Mixup | ||
Contributions of Science and Technology for Engineering | ||
مقالات آماده انتشار، پذیرفته شده، انتشار آنلاین از تاریخ 15 شهریور 1404 | ||
نوع مقاله: Original Article | ||
شناسه دیجیتال (DOI): 10.22080/cste.2025.29798.1073 | ||
نویسندگان | ||
Mojtaba Padashi1؛ Meysam Roostaee* 2؛ Hassan Zeynali1؛ Alireza Jafari1 | ||
1Faculty of Engineering and Technology, University of Mazandaran | ||
2Department of computer engineering, Faculaty of Engineering and Technology, University of Mazandaran, Iran | ||
تاریخ دریافت: 16 مرداد 1404، تاریخ بازنگری: 09 شهریور 1404، تاریخ پذیرش: 10 شهریور 1404 | ||
چکیده | ||
Automated fake-news detection is a critical challenge for preserving the integrity of the online information ecosystem. Current state-of-the-art systems increasingly depend on external context, such as social propagation graphs, which fundamentally limits their applicability in real-time or “cold-start” scenarios where such signals are unavailable. We challenge the prevailing assumption that this external context is indispensable for top-tier performance. Instead, we argue that the primary bottleneck is the brittle and poorly structured content representations learned via standard model fine-tuning. To address this, we propose a synergistic training framework that sculpts a more robust and discriminative embedding space. Our method harmonizes two complementary and powerful techniques: (1) supervised contrastive regularization, which explicitly structures the feature space by enforcing tight intra-class clustering and clear inter-class separation, and (2) embedding-space mixup, a regularization strategy that creates smoother, more generalizable decision boundaries. On two widely used public benchmarks, Twitter15 and Twitter16, our purely content-only framework establishes a new state-of-the-art achieving Weighted F1-scores of 94.2% and 94.7%, respectively, significantly outperforming not only other text-based models but also leading context-aware methods. Our results demonstrate that, with a sufficiently rigorous training regimen, the intrinsic signals within text alone can drive superior veracity assessment. | ||
کلیدواژهها | ||
Misinformation Detection؛ Representation Learning؛ Supervised Contrastive Learning؛ Embedding-Space Mixup | ||
آمار تعداد مشاهده مقاله: 3 |