用图文融合方法提升印度假新闻识别准确率
F2IND-IT! -- Multimodal Fuzzy Fake Indian News Detection using Images and Text
- 结合图像与文本特征，通过注意力机制动态加权融合
- 在IFND数据集上准确率达92.3%，F1分数达91.1%
- 适合关注多模态假信息检测的AI研究者与媒体安全从业者
印度等地的区域与全国性媒体普遍存在事实偏倚，给虚假新闻检测带来挑战。本文提出一种新颖的多模态框架，融合视觉与文本信息以增强对印度媒体假新闻的识别能力。该架构采用ResNet-50提取新闻图片的视觉特征，使用DistilBERT编码器获取文本语义嵌入，并通过自适应神经模糊推理系统（ANFIS）生成模糊可靠性评分。一个轻量级基于注意力的融合模块在分类前为各模态分配可学习权重。在IFND数据集上的评估表明，所提模型在准确率、精确率、召回率和F1分数上均优于现有方法，验证了其有效性。
原文摘要 · Abstract (English)
Biased manipulation of facts across regional and national media outlets complicates misinformation detection in diverse landscapes like India. This paper introduces a novel multimodal framework combining visual and textual modalities for enhanced fake news detection on Indian media. The architecture utilizes a ResNet-50 Convolutional Neural Network to extract visual features from news images, a DistilBERT encoder to obtain textual semantic embeddings, and an Adaptive Neuro-Fuzzy Inference System (ANFIS) to generate a fuzzy reliability score. A lightweight attention-based fusion module assigns learnable weights to each modality prior to classification. Evaluated on the IFND dataset, the proposed model is validated through an in-depth comparative analysis against previous research. Experimental results demonstrate superior performance across accuracy, precision, recall, and $F_1$-scores, confirming the efficacy of the architecture.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。