• Prachi Vishnu Wankhede
• Krushna Ankushrao Kale
• Shamma Ayubkhan Pathan
• Madhuri Ganesh Dange

The dramatic advent of social media has changed everything from making material to sharing it and using it. The digital revolution, on the other hand, has made it easier for fake news to spread, which is a big threat to public trust, political stability, and social awareness. This study presents a deep learning framework capable of detecting bogus news articles by integrating visual and linguistic data from social media posts. The system uses NLP methods like TF-IDF and Word2Vec to represent text. It uses CNNs like VGG16 and ResNet50 to get visual features. By putting together the features that were found, a full picture is formed that can show how images and text interact in terms of meaning and context. The next stage is to use a Dense Neural Network (DNN) classifier to figure out if news stories are real. When tested on benchmark datasets, the proposed model is more accurate and robust than the best text-only techniques. The results show that combining visual and textual signals makes the algorithm better at spotting altered or misleading information on social media sites.

Detecting fake news, multi-modal learning, deep learning, social media, TF-IDF, Word2Vec, CNN, feature fusion, verifying authenticity, and finding false information.

"A Multi-Modal Deep Learning Framework for Detecting Fake News Utilizing Textual and Visual Features ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.13, Issue 3, page no.d296-d303, March-2026, Available :http://www.jetir.org/papers/JETIR2603336.pdf

"A Multi-Modal Deep Learning Framework for Detecting Fake News Utilizing Textual and Visual Features ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.13, Issue 3, page no. ppd296-d303, March-2026, Available at : http://www.jetir.org/papers/JETIR2603336.pdf