Real Time AI Graded Platform for Debate Analysis Using CRAG and Wave2Vec2 Models
- DOI
- 10.2991/978-94-6463-948-3_62How to use a DOI?
- Keywords
- CRAG; emotion detection; deep learning; confidence detection; relevance; fact check
- Abstract
The wide spread of misinformation on the web can present a danger to the credibility and quality of online discussion. The proposed work introduces an AI platform that offers real-time fact-checking in debates by using CRAG. The system uses cutting-edge natural language processing and corrective retrieval-augmented generation to examine assertions as they are uttered and send immediate feedback regarding their factual correctness and analyses the user based on various other parameters. The proposed system’s design is scalable for deployment and its adaptable modes of verification and debate analysis. Early tests confirm the proposed system’s efficiency in enabling correct information exchange and inducing critical thinking among users. By overcoming the weaknesses of conventional, the solution provides a practical and adaptable framework for enhancing trust and ensuring information integrity in online world.
- Copyright
- © 2025 The Author(s)
- Open Access
- Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.
Cite this article
TY - CONF AU - Keshav Tambre AU - Aryan Ghadekar AU - Omkar Ghantalwad AU - Yash Gawande AU - Kirti Genge AU - Aditya Ghadge AU - Arjun Gaware PY - 2026 DA - 2026/01/06 TI - Real Time AI Graded Platform for Debate Analysis Using CRAG and Wave2Vec2 Models BT - Proceedings of the International Conference on Sustainable Innovation with Artificial Intelligence and Machine Learning 2025 (ICSIAIML 2025) PB - Atlantis Press SP - 903 EP - 914 SN - 1951-6851 UR - https://doi.org/10.2991/978-94-6463-948-3_62 DO - 10.2991/978-94-6463-948-3_62 ID - Tambre2026 ER -