International Journal For Multidisciplinary Research
E-ISSN: 2582-2160
•
Impact Factor: 9.24
A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal
Home
Research Paper
Submit Research Paper
Publication Guidelines
Publication Charges
Upload Documents
Track Status / Pay Fees / Download Publication Certi.
Editors & Reviewers
View All
Join as a Reviewer
Get Membership Certificate
Current Issue
Publication Archive
Conference
Publishing Conf. with IJFMR
Upcoming Conference(s) ↓
Conferences Published ↓
DePaul-2026
IC-AIRCM-T3-2026
SPHERE-2025
AIMAR-2025
SVGASCA-2025
ICCE-2025
Chinai-2023
PIPRDA-2023
ICMRS'23
Contact Us
Plagiarism is checked by the leading plagiarism checker
Call for Paper
Volume 8 Issue 3
May-June 2026
Indexing Partners
VerifyIt: A Multi-Modal Misinformation and Fake News Detection System
| Author(s) | Mr. Vivek Bhagwat, Mr. Smit Borkhetaria, Devansh Sanghvi, Karan Parelkar, Shwetambari Borade |
|---|---|
| Country | India |
| Abstract | The rapid proliferation of misinformation and fake news across digital platforms has become a major societal concern, affecting public opinion, democratic processes, healthcare decisions, and economic stability. The scale, speed, and complexity of online information dissemination make traditional manual fact-checking approaches inadequate. In response to this challenge, this paper presents VerifyIt, a multi-modal misinformation and fake news detection system designed to provide automated,scalable, and explainable verification of digital content in real time. VerifyIt integrates Large Language Models (LLMs), Natural Language Processing (NLP) techniques, semantic similarity analysis, and real-time evidence retrieval to assess the credibility of user-submitted claims. The system supports multiple input modalities, including text, images, URLs, and audio, enabling verification across diverse digital content formats. Non-text inputs are transformed into standardized textual representations using Optical Character Recognition (OCR), speech-to-text conversion, and web scraping mechanisms. The verification pipeline decomposes complex claims into factual sub-claims, retrieves corroborating or contradictory evidence from trusted online sources, and applies probabilistic scoring models to classify information as verified or deceptive. Emphasis is placed on explainability and transparency by generating human-readable summaries that justify each verification decision. The modular and scalable architecture of VerifyIt allows efficient handling of concurrent requests and adaptability to evolving misinformation patterns. The proposed system demonstrates the potential of AI-driven fact verification in enhancing information integrity and combating the spread of misinformation in realworld digital ecosystems. |
| Keywords | Large Language Model (LLM), Fake News Detection, Natural Language Processing (NLP), Semantic Similarity, Evidence Retrieval, Claim Decomposition, Probabilistic Scoring, Knowledge-Grounded Evaluation, Explainability, Real-Time Verification, Misinformation Detection. |
| Field | Engineering |
| Published In | Volume 8, Issue 3, May-June 2026 |
| Published On | 2026-05-18 |
Share this

E-ISSN 2582-2160
CrossRef DOI is assigned to each research paper published in our journal.
IJFMR DOI prefix is
10.36948/ijfmr
Downloads
All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.
Powered by Sky Research Publication and Journals