UofA-Truth at Factify 2022 : Transformer And Transfer Learning Based Multi-Modal Fact-Checking

Identifying fake news is a very difficult task, especially when considering the multiple modes of conveying information through text, image, video and/or audio. We attempted to tackle the problem of automated misinformation/disinformation detection in multi-modal news sources (including text and images) through our simple, yet effective, approach in the FACTIFY shared task at De-Factify@AAAI2022. Our model produced an F1-weighted score of 74.807%, which was the fourth best out of all the submissions. In this paper we will explain our approach to undertake the shared task.

cs.MM cs.AI cs.CL Misinformation and Its Impacts Topic Modeling Hate Speech and Cyberbullying Detection Computer Science

View graph Source

Paper

References (15)

01Sentence-BERT: Sentence Embeddings using Siamese BERT-NetworksNils Reimers, Iryna Gurevych2019 · Conference on Empirical Methods in Natural Language Processing · 19k citations In Library

02A Retrospective Analysis of the Fake News Challenge Stance-Detection TaskAndreas Hanselowski, S. AvineshP.V., Benjamin Schiller et al.2018 · International Conference on Computational Linguistics · 268 citations In Library

03A simple but tough-to-beat baseline for the Fake News Challenge stance detection taskB. Riedel, Isabelle Augenstein, Georgios P. Spithourakis et al.2017 · arXiv.org · 253 citations In Library

04Xception: Deep Learning with Depthwise Separable ConvolutionsFrançois Chollet2016 · Computer Vision and Pattern Recognition · 18k citations In Library

05XGBoost: A Scalable Tree Boosting SystemTianqi Chen, Carlos Guestrin2016 · Knowledge Discovery and Data Mining · 58k citations In Library

06Distilling the Knowledge in a Neural NetworkGeoffrey E. Hinton, O. Vinyals, J. Dean2015 · arXiv.org · 25k citations In Library

07FACTIFY: A Multi-Modal Fact Verification DatasetShreyash Mishra, S. Suryavardan, Amrit Bhaskar et al.2022 · DE-FACTIFY@AAAI · 75 citations

08International fact-checking network2021

09athene_system2018 · https://github.com/ hanselowski/athene_system

10Verified signatories of the ifcn code of principles2021

11santiagonasar2020 · Rusty, Rushat, L. Lopez, Piotti, Preprocessor, https://github.com/ s/preprocessor

12Stance detection: A survey2020 · ACM Computing Surveys 53

Scroll for more · 3 remaining

Similar papers

Findings of Factify 2: Multimodal Fake News DetectionS Suryavardan, Shreyash Mishra, Megha Chakraborty et al.2023 · arXiv (Cornell University) · 18 citations In Library

Logically at Factify 2022: Multimodal Fact VerificationJie Gao, Hella-Franziska Hoffmann, Stylianos Oikonomou et al.2021 · arXiv (Cornell University) In Library

INO at Factify 2: Structure Coherence based Multi-Modal Fact VerificationYinuo Zhang, Zhulin Tao, Xi Wang et al.2023 · arXiv (Cornell University) · 7 citations In Library

Logically at Factify 2: A Multi-Modal Fact Checking System Based on Evidence Retrieval techniques and Transformer Encoder ArchitectureP. J. Verschuuren, Jie Gao, Adelize van Eeden et al.2023 · arXiv (Cornell University) · 2 citations In Library

Team Yao at Factify 2022: Utilizing Pre-trained Models and Co-attention Networks for Multi-Modal Fact VerificationWei‐Yao Wang, Wen-Chih Peng2022 · arXiv (Cornell University) · 10 citations In Library

Team Triple-Check at Factify 2: Parameter-Efficient Large Foundation Models with Feature Representations for Multi-Modal Fact VerificationWeiwei Du, Hong-Wei Wu, Wei‐Yao Wang et al.2023 · arXiv (Cornell University) · 14 citations In Library

FACTIFY3M: A Benchmark for Multimodal Fact Verification with Explainability through 5W Question-AnsweringMegha Chakraborty, Pahwa, Khushbu, Anku Rani et al.2023 · arXiv (Cornell University) · 16 citations In Library

FactVerify AI: An End-to-End Cross-Lingual Fact Verification Pipeline Using Transformer ModelsK. Hrudayesh, N.Sathwika2026 · Zenodo (CERN European Organization for Nuclear Research) In Library

FactVerify AI: An End-to-End Cross-Lingual Fact Verification Pipeline Using Transformer ModelsK. Hrudayesh, N.Sathwika2026 · Zenodo (CERN European Organization for Nuclear Research) In Library

Fake News Detection and Fact-Checking SystemMonu Saini2025 · International Journal for Research in Applied Science and Engineering Technology In Library

Source of record

arXiv

44B

Welcome.

This panel sticks with you. Pick anything below and it opens right beside it, so you can dig through 60,000-plus records without ever losing your spot here.

Travel 44B

LibraryPapers, policy, standards, statute LabsEvery organization building AI ModelsIntelligence, price, and speed BenchmarksThe evaluation catalog IncidentsAI failures and harms SearchOne field across everything DashboardThe state of AI accountability in NY 44B RegistryThe Art. 44-B compliance portal