# Misinformation Detection on YouTube Using Video Captions

arXiv: https://arxiv.org/abs/2107.00941 · HTML: https://mlsanity.com/paper/2107.00941/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 66 references that are in the map.
- First posted on arXiv 2 Jul 2021.

## Builds on (most cited first, 11 of 11)

- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Fake News Detection on Social Media: A Data Mining Perspective](https://mlsanity.com/paper/1708.01967/) (2017)
- [Automatic Detection of Fake News](https://mlsanity.com/paper/1708.07104/) (2017)
- [Attention in Natural Language Processing](https://mlsanity.com/paper/1902.02181/) (2019)
- [DeClarE: Debunking Fake News and False Claims using Evidence-Aware Deep Learning](https://mlsanity.com/paper/1809.06416/) (2018)
- [Automated Fact Checking: Task formulations, methods and future directions](https://mlsanity.com/paper/1806.07687/) (2018)
- [A Retrospective Analysis of the Fake News Challenge Stance Detection Task](https://mlsanity.com/paper/1806.05180/) (2018)
- [A Survey of Fake News: Fundamental Theories, Detection Methods, and Opportunities](https://mlsanity.com/paper/1812.00315/) (2018)
- [Identifying Possible Rumor Spreaders on Twitter: A Weak Supervised Learning Approach](https://mlsanity.com/paper/2010.07647/) (2020)
- [Rumor Detection on Social Media: Datasets, Methods and Opportunities](https://mlsanity.com/paper/1911.07199/) (2019)
- [Neural Architectures for Fine-Grained Propaganda Detection in News](https://mlsanity.com/paper/1909.06162/) (2019)

## Built on by (most cited first, 12 of 12)

- [FakingRecipe: Detecting Fake News on Short Video Platforms from the Perspective of Creative Process](https://mlsanity.com/paper/2407.16670/) (2024)
- [Combating Online Misinformation Videos: Characterization, Detection, and Future Directions](https://mlsanity.com/paper/2302.03242/) (2023)
- [DEAP-FAKED: Knowledge Graph based Approach for Fake News Detection](https://mlsanity.com/paper/2107.10648/) (2021)
- [GAME-ON: Graph Attention Network based Multimodal Fusion for Fake News Detection](https://mlsanity.com/paper/2202.12478/) (2022)
- [Misleading the Covid-19 vaccination discourse on Twitter: An exploratory study of infodemic around the pandemic](https://mlsanity.com/paper/2108.10735/) (2021)
- [Identifying Misinformation on YouTube through Transcript Contextual Analysis with Transformer Models](https://mlsanity.com/paper/2307.12155/) (2023)
- [Misinformation Concierge: A Proof-of-Concept with Curated Twitter Dataset on COVID-19 Vaccination](https://mlsanity.com/paper/2309.00639/) (2023)
- [COVID-19 on YouTube: A Data-Driven Analysis of Sentiment, Toxicity, and Content Recommendations](https://mlsanity.com/paper/2412.17180/) (2024)
- [AMIR: Automated MisInformation Rebuttal -- A COVID-19 Vaccination Datasets based Recommendation System](https://mlsanity.com/paper/2310.19834/) (2023)
- [Online Misinformation Detection in Live Streaming Videos](https://mlsanity.com/paper/2503.12627/) (2025)
- [Multimodal Learning for Fake News Detection in Short Videos Using Linguistically Verified Data and Heterogeneous Modality Fusion](https://mlsanity.com/paper/2509.15578/) (2025)
- [Misinformation Span Detection in Videos via Audio Transcripts](https://mlsanity.com/paper/2604.21767/) (2026)

## Abstract (arXiv)

Millions of people use platforms such as YouTube, Facebook, Twitter, and other mass media. Due to the accessibility of these platforms, they are often used to establish a narrative, conduct propaganda, and disseminate misinformation. This work proposes an approach that uses state-of-the-art NLP techniques to extract features from video captions (subtitles). To evaluate our approach, we utilize a publicly accessible and labeled dataset for classifying videos as misinformation or not. The motivation behind exploring video captions stems from our analysis of videos metadata. Attributes such as the number of views, likes, dislikes, and comments are ineffective as videos are hard to differentiate using this information. Using caption dataset, the proposed models can classify videos among three classes (Misinformation, Debunking Misinformation, and Neutral) with 0.85 to 0.90 F1-score. To emphasize the relevance of the misinformation class, we re-formulate our classification problem as a two-class classification - Misinformation vs. others (Debunking Misinformation and Neutral). In our experiments, the proposed models can classify videos with 0.92 to 0.95 F1-score and 0.78 to 0.90 AUC ROC.