# COVID-19 on YouTube: A Data-Driven Analysis of Sentiment, Toxicity, and Content Recommendations

arXiv: https://arxiv.org/abs/2412.17180 · HTML: https://mlsanity.com/paper/2412.17180/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 84 references that are in the map.
- First posted on arXiv 22 Dec 2024.

## Builds on (most cited first, 10 of 10)

- [PDEBENCH: An Extensive Benchmark for Scientific Machine Learning](https://mlsanity.com/paper/2210.07182/) (2022)
- [Latent Dirichlet Allocation (LDA) and Topic modeling: models, applications, a survey](https://mlsanity.com/paper/1711.04305/) (2017)
- [Multimodal Pretraining, Adaptation, and Generation for Recommendation: A Survey](https://mlsanity.com/paper/2404.00621/) (2024)
- [Misinformation Detection on YouTube Using Video Captions](https://mlsanity.com/paper/2107.00941/) (2021)
- [A Large-Scale Dataset of Twitter Chatter about Online Learning during the Current COVID-19 Omicron Wave](https://mlsanity.com/paper/2208.07810/) (2022)
- [Sentiment Analysis and Text Analysis of the Public Discourse on Twitter about COVID-19 and MPox](https://mlsanity.com/paper/2312.10580/) (2023)
- [An Exploratory Study of Tweets about the SARS-CoV-2 Omicron Variant: Insights from Sentiment Analysis, Language Interpretation, Source Tracking, Type Classification, and Embedded URL Detection](https://mlsanity.com/paper/2208.10252/) (2022)
- [One Year of COVID-19 Vaccine Misinformation on Twitter: Longitudinal Study](https://mlsanity.com/paper/2209.01675/) (2022)
- [Reliability of Content and Echo Chambers on YouTube during the COVID-19 Debate](https://mlsanity.com/paper/2106.08684/) (2021)
- [Five Years of COVID-19 Discourse on Instagram: A Labeled Instagram Dataset of Over Half a Million Posts for Multilingual Sentiment Analysis](https://mlsanity.com/paper/2410.03293/) (2024)

## Built on by (most cited first, 2 of 2)

- [Systematic Classification of Studies Investigating Social Media Conversations about Long COVID Using a Novel Zero-Shot Transformer Framework](https://mlsanity.com/paper/2503.11845/) (2025)
- [Content and Engagement Trends in COVID-19 YouTube Videos: Evidence from the Late Pandemic](https://mlsanity.com/paper/2509.01954/) (2025)

## Abstract (arXiv)

This study presents a data-driven analysis of COVID-19 discourse on YouTube, examining the sentiment, toxicity, and thematic patterns of video content published between January 2023 and October 2024. The analysis involved applying advanced natural language processing (NLP) techniques: sentiment analysis with VADER, toxicity detection with Detoxify, and topic modeling using Latent Dirichlet Allocation (LDA). The sentiment analysis revealed that 49.32% of video descriptions were positive, 36.63% were neutral, and 14.05% were negative, indicating a generally informative and supportive tone in pandemic-related content. Toxicity analysis identified only 0.91% of content as toxic, suggesting minimal exposure to toxic content. Topic modeling revealed two main themes, with 66.74% of the videos covering general health information and pandemic-related impacts and 33.26% focused on news and real-time updates, highlighting the dual informational role of YouTube. A recommendation system was also developed using TF-IDF vectorization and cosine similarity, refined by sentiment, toxicity, and topic filters to ensure relevant and context-aligned video recommendations. This system achieved 69% aggregate coverage, with monthly coverage rates consistently above 85%, demonstrating robust performance and adaptability over time. Evaluation across recommendation sizes showed coverage reaching 69% for five video recommendations and 79% for ten video recommendations per video. In summary, this work presents a framework for understanding COVID-19 discourse on YouTube and a recommendation system that supports user engagement while promoting responsible and relevant content related to COVID-19.