What is it about?

This study investigates public views of the Paris 2024 Olympics by analyzing tweets with the aim of elucidating public perceptions and identifying the factors that influence engagement, sentiment, and discourse related to this mega event. We analyze 30,300 public X (Twitter) posts about the Paris 2024 Olympics collected July 26 to August 14, using a Twitter-tuned RoBERTa model benchmarked against GPT-4 to classify sentiment. Most posts were neutral or positive (91.1%), with activity peaking around the Opening Ceremony and key medal days in August 7–9. Negative posts were fewer but drew the highest average likes and retweets. Sentiment patterns also varied by country and sport, and tweets about women’s sport skewed positive.

Featured Image

Why is it important?

The Olympics spark huge global conversations, and understanding that mood helps organizers, media, and sponsors make better decisions. We analyzed 30,300 posts about Paris 2024 and found that 91.1% were neutral or positive, indicating broadly favorable reactions, while a small share of negative posts drew the highest average likes and retweets, which can shape the public narrative more than their volume suggests. Engagement spiked around the opening ceremony and key medal moments, and reactions varied by country and sport. Tweets about women’s sport were mostly positive. These patterns offer practical signals for programming, crisis response, and inclusive storytelling.

Perspectives

Next, we plan to turn these insights into real-time dashboards for event teams, extend coverage to more languages and platforms, and improve handling of sarcasm. Comparing sports and countries over time can guide scheduling, messaging, and sponsor activations. We also benchmarked models and found a Twitter-specific RoBERTa model worked best for short, slang-heavy posts, which can help future studies pick the right tools.

Dr Mahdi Ghafouri Yazdi
University of Tehran

Read the Original

This page is a summary of: Sentiment analysis of the 2024 Paris Olympics using RoBERTa language model, International Journal of Event and Festival Management, September 2025, Emerald,
DOI: 10.1108/ijefm-01-2025-0007.
You can read the full text:

Read

Contributors

The following have contributed to this page