2025
doi: 10.12720/jait.16.1.12-20
Initial Coin Offerings Success Prediction Using Social Media and Large Language Models
Khouloud Safi Eljil1,2,*
,
Essia Hamouda3 ,
Farid Nait-Abdesselam1
- 1Computer Science Department, Université Paris Cité, France
- 2Higher School of Communications, University of Carthage, SUP’COM, Tunisia
- 3Department of Information and Decision Sciences, California State University San Bernardino, USA
- Manuscript receivedJune 21, 2024
- revisedJuly 10, 2024
- acceptedAugust 13, 2024
- publishedJanuary 9, 2025
Abstract
Initial Coin Offering (ICO) is a fundraising method utilized by blockchain startups to raise capital by issuing and selling digital tokens to investors. ICOs have become widely popular for cryptocurrency fundraising, often generating millions of dollars, and surpassing traditional crowdfunding methods like Initial Public Offerings. However, ICO is a risky way of investing and raising capital due to the lack of regulations and standardisation. In this research, we delve into the impact of social media and sentiment analysis on the success of ICOs, employing various machine learning models and Large Language Models. Our analysis is based on data from over 1,000 ICOs gathered from diverse ICO information platforms, coupled with a corpus of 910,478 tweets associated with these ICOs. We extend our investigation to include other social media platforms such as BitcoinTalk, Telegram, Facebook, and Medium. Our analysis revealed that valuable insights regarding the success of ICOs can be derived by examining text sentiment and investigating metadata across these diverse social media channels.
Keywords
- token sales
- web scraping
- sentiment analysis
- social media
- Bidirectional Encoder Representations from Transformers (BERT)
How to Cite
Khouloud Safi Eljil, Essia Hamouda, and Farid Nait-Abdesselam, "Initial Coin Offerings Success Prediction Using Social Media and Large Language Models," Journal of Advances in Information Technology, vol. 16, no. 1, pp. 12-20, 2025. https://doi.org/10.12720/jait.16.1.12-20
Copyright & License
Copyright © 2025 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
