Generative artificial intelligence and machine learning methods to screen social media content
ChatGPT has mixed capacity to screen social media content that has been converted into text data using machine learning techniques such as object detection. ChatGPT's sensitivity was found to be lower than a human coder in the current case example but has demonstrated power for screening out irrelevant content and can be used as an initial pass at screening content. Future studies should explore ways to enhance ChatGPT's sensitivity.
Authors
- Rachel R. Ouellette (ORCID: https://orcid.org/0000-0001-6982-0830)
- Elise E. DeVito (ORCID: https://orcid.org/0000-0002-9816-3494)
- Dhiraj Murthy (ORCID: https://orcid.org/0000-0001-9734-1124)
- Neil S. Kamdar (ORCID: https://orcid.org/0000-0002-1898-1594)
- Grace Kong (ORCID: https://orcid.org/0000-0002-9269-3435)
- Ranjan K. Singh (ORCID: https://orcid.org/0000-0002-1380-7829)
- Kellen Sharp (ORCID: https://orcid.org/0009-0005-5519-9787)
- Amanda de la Noval
Institutions
- Yale University (US)
- The University of Texas at Austin (US)
Publication Details
- Journal
- PeerJ Computer Science
- Published
- 2025-03-14
- DOI
- https://doi.org/10.7717/peerj-cs.2710
- Citations
- 6
- Primary Topic
- Topic Modeling
- Type
- article
- Field-Weighted Citation Impact
- 14.89