Please use this identifier to cite or link to this item: https://repository.isls.org//handle/1/10586
Title: Use of AI to Foster Greater Awareness and Reflexivity Around Harmful Content in Online Discussion Tools
Authors: MacKinnon, Kim
Liu, Jingyu
Fong, Cresencia
Pandey, Jai
Keywords: CSCL
Issue Date: 2024
Publisher: International Society of the Learning Sciences
Citation: MacKinnon, K., Liu, J., Fong, C., & Pandey, J. (2024). Use of AI to Foster Greater Awareness and Reflexivity Around Harmful Content in Online Discussion Tools. In Clarke-Midura, J., Kollar, I., Gu, X., & D'Angelo, C. (Eds.), Proceedings of the 17th International Conference on Computer-Supported Collaborative Learning - CSCL 2024 (pp. 423-424). International Society of the Learning Sciences.
Abstract: In this project, we explore the development of an AI-powered harmful content detector for an online discussion tool. We explored three possible large language processors (Moderation API, roBERTa, and ChatGPT) using a dataset of 5,747 publicly-accessible online posts. Results indicated that the pre-trained, fine-tuned roBERTa processor was the most accurate at detecting harmful content and distinguishing it from non-harmful content.
Description: Poster
URI: https://doi.org/10.22318/cscl2024.584821
https://repository.isls.org//handle/1/10586
Appears in Collections:ISLS Annual Meeting 2024

Files in This Item:
File SizeFormat 
CSCL2024_423-424.pdf245.62 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.