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 | Size | Format | |
---|---|---|---|
CSCL2024_423-424.pdf | 245.62 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.