Sign In
Personal Schedule
Change Preferences
Search
Browse By Day
Browse By Time
Browse By Person
Browse By Group
Browse By Session Type
Browse By Research Area
Search Tips
AECT 2022 Convention Page
X (Twitter)
Recent educational studies have examined the affordances of conversational agents (CA) powered by artificial intelligence to automatically support students’ participation in discussion forums. However, few studies have paid attention to the safety of CAs. This study aimed to investigate and address the safety challenges of CAs constructed with educational big data (2,097,139 post-reply pairs by 71,918 students) to support learning. Our proposed model can effectively enhance the safety of generated texts while providing comparable support.
Presenter: Chenglu Li, University of Florida
Presenter: Wanli Xing, University of Florida
Contributor: Walter Leite, University of Florida