Please use this identifier to cite or link to this item: https://repository.isls.org/handle/1/10229
Full metadata record
DC FieldValueLanguage
dc.contributor.authorRusso, Renato
dc.contributor.authorBlikstein, Paulo
dc.date.accessioned2023-10-10T16:08:07Z-
dc.date.available2023-10-10T11:57:01Z
dc.date.available2023-10-10T16:08:07Z-
dc.date.issued2023
dc.identifier.citationRusso, R. & Blikstein, P. (2023). Aide: A conversational agent based on inoculation theory and large language models to empower learners to recognize disinformation. In Blikstein, P., Van Aalst, J., Kizito, R., & Brennan, K. (Eds.), Proceedings of the 17th International Conference of the Learning Sciences - ICLS 2023 (pp. 2209-2212). International Society of the Learning Sciences.en
dc.identifier.urihttps://doi.org/10.22318/icls2023.715792
dc.identifier.urihttps://repository.isls.org//handle/1/10229-
dc.descriptionTechnology Innovation Paperen
dc.description.abstractDisinformation has been fueled in recent years, and inoculation theory offers an approach to supply the tools that will enable citizens to identify disinformation. It proposes that interventions can act like “vaccines” by exposing individuals to controlled doses of false or misleading information. This project draws on that theory to design a conversational agent that uses language modeling to surface strategies commonly used in disinformation. This paper lays out the motivation for the work, points to referential literature and related work, presents core design elements, and delineates future design directions based on testing data.en
dc.publisherInternational Society of the Learning Sciences
dc.relation.ispartofurn:ISBN:978-1-7373306-7-7
dc.relation.ispartofProceedings of the 17th International Conference of the Learning Sciences - ICLS 2023, pp. 2209-2212
dc.subjectLearning Sciencesen
dc.titleAide: A Conversational Agent Based on Inoculation Theory and Large Language Models to Empower Learners to Recognize Disinformationen
dc.typeconferencePaper
dc.identifier.doi10.22318/icls2023.715792
Appears in Collections:ISLS Annual Meeting 2023

Files in This Item:
File SizeFormat 
ICLS2023_2209-2212.pdf195.35 kBAdobe PDFView/Open


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