Abstract

Understanding individual differences in students could help Intelligent Virtual Agents (IVAs) to provide tailored educational and emotional support. Towards creating a student model that the agent can reason over and adapt to accordingly, we conducted a study to identify possible relationships and rules based on the students’ personality, emotional state and character preferences. The purpose of our virtual advisors was to “Reduce Study Stress”. The experiment with 73 participants, consisting of one within-subjects factor (virtual advisors with empathic and neutral dialogue) and one between-subjects factor (different order of receiving empathic and neutral advisors), formed two experimental and one control groups. We measured preferences, perceived helpfulness and study stress level. Groups using the IVAs reported significantly lower levels of study stress at the end of the study. Some differences were found in preferences for and responses to IVA behaviour based on participants’ gender, personality and levels of depression, anxiety and stress.

Recommended Citation

Ranjbartabar, H., Richards, D., Kutay, C., & Mascarenhas, S. (2018). Towards an Adaptive System: Users’ Preferences and Responses to an Intelligent Virtual Advisor based on Individual Differences. In B. Andersson, B. Johansson, S. Carlsson, C. Barry, M. Lang, H. Linger, & C. Schneider (Eds.), Designing Digitalization (ISD2018 Proceedings). Lund, Sweden: Lund University. ISBN: 978-91-7753-876-9. http://aisel.aisnet.org/isd2014/proceedings2018/HCI/6.

Paper Type

Event

Share

COinS
 

Towards an Adaptive System: Users’ Preferences and Responses to an Intelligent Virtual Advisor based on Individual Differences

Understanding individual differences in students could help Intelligent Virtual Agents (IVAs) to provide tailored educational and emotional support. Towards creating a student model that the agent can reason over and adapt to accordingly, we conducted a study to identify possible relationships and rules based on the students’ personality, emotional state and character preferences. The purpose of our virtual advisors was to “Reduce Study Stress”. The experiment with 73 participants, consisting of one within-subjects factor (virtual advisors with empathic and neutral dialogue) and one between-subjects factor (different order of receiving empathic and neutral advisors), formed two experimental and one control groups. We measured preferences, perceived helpfulness and study stress level. Groups using the IVAs reported significantly lower levels of study stress at the end of the study. Some differences were found in preferences for and responses to IVA behaviour based on participants’ gender, personality and levels of depression, anxiety and stress.