TY - JOUR

T1 - Running a double-blind true social experiment with a goal oriented adaptive AI-based conversational agent in educational research

AU - Cingillioglu, Ilker

AU - Gal , Uri

AU - Прохоров, Артем Борисович

PY - 2024

Y1 - 2024

N2 - This study introduces an innovative AI-facilitated interview-like survey system generating a combination of qualitative and quantitative data insights for higher education research. We employed a goal oriented adaptive AI-based Conversational Agent (AICA) which collected data directly from 1223 participants globally and ran a double-blind true social experiment online. During interviews, the AI established strong rapport with the participants, offering them personalized guidance while fostering comfort, ownership, and commitment to the study. In this entirely automated experiment, we empirically tested 8 hypotheses related to students' university selection. The results confirmed 5 of these hypotheses while refuting 3 factors previously identified in the literature. The study showcases the potential of AICAs to efficiently collect and analyse data from substantial sample sizes in real-time, fostering a streamlined and harmonious research process producing results that are not only statistically reliable and bias-free but also broadly generalizable.

AB - This study introduces an innovative AI-facilitated interview-like survey system generating a combination of qualitative and quantitative data insights for higher education research. We employed a goal oriented adaptive AI-based Conversational Agent (AICA) which collected data directly from 1223 participants globally and ran a double-blind true social experiment online. During interviews, the AI established strong rapport with the participants, offering them personalized guidance while fostering comfort, ownership, and commitment to the study. In this entirely automated experiment, we empirically tested 8 hypotheses related to students' university selection. The results confirmed 5 of these hypotheses while refuting 3 factors previously identified in the literature. The study showcases the potential of AICAs to efficiently collect and analyse data from substantial sample sizes in real-time, fostering a streamlined and harmonious research process producing results that are not only statistically reliable and bias-free but also broadly generalizable.

KW - AI-driven data collection

KW - AI-driven research

KW - Conversational agents in higher education research

KW - Experiments in higher education

KW - Social online experiments

UR - https://www.mendeley.com/catalogue/e35dadb2-cb3a-3160-a446-3c834767edb0/

U2 - 10.1016/j.ijer.2024.102323

DO - 10.1016/j.ijer.2024.102323

M3 - Article

VL - 124

JO - International Journal of Educational Research

JF - International Journal of Educational Research

SN - 0883-0355

M1 - 102323

ER -