MétaCan
Menu
Back to cohort
Record W4391759979 · doi:10.1016/j.ijer.2024.102323

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

2024· article· en· W4391759979 on OpenAlexaff
Ilker Cingillioglu, Uri Gal, Artem Prokhorov

Bibliographic record

VenueInternational Journal of Educational Research · 2024
Typearticle
Languageen
FieldComputer Science
TopicOnline Learning and Analytics
Canadian institutionsUniversité de Montréal
Fundersnot available
KeywordsPsychologyMathematics educationCognitive psychologyComputer scienceApplied psychology

Abstract

fetched live from OpenAlex

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.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.026
metaresearch head score (Gemma)0.053
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Randomized trial · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.026
Threshold uncertainty score0.137

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0260.053
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.000
Science and technology studies0.0020.003
Scholarly communication0.0020.002
Open science0.0020.003
Research integrity0.0020.002
Insufficient payload (model declined to judge)0.0040.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.179
GPT teacher head0.505
Teacher spread0.326 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designRandomized trial
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations4
Published2024
Admission routes1
Has abstractyes

Explore more

Same venueInternational Journal of Educational ResearchSame topicOnline Learning and AnalyticsFrench-language works237,207