MétaCan
Menu
Back to cohort
Record W4411166643 · doi:10.31542/qjkrkx86

Unmasking Chatbots' Multiple Personalities: A Student-Faculty Collaboration

2025· article· en· W4411166643 on OpenAlexafffund
Isabelle Sperano, Jacynthe Roberge, Danielle McDow-York, Ingrid Felfly

Bibliographic record

VenuePedagogical Inquiry and Practice · 2025
Typearticle
Languageen
FieldComputer Science
TopicAI in Service Interactions
Canadian institutionsUniversité LavalMacEwan University
FundersMacEwan UniversityImpact Fund
KeywordsPersonality psychologyPsychologyWorld Wide WebComputer sciencePsychoanalysisPersonality

Abstract

fetched live from OpenAlex

Humans have long anthropomorphized non-human entities, attributing human characteristics to objects like cars, sports equipment, and dolls. This tendency has intensified with connected devices and generative AI tools that simulate human interactions, producing sophisticated, human-like responses. If AI tools were personified based on their interaction and communication styles, what personalities might they embody? How could they be visually represented? What pedagogical opportunities could they reveal? These questions initiated the first phase of a practice-led project exploring AI personifications through a creative, collaborative pedagogical approach involving design students and faculty members. During an undergraduate design course, the faculty-student team used several generative AI tools for a project and reflected on their interactions by identifying various personalities the AI embodied. Each personality was named, described, and visually represented using generative AI illustration tools. The team identified six AI personalities: the assistant, the angel, the erudite, the slacker, the bullshitter, and the stalker. This project aims to contribute to emerging discussions about AI integration in education by offering a creative approach to support students and instructors who are navigating rapidly evolving technological interactions. By anthropomorphizing AI interactions, the team sought to enhance understanding of human-AI dynamics and potentially help develop AI literacy skills. The team also explores and reflects on a pedagogical approach that emphasizes student and faculty collaboration, creating a shared learning environment through a creative knowledge-building activity. This article presents the first phase of the project, offering early findings, exploring potential educational implications, and presenting future research directions.

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 distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.002
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.782
Threshold uncertainty score0.652

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.002
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0010.003
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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 head0.281
GPT teacher head0.502
Teacher spread0.221 · 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 teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designNot applicable
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

Citations0
Published2025
Admission routes2
Has abstractyes

Explore more

Same venuePedagogical Inquiry and PracticeSame topicAI in Service InteractionsFrench-language works237,207