MétaCan
Menu
Back to cohort
Record W4392681534 · doi:10.22318/icls2023.530792

Design and Evaluation of a Conversational Agent for Formative Assessment in Higher Education

2023· article· en· W4392681534 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueProceedings. · 2023
Typearticle
Languageen
FieldComputer Science
TopicIntelligent Tutoring Systems and Adaptive Learning
Canadian institutionsUniversity of AlbertaConcordia University of Edmonton
Fundersnot available
KeywordsFormative assessmentConversationSoftware walkthroughComputer sciencePsychologyMathematics education

Abstract

fetched live from OpenAlex

In recent years, there have been attempts to design and use conversational agents for educational assessments (i.e., conversation-based assessments: CBA).To address the limited research on CBA, we designed a CBA to serve as a formative assessment of higher-education students' knowledge and scaffold their learning by providing support and feedback.CBA was designed using Rasaan artificial intelligence-based tooland shared with students via Google Chat.The conversation data showed that CBA produced high standard accuracy measures and confidence scores.The findings suggest that ensuring the accuracy of CBA with constructed-response items is more challenging than CBA with selected-response items.In addition, a cognitive walkthrough of CBA provided preliminary evidence for the use of CBA as an interactive assessment tool.According to survey responses, most of the participating students reported positive attitudes toward CBA and its use to improve their assessment experience and learning.

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.

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)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.939
Threshold uncertainty score0.174

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
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 head0.145
GPT teacher head0.362
Teacher spread0.217 · 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