Innovating Assessment with Conversational Agents: A Technology-Enhanced Approach to Formative Assessments
Bibliographic record
Abstract
Conversational agents (e.g., ChatGPT) have become popular tools for simulating formal and casual human-like dialogues. Researchers have designed conversational agents to improve instruction quality and support student learning and investigated their effects on learning outcomes. In addition to their instructional use, conversational agents can also be incorporated into assessments to measure student learning. Students can answer items within a digital conversational environment by typing their answers while receiving feedback for correct responses and follow-up questions for incorrect responses. This study introduced a conversation-based assessment (CBA) with three selected-response and two constructed-response tests and evaluated its performance based on intent classification and confidence score. CBA was designed using Rasa and deployed to Google Chat to share with students in an undergraduate-level course. The results showed that CBA with both selected-response and constructed-response tests produced high performance and confidence scores for student responses. In particular, CBA with the selected-response format showed perfect accuracy between system design and implementation. In comparison, CBA with constructed-response items consistently matched student responses to the appropriate conversation paths for the most part. Overall, this study shows the potential of CBA as a technology-enhanced assessment tool.
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 imitationNot 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.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.011 | 0.038 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.004 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".