THE ROLE OF GENERATIVE AI-POWERED PERSONAS IN DEVELOPING GRADUATE INTERVIEWING SKILLS
Bibliographic record
Abstract
This article presents an in-depth examination of the artificial intelligence (AI)-powered persona-generating program PEARL-Persona Emulating Adaptive Research and Learning Bot, which utilizes GPT-4 application programming interface (API), for developing graduate students' research-interview skills. PEARL offers a novel solution to the challenges faced in qualitative research, such as ethical concerns, participant accessibility, and data diversity, by simulating realistic personas for interview training. This study, framed by experiential learning theory (ELT), explores graduate students' experiences with PEARL in a graduate course, focusing on how it enhances the four facets of ELT: concrete experience, reflective observation, abstract conceptualization, and active experimentation. The findings reveal that while students perceive PEARL as a beneficial tool for experiential learning and skill development, it also has limitations in replicating the complexity of human interactions. The study contributes valuable insights into the integration of generative AI in enhancing graduate research competencies and underscores the enduring need for human involvement in the research process. It highlights the potential of generative AI tools like PEARL to bridge the gap between theoretical knowledge and practical skills in graduate education, while also drawing attention to areas for future refinement and ethical considerations in generative AI-enabled pedagogy.
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 | 0.091 | 0.160 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.004 | 0.009 |
| Scholarly communication | 0.006 | 0.006 |
| Open science | 0.003 | 0.012 |
| Research integrity | 0.002 | 0.004 |
| Insufficient payload (model declined to judge) | 0.004 | 0.002 |
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".