Intrinsic and Contextual Factors Impacting Student Ratings of Automatically Generated Questions: A Large-Scale Data Analysis
Bibliographic record
Abstract
Combining formative practice with the primary expository content in a learning by doing method is a proven approach to increase student learning. Artificial intelligence has led the way for automatic question generation (AQG) systems that can generate volumes of formative practice otherwise prohibitive to create with human effort. One such AQG system was developed that used textbooks as the corpus of generation for the sole purpose of generating formative practice to place alongside the textbook content for students to use as a study tool. In this work, we analyzed a data set comprising over 5.2 million student-question interaction sessions. More than 800,000 unique questions were answered across more than 9,000 textbooks, with over 400,000 students using them. As part of the user experience, students could rate questions after answering with a social media-style thumbs up or thumbs down. In this investigation, this student feedback data was used to gain new insights into the automatically generated questions: are there features of questions that influence student ratings? An explanatory model was developed to analyze ten key features that may influence student ratings. Results and implications for improving automatic question generation are discussed. The code and data for this paper are available at https://github.com/vitalsource/data.
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 | 0.010 | 0.069 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".