Machine Learning for Detecting Bias in Productivity Perception
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.
Bibliographic record
Abstract
In the digital age, people's self-perception of productivity tends to diverge from reality, with some overestimating and others underestimating their output. This study analyzed 30,000 behavioral and demographic records to predict such perception gaps. By establishing a threshold based on half a standard deviation in the perception gap, three categories were identified: Overestimators, Underestimators, and Accurate assessors. Class imbalances were addressed through Synthetic Minority Over-sampling Technique (SMOTE), and four classifiers-Logistic Regression, Random Forest, Light Gradient Boosting Machine (LightGBM), and XGBoost-were evaluated using macro and weighted Fl-scores. Logistic Regression achieved the best performance with a macro Fl-score of 0.35 and a weighted Fl-score of 0.50, outperforming more complex models while remaining interpretable. Feature importance identified job type and digital preferences for social media as the strongest predictors, with workers in the fields of finance, health, and IT, as well as frequent users of Instagram or TikTok, demonstrating overestimation rates, in particular. These findings highlight that internal behavioral characteristics, rather than external cues alone, drive productivity misperception and also propose interventions based on contexts of occupation and digital usage habits that could enhance productivity awareness as well as digital well-being.
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 imitationNot 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.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it