Detecting Explicit and Implicit Gender Bias in Software Engineering Education
Bibliographic record
Abstract
Gender bias in software engineering education appears in both explicit and implicit forms, including Stereotyping Bias, Generic Pronouns, Sexism, Semantic Bias, and Exclusionary Terms. These biases-embedded in textbooks, slides, assignments, and examples-can discourage participation from underrepresented groups in the field. In this work, we propose an automated approach for detecting both explicit and implicit gender bias in software engineering educational content. We first constructed a diverse, multi-source dataset by combining samples from SEBiasText, Gender Bias in Text: Labeled Datasets and Lexicons, GenderAlign, CrowS-Pairs, and StereoSet. To generate highquality training labels, we applied a hybrid labeling approach that combines rule-based techniques with predictions from a fine-tuned BERT model. Once labeled, we trained a separate BERT-based multi-label classifier to detect multiple bias types within a sentence. To evaluate its real-world applicability, we tested the model exclusively on software engineering materials drawn from widely adopted textbooks. The model achieved an F1-score of 91.22 % and an accuracy of 87.51 %, demonstrating strong performance in detecting both obvious and less noticeable forms of gender bias. These results highlight the effectiveness, scalability, and practical value of our approach in supporting educators, curriculum designers, and researchers in creating more inclusive educational content in software engineering.
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 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 | 0.001 | 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 | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".