BIAS Word inventory for work and employment diversity, (in)equality and inclusivity (Version 2.0)
Bibliographic record
Abstract
The language used in job advertisements contains explicit and implicit cues, which signal employers’ preferences for candidates of certain ascribed characteristics, such as gender and ethnicity/race. To capture such biases in language use, existing word inventories have focused predominantly on gender and are based on general perceptions of the ‘masculine’ or ‘feminine’ orientations of specific words and socio-psychological understandings of ‘agentic’ and ‘communal’ traits. Nevertheless, these approaches are limited to gender and they do not consider the specific contexts in which the language is used. To address these limitations, we have developed the first comprehensive word inventory for work and employment diversity, (in)equality, and inclusivity that builds on a number of conceptual and methodological innovations. The BIAS Word Inventory was developed as part of our work in an international, interdisciplinary project – BIAS: Responsible AI for Labour Market Equality – in Canada and the United Kingdom (UK). Conceptually, we rely on a sociological approach that is attuned to various documented causes and correlates of inequalities related to gender, sexuality, ethnicity/race, immigration and family statuses in the labour market context. Methodologically, we rely on ‘expert’ coding of actual job advertisements in Canada and the UK, as well as iterative cycles of inter-rater verification. Our inventory is particularly suited for studying labour market inequalities, as it reflects the language used to describe job postings, and the inventory takes account of cues at various dimensions, including explicit and implicit cues associated with gender, ethnicity, citizenship and immigration statuses, role specifications, equality, equity and inclusivity policies and pledges, work-family policies, and workplace context.
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 | 0.007 | 0.024 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.004 | 0.004 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.001 | 0.003 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.011 | 0.004 |
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".