Everyone's Voice Matters: Quantifying Annotation Disagreement Using Demographic Information
Bibliographic record
Abstract
In NLP annotation, it is common to have multiple annotators label the text and then obtain the ground truth labels based on major annotators’ agreement. However, annotators are individuals with different backgrounds and various voices. When annotation tasks become subjective, such as detecting politeness, offense, and social norms, annotators’ voices differ and vary. Their diverse voices may represent the true distribution of people’s opinions on subjective matters. Therefore, it is crucial to study the disagreement from annotation to understand which content is controversial from the annotators. In our research, we extract disagreement labels from five subjective datasets, then fine-tune language models to predict annotators’ disagreement. Our results show that knowing annotators’ demographic information (e.g., gender, ethnicity, education level), in addition to the task text, helps predict the disagreement. To investigate the effect of annotators’ demographics on their disagreement level, we simulate different combinations of their artificial demographics and explore the variance of the prediction to distinguish the disagreement from the inherent controversy from text content and the disagreement in the annotators’ perspective. Overall, we propose an innovative disagreement prediction mechanism for better design of the annotation process that will achieve more accurate and inclusive results for NLP systems. Our code and dataset are publicly available.
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 | 0.002 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.004 | 0.006 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.003 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.009 |
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".