#ContextMatters: Advantages and Limitations of Using Machine Learning to\n Support Women in Politics
Bibliographic record
Abstract
The United Nations identified gender equality as a Sustainable Development\nGoal in 2015, recognizing the underrepresentation of women in politics as a\nspecific barrier to achieving gender equality. Political systems around the\nworld experience gender inequality across all levels of elected government as\nfewer women run for office than men. This is due in part to online abuse,\nparticularly on social media platforms like Twitter, where women seeking or in\npower tend to be targeted with more toxic maltreatment than their male\ncounterparts. In this paper, we present reflections on ParityBOT - the first\nnatural language processing-based intervention designed to affect online\ndiscourse for women in politics for the better, at scale. Deployed across\nelections in Canada, the United States and New Zealand, ParityBOT was used to\nanalyse and classify more than 12 million tweets directed at women candidates\nand counter toxic tweets with supportive ones. From these elections we present\nthree case studies highlighting the current limitations of, and future research\nand application opportunities for, using a natural language processing-based\nsystem to detect online toxicity, specifically with regards to contextually\nimportant microaggressions. We examine the rate of false negatives, where\nParityBOT failed to pick up on insults directed at specific high profile women,\nwhich would be obvious to human users. We examine the unaddressed harms of\nmicroaggressions and the potential of yet unseen damage they cause for women in\nthese communities, and for progress towards gender equality overall, in light\nof these technological blindspots. This work concludes with a discussion on the\nbenefits of partnerships between nonprofit social groups and technology experts\nto develop responsible, socially impactful approaches to addressing online\nhate.\n
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.001 |
| 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".