A Novel Women Safety Analyis and Monitoring Sysetm over Social Media using Machine Learning
Bibliographic record
Abstract
In the current scenario, women community facing issues like gender discrimination, schooling, child marriage, sexual assault and harassment, and much more, not just from society but also from social media. Women are protected by organizations like the She Team, Disha Act, and many others in society, but these organizations are much less in social media. Social networking sites like Twitter, Instagram, Facebook, etc. cause problems for women. This paper focuses on the safety analysis and monitoring of women using various social media platforms in Indian cities. The posts on Facebook and Instagram, as well as tweets on Twitter, that abuse women are considered and show the percentage of threats that women face from social media, which aids in understanding by the youth of India who misuse the women’s safety and harass them in social medias via tweets, posts, and text should face strict action. People may grasp the threats to women with the help of this, and it demonstrates that women face challenges not only from society but also from social media platforms. The outcome is easily comprehended in the form of a graph and a pie chart. Algorithms such as Nave Bayes (NB) and XGBoost are used in the analysis of women’s safety on various social media sites. The goal is to use classification techniques to categorize or forecast the Type based on dataset properties. Using categorization algorithms, we can determine whether social media content is positive, negative, or neutral. It has been substantiated that Naive Bayes algorithm has proved better accuracy compared to random forest and decision tree algorithms.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".