Prediction on Domestic Violence in Bangladesh during the COVID-19 Outbreak Using Machine Learning Methods
Problem
Family violence in Bangladesh during the COVID-19 lockdown needed to be forecast to anticipate social harm.
Why it matters
Domestic violence prediction could inform protection of vulnerable people during crises.
What the AI did
Random Forest, Logistic Regression and Naive Bayes classifiers were applied to predict family violence, with SMOTE used to address class imbalance and feature importance extracted.
Results
not stated in source
Impact
The evidence supports that ML classifiers were applied and evaluated on accuracy, precision, recall and F-score, without reported values.
Record
| Venue | Applied System Innovation |
|---|---|
| Published | 2021 |
| Work type | article |
| Authors | Md. Murad Hossain, Md. Asadullah, Abidur Rahaman, Md Sipon Miah, Md. Zahid Hasan, Tonmay Paul, Mohammad Amzad Hossain |
| Citations | 41 (OpenAlex, at import time) |
| References | 26 |
| Model or method | Random Forest, Logistic Regression, Naive Bayes |
| Organization | not stated in source |
| Primary source | https://doi.org/10.3390/asi4040077 |
| Open access | gold |
| Keywords | domestic violence, COVID-19, machine learning, SMOTE, Bangladesh, classification |
Importance rating
real but narrower advance
Family violence during COVID-19 lockdown is a real social harm affecting vulnerable people, but the abstract frames a single-country forecast with no stated scale of affected population or deployment.
More in Research & Humanities
| # | Paper | Year | Citations | Importance |
|---|---|---|---|---|
| 1 | Machine Learning as a Tool for Hypothesis Generation | 2024 | 85 |
6
|
| 2 | A Hybrid Semi-Automated Workflow for Systematic and Literature Review Processes with Large Language Model Analysis | 2024 | 28 |
6
|
| 3 | Restoring and attributing ancient texts using deep neural networks | 2022 | 206 |
5
|
| 4 | Can Large Language Models Transform Computational Social Science? | 2023 | 559 |
4
|
| 5 | AI-accelerated Nazca survey nearly doubles the number of known figurative geoglyphs | 2024 | 18 |
4
|