Fitting Machine Learning Models for the Identification of Social Vulnerability in the Event of Political Instability in Nigeria
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Due to the high rate of poverty and the unequal distribution, social vulnerability is extremely common in rising economies around the world, including Nigeria. As a result of political instability in Nigeria, this research study's machine learning has been suitably fitted to identify potential social vulnerability. The outcomes of the machine learning optimizations indicate that a high incidence of social inequality, political unrest, natural disasters and agricultural instability will probably all contribute to the high degree of social vulnerability in Nigeria. The results of the predictor variables' contribution to the likelihood of high social vulnerability in Nigerian communities indicate that, at 100% and 74.8%, natural disasters related to flooding and political grievances respectively account for the majority of Nigeria's high level of vulnerability. Surpassing the logistic regression method, support vector machine, and random forest, the artificial neural network (ANN) attained the maximum prediction accuracy of 85% with a precision of 82%, according to the model performance evaluation. Therefore the best model for forecasting high social vulnerability in Nigerian currently, is the ANN. In order to reduce the high level of social vulnerability, the Nigerian government should establish an all-inclusive government that will resolve political grievances among citizens and also establish an efficient security network that will combat the country's current high level of insecurity. In the event that political instability, the government should then embrace the use of machine learning models for the future prediction of social vulnerability.
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.
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 | 0.004 | 0.001 |
| 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 | 0.000 |
| 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 it