Logo Lanfrica

kingsleyosunkwo/Outlier-Detection-in-Election-Data-Using-Geospatial-Analysis

Domain:

peace and securitygeospatial

Record type:

project
Creator:
kin
Host:
This project ensures election integrity in Imo State, Nigeria, by detecting potential voting irregularities. By identifying outlier polling units where results deviate significantly from neighbouring units, we aim to highlight possible influences or rigging, supporting transparency and accuracy in election results. # Outlier-Detection-in-Election-Data-Using-Geospatial-Analysis-HNG-Internship- This project ensures election integrity in Imo State, Nigeria, by detecting potential voting irregularities. By identifying outlier polling units where results deviate significantly from neighbouring units, we aim to highlight possible influences or rigging, supporting transparency and accuracy in election results. ## TABLE OF CONTENT - INTRODUCTION - METHODOLOGY - NEIGHBOUR IDENTIFICATION - OUTLIER SCORE CALCULATION - EXPORTING THE DATA - SORTING AND REPORTING - FINDINGS - CONCLUSION # INTRODUCTION In this report, I aim to uncover potential voting irregularities in the recently concluded election in Imo State, Nigeria. The Independent National Electoral Commission (INEC) has faced multiple legal challenges concerning the integrity and accuracy of the election results. Allegations of vote manipulation and irregularities have prompted a thorough investigation into the matter. Our analysis will focus on identifying outlier polling units based on the votes each party received, using geospatial techniques to find neighboring polling units and calculate an outlier score for each party. # METHODOLOGY Dataset Preparation Data Source: The dataset was obtained from the provided link, focusing on Imo State. Geocoding: Longitude and latitude values were added to each polling unit using geocoding techniques. Cleaning: The dataset was cleaned to remove any inconsistencies and ensure accuracy. ``` install.packages("tidyverse") library(dplyr) # Display the first few rows to ensure it is loaded correctly head(geocoded_data) State LGA Ward PU_Code PU_Name Accredited_Voters Registered_Voters Results_Found 1 IMO ABOH MBA... ENYI... 16-01-... ALADIN... 175 905 TRUE 2 IMO ABOH MBA... ENYI... 16-01-... OKWUAK... 243 852 TRUE 3 IMO ABOH MBA... ENYI... 16-01-... UMUNKW... 183 704 TRUE 4 IMO ABOH MBA... ENYI …