From Volunteers to Voters: Machine Learning Insights into Citizen Engagement

This study examines the link between volunteering and voting behavior.The main goal is to identify the key factors responsible for the impact on volunteers' decisions to vote and build a predictive model to assess the likelihood of individual volunteers participating in elections.Data collected from 650 volunteers at the Paris 2024 Olympic Games were analyzed using machine learning methods, with Gradient Boosted Trees achieving the highest accuracy.These findings provide insights for enhancing civic engagement and voter turnout.Their responses were used to train a model aimed at predicting whether the participants had voted in the most recent elections.Various Machine Learning (ML) algorithms based on Decision Trees (DT) and kNN were employed for classification and prediction tasks.A key feature of the proposed approach is the use of an ML pipeline developed with an open-source visual programming tool, streamlining the entire process.The methodology encompasses a pre-processing stage and a modeling stage involving five classifiers.Among the algorithms, the Gradient Boosted Trees method demonstrated the highest performance with an accuracy of 0.92.