Modified Genetic Algorithm for Feature Selection and Hyper Parameter Optimization: Case of XGBoost in Spam Prediction
This addresses spam detection in social networks, offering a more efficient model for researchers and businesses, though it is incremental as it builds on existing genetic algorithm and XGBoost methods.
The paper tackles spam prediction on Twitter by proposing a modified genetic algorithm for simultaneous feature selection and hyperparameter optimization with XGBoost, achieving an average accuracy of 92.67% and geometric mean of 82.32% using less than 10% of features.
Recently, spam on online social networks has attracted attention in the research and business world. Twitter has become the preferred medium to spread spam content. Many research efforts attempted to encounter social networks spam. Twitter brought extra challenges represented by the feature space size, and imbalanced data distributions. Usually, the related research works focus on part of these main challenges or produce black-box models. In this paper, we propose a modified genetic algorithm for simultaneous dimensionality reduction and hyper parameter optimization over imbalanced datasets. The algorithm initialized an eXtreme Gradient Boosting classifier and reduced the features space of tweets dataset; to generate a spam prediction model. The model is validated using a 50 times repeated 10-fold stratified cross-validation, and analyzed using nonparametric statistical tests. The resulted prediction model attains on average 82.32\% and 92.67\% in terms of geometric mean and accuracy respectively, utilizing less than 10\% of the total feature space. The empirical results show that the modified genetic algorithm outperforms $Chi^2$ and $PCA$ feature selection methods. In addition, eXtreme Gradient Boosting outperforms many machine learning algorithms, including BERT-based deep learning model, in spam prediction. Furthermore, the proposed approach is applied to SMS spam modeling and compared to related works.