Optimizing Stochastic Gradient Descent in Text Classification Based on Fine-Tuning Hyper-Parameters Approach. A Case Study on Automatic Classification of Global Terrorist Attacks
This work addresses performance optimization in text classification for applications like terrorism analysis, but it is incremental as it builds on existing SGD and grid-search methods.
The research tackled improving Stochastic Gradient Descent (SGD) for text classification by fine-tuning hyper-parameters using a grid-search approach, applied to classifying global terrorist attacks, resulting in optimized accuracy and execution time for classifiers like SVM, Logistic Regression, and Perceptron.
The objective of this research is to enhance performance of Stochastic Gradient Descent (SGD) algorithm in text classification. In our research, we proposed using SGD learning with Grid-Search approach to fine-tuning hyper-parameters in order to enhance the performance of SGD classification. We explored different settings for representation, transformation and weighting features from the summary description of terrorist attacks incidents obtained from the Global Terrorism Database as a pre-classification step, and validated SGD learning on Support Vector Machine (SVM), Logistic Regression and Perceptron classifiers by stratified 10-K-fold cross-validation to compare the performance of different classifiers embedded in SGD algorithm. The research concludes that using a grid-search to find the hyper-parameters optimize SGD classification, not in the pre-classification settings only, but also in the performance of the classifiers in terms of accuracy and execution time.