Comparison of Salp Swarm Algorithm and Particle Swarm Optimization as Feature Selection Techniques for Recession Sentiment Analysis in Indonesia

Amidst global economic uncertainty, this study focuses on Twitter sentiment during the global recession issue on social media, especially in Indonesia. By utilizing sentiment analysis, this study uses machine learning algorithms such as Naïve Bayes (NB), Support Vector Machine (SVM), K-Nearest Neighbor (KNN) which are still less than optimal on high-dimensional Twitter data. The purpose of this study is to improve the accuracy of conventional machine learning using basic metaheuristic algorithms, namely the Salp Swarm Algorithm (SSA) and Particle Swarm Optimization (PSO) as feature selection. From January to May 2023, this study captures the evolving sentiment in response to economic conditions. Data preprocessing, including labeling through the TextBlob and VADER libraries, sets the stage for the analysis. Performance is compared based on labeling techniques, feature selection, and classification algorithms. Specifically, when applied to VADER labeled data without feature selection, the SVM model achieves an outstanding accuracy of 83% and an F1 score of 67%—notably, the application of SSA and PSO results in a reduction in model accuracy by 1%. However, the application of SSA and PSO slightly reduced the model accuracy performance by 1%. On the TextBlob labeled data, SVM showed an outstanding performance (80% accuracy, 77% F1 score). Interestingly, PSO on TextBlob data with SVM significantly decreased the model's performance. These findings contribute significantly to understanding the intricacies of sentiment dynamics during economic uncertainty on social media platforms, with SVM emerging as a strong choice for practical sentiment analysis.