Abstract

Sentiment analysis of social media data involves extracting valuable insights from vast amounts of unstructured text. Feature selection plays a crucial role in enhancing the accuracy and efficiency of sentiment analysis algorithms. This study proposes the application of the Ant Colony Optimization (ACO) algorithm for feature selection in sentiment analysis. ACO is inspired by the foraging behavior of ants and has been successfully applied to various optimization problems. In this context, ACO is utilized to select the most informative features from the dataset, thereby improving the performance of sentiment analysis models. The contribution of this research lies in the adaptation of ACO for feature selection in sentiment analysis of social media data. By leveraging the inherent strengths of ACO, such as its ability to explore large solution spaces and adapt to dynamic environments, more accurate sentiment analysis models can be developed. Experimental results demonstrate that the proposed ACO-based feature selection approach outperforms traditional methods in terms of classification accuracy and computational efficiency. The selected features exhibit strong predictive power, leading to improved sentiment analysis performance on social media data.