Twitter Data Feature Selection Using Enhanced Genetic Algorithm

Abstract

Feature selection is a basic critical task in sentiment analysis, especially while analyzing Twitter data for stock market sentiment. This paper proposes an enhanced genetic algorithm (GA) for feature selection utilizing Finance Yahoo stocks data and openly accessible Twitter data. The objective is to distinguish the most relevant features that can successfully anticipate stock market sentiment. The proposed GA integrates methods to enhance the investigation and double-dealing capacities, empowering it to look through a bigger feature space and work on the nature of chosen features. The algorithm starts by introducing a populace of random binary chromosomes, with every chromosome addressing a feature subset. Wellness assessment is performed utilizing sentiment analysis strategies to survey the prescient force of each feature subset. Trial assessment utilizing Finance Yahoo stocks and Twitter data shows that the enhanced GA beats customary GA and PSO strategies concerning exactness and forecast performance. The proposed approach gives important experiences to sentiment analysis and feature selection with regards to stock market sentiment utilizing Twitter data.