Improving sentiment analysis of financial news headlines using hybrid Word2Vec-TFIDF feature extraction technique
Meera George, R. Murugesan
Abstract
With the evolution of big data and information technology, sentiment analysis has become a research hotspot in the financial market. Researchers are increasingly focused on improving the efficiency of sentiment analysis using different machine learning and deep learning architectures. Feature extraction is a fundamental process in sentiment analysis that enhances text representation and classification. Though various feature extraction techniques are present in the field, limited attention has been given to hybrid feature extraction techniques. The primary objective of this study is to improve the sentiment analysis of financial news headlines using a hybrid Word2Vec-TFIDF feature extraction technique. The study evaluates the performance of Word2Vec, Doc2Vec, TFIDF, Word2Vec-TFIDF, and Doc2Vec-TFIDF with six machine learning classifiers. The results find that the hybrid feature extraction technique, Word2vec-TFIDF with SVM classifier, outperforms all other sentiment analysis models with an accuracy of 82 percent.