Sentiment Analysis of Financial News Data using TF-IDF and Machine Learning Algorithms

Abstract

Blogs, online forums, comment sections, and social networking sites like Facebook, Twitter (now known as X), and Instagram can all be called social media. The growing use of social media has made some unstructured data available, which can benefit us if we clean, structure, and analyze the data. Twitter is a popular microblogging social media platform where people share and express their opinions about any topic. The act of analyzing these opinions of people is called sentimental analysis. Sentimental analysis can be helpful to individuals, businesses, government agencies, etc. In this study, tweets related to financial news were extracted, labeled, and analyzed to capture the opinions of people around the world. This paper proposes a novel machine learning-based approach to analyze social media data for sentiment analysis. The presented approach is divided into three steps. The first stage is preprocessing, where the tweets are refined and filtered. In the second stage, feature extraction was performed using Term Frequency and Inverse Document Frequency (TF-IDF). The third stage involves using the extracted features to make predictions using machine learning algorithms. Three machine learning models were used, namely, random forest classifier (RF), Naïve Bayes (NB), and k-nearest neighbor (KNN). The evaluation results show that both NB and RF perform better than KNN in accuracy, precision, Recall, and F1-score metrics. These results also show an overwhelmingly positive opinion regarding financial news.