Empowering Investors: Insights from Sentiment Analysis, FFT, and Regression in Indian Stock Markets

Sentiment Analysis has become a tool, for analyzing text data and extracting insights. In our research, we use sentiment examination techniques to calculate stock market trends in the market. We collected a dataset of news articles from two years focusing on financial news related to Indian stocks obtained through the Google News API. Using the NLTK VADER algorithm we calculate polarity scores for the news headlines to measure the sentiment associated with each article. To further improve our analysis, we introduce an approach by smearing Fast Fourier Transform and Inverse Fast Fourier Transform to analyze patterns or frequencies in the sentiment scores. This technique aims to provide features for enhancing stock market analysis. At the time we gather stock data using the Python y finance library. This includes indicators, like price changes, trading volumes, and other financial measurements. This data is essential for our regression models. We use these models to examine how the features derived from sentiment analysis and FFT components are related and how they correlate with stock price movements. By combining sentiment analysis with regression modeling the main goal of this research project is to provide insights into how news sentiment, FFT components, and stock market trends interact in the market. The results of this research endeavour could potentially equip investors with the knowledge they need to make decisions and develop strategies that contribute to participation, in the stock market.