Efficacy of News Sentiment for Stock Market Prediction

Abstract

Stock Market trend prediction will always remain a challenging task due to stochastic nature. The enormous amount of data generated by the news, blogs, reviews, financial reports and social media are considered a treasure of knowledge for researchers and investors. The present work focuses to observe fluctuations in stock prices with respect to the relevant news articles of a company. In this paper, a daily prediction model is proposed using historical data and news articles to predict the Indian stock market movements. Classifier Naïve Bayes is used to categorize the news text having negative or positive sentiment. The count of the positive and negative sentiment of news articles for each day and variance of adjacent days close price along with historical data is used for prediction purpose and an accuracy ranging from 65.30 to 91.2 % achieved with various machine learning techniques.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 50 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.