stock market; analytical prediction

This study explores the relationship between social media sentiment and stock market movements using a dataset of tweets related to various publicly traded companies. The dataset comprises time-stamped tweets containing company-specific information, stock ticker symbols, and company names. By leveraging natural language processing (NLP) techniques, we analyze the sentiment of tweets to determine their impact on stock price fluctuations. This research aims to develop predictive models that incorporate tweet sentiment and frequency as features to forecast stock price movements.

Innostock focuses on stock price movement prediction tasks of newly formed technology companies listed on China's Sci-Tech Innovation Board, aggregating their financial news from various online platforms. It's stock prices were originally collected from CSMAR (https://cn.gtadata.com). To support multimodal input of each stock, we further collect the industrial sector relationships for each stock and build knowledge graphs.

The focus has been on investors’ hopes for the stock market for a considerable amount of time.Becauseoftheanticipatedhighreturns,thisisthepreferredinvestmentoption.However,dueto the significance of accurate forecasting, such investments are high-risk. In order to analyze stock market forecasts, investors utilize a technical analyst and AI technologies. Predictions and forecasts may be impacted by several obstacles, including analyst bias towards specific firms, investor pro-clivities, the impactof corporate news and economic circumstances, and the reliance on human skills.

For the purpose of experimentation, the historical stock prices of three petroleum companies: Pakistan State Oil (PSO), Hascol, and Attock Petroleum Limited (APL), are extracted from the Pakistan Stock Exchange (PSX) website through a web scrapper for the last four years. Different attributes related to the stocks of each of these companies are extracted for each day. Along with this, for each of these companies, Twitter data for sentiment analysis is also extracted using Twint.