E. Naresh, Babu J Ananda, K. Keerthi, M. R. Tejonidhi
{"title":"Predicting the Stock Price Using Natural Language Processing and Random Forest Regressor","authors":"E. Naresh, Babu J Ananda, K. Keerthi, M. R. Tejonidhi","doi":"10.1109/ICDSIS55133.2022.9915940","DOIUrl":null,"url":null,"abstract":"Together with data mining, artificial intelligence and machine learning techniques have been used to rectify a multitude of real-world problems. Such methods have found to be completely successful, resulting in full accuracy with reduced monetary expenditure and preserving massive amounts of time, too. Sentiment analysis is frequently implemented to customer voice components like evaluations and review reactions, web and digital media, and health system components for applications ranging from marketing to customer support to clinical research. Social media is a framework commonly used by individuals to share their opinions and demonstrate sentiments on various occasions. Stock market index forecasting is a tedious task; this is purely since stock data series starts behaving as a similar to arbitrary-walk. The businesses have to hire investment specialists who would take excessively high profits in order to advise on investment choices. Such investment professionals offer an easy approach, which can be used by anyone with an internet connection and a computer. The main objective is to build a reliable, inexpensive and sustainable framework for forecasting the stock market value by implementing sentiment classification to twitter data. The real time twitter data is pre-processed to remove unwanted data and tokenization is applied. The sentiment analysis is applied followed by Random Forest classifier and the graph plots are obtained. X-axis in the resultant graph represents time series and Y-axis represents the closing price.","PeriodicalId":178360,"journal":{"name":"2022 IEEE International Conference on Data Science and Information System (ICDSIS)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE International Conference on Data Science and Information System (ICDSIS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICDSIS55133.2022.9915940","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Together with data mining, artificial intelligence and machine learning techniques have been used to rectify a multitude of real-world problems. Such methods have found to be completely successful, resulting in full accuracy with reduced monetary expenditure and preserving massive amounts of time, too. Sentiment analysis is frequently implemented to customer voice components like evaluations and review reactions, web and digital media, and health system components for applications ranging from marketing to customer support to clinical research. Social media is a framework commonly used by individuals to share their opinions and demonstrate sentiments on various occasions. Stock market index forecasting is a tedious task; this is purely since stock data series starts behaving as a similar to arbitrary-walk. The businesses have to hire investment specialists who would take excessively high profits in order to advise on investment choices. Such investment professionals offer an easy approach, which can be used by anyone with an internet connection and a computer. The main objective is to build a reliable, inexpensive and sustainable framework for forecasting the stock market value by implementing sentiment classification to twitter data. The real time twitter data is pre-processed to remove unwanted data and tokenization is applied. The sentiment analysis is applied followed by Random Forest classifier and the graph plots are obtained. X-axis in the resultant graph represents time series and Y-axis represents the closing price.