Machine Learning-based USD/PKR Exchange Rate Forecasting Using Sentiment Analysis of Twitter Data
作者机构:Department of Computer Science&ITGlim Institute of Modern StudiesBahawalpur63100Pakistan Institute of Numerical SciencesKohat University of Science&TechnologyKohat26000Pakistan Department of Computer ScienceConcordia College BahawalpurBahawalpur63100Pakistan Institute of ComputingKohat University of Science and TechnologyKohat26000Pakistan Faculty of Applied StudiesKing Abdulaziz UniversityJeddah21577Saudi Arabia Department of StatisticsThe Islamia University of BahawalpurBahawalpur63100Pakistan Department of MathematicsUniversitéde CaenLMNOCampus IIScience 3Caen14032France
出 版 物:《Computers, Materials & Continua》 (计算机、材料和连续体(英文))
年 卷 期:2021年第67卷第6期
页 面:3451-3461页
核心收录:
学科分类:0808[工学-电气工程] 0809[工学-电子科学与技术(可授工学、理学学位)] 07[理学] 08[工学] 071102[理学-系统分析与集成] 0831[工学-生物医学工程(可授工学、理学、医学学位)] 0711[理学-系统科学] 0805[工学-材料科学与工程(可授工学、理学学位)] 081101[工学-控制理论与控制工程] 0701[理学-数学] 0811[工学-控制科学与工程] 0801[工学-力学(可授工学、理学学位)] 0812[工学-计算机科学与技术(可授工学、理学学位)] 081103[工学-系统工程]
基 金:Department of Information Technology Islamia University of Bahawalpur, IUB
主 题:Machine learning exchange rate sentiment analysis linear discriminant analysis principal component analysis simple logistic
摘 要:This study proposes an approach based on machine learning to forecast currency exchange rates by applying sentiment analysis to messages on Twitter(called tweets).A dataset of the exchange rates between the United States Dollar(USD)and the Pakistani Rupee(PKR)was formed by collecting information from a forex website as well as a collection of tweets from the business community in Pakistan containing finance-related *** dataset was collected in raw form,and was subjected to natural language processing by way of data *** variable labeling was then applied to the standardized dataset,where the response variables were divided into two classes:“1indicated an increase in the exchange rate and“−1indicated a decrease in *** better represent the dataset,we used linear discriminant analysis and principal component analysis to visualize the data in three-dimensional vector *** that were obtained using a sampling approach were then used for data *** machine learning classifiers—the simple logistic classifier,the random forest,bagging,naïve Bayes,and the support vector machine—were applied to the optimized *** results show that the simple logistic classifier yielded the highest accuracy of 82.14%for the USD and the PKR exchange rates forecasting.