Identification of Donald Trump's Tweets Using Machine Learning

被引:0
|
作者
Ahmad, Lina [1 ]
Al-Mousa, Amjed [1 ]
机构
[1] Princess Sumaya Univ Technol, Comp Engn Dept, Amman, Jordan
关键词
machine learning; text analysis; Twitter; Trump; randomforest classifier; multinomial Naive Bayes classifier; support vector classifier;
D O I
10.1109/SSD52085.2021.9429330
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
The current president of the United States of America, Donald Trump, is well known for his active Twitter account where he shares his personal daily thoughts using the Twitter handle '@realDonaldTrump'. This paper presents the use of classical machine learning techniques in an attempt to analyze Trump's use of words. Afterward, multiple steps of data preprocessing are applied to build a dictionary of definitive words Trump continuously uses, subsequently feeding this dictionary to a number of machine learning models to correctly classify a tweet as written by Trump or not. The accurate result this project has produced proves that Donald Trump has developed a certain pattern of word usage in what he chooses to criticize or shed light upon.
引用
收藏
页码:655 / 660
页数:6
相关论文
共 50 条