Supervised Sentiment Analysis of Twitter Handle of President Trump with Data Visualization Technique

The approval rating of the President of the United States (POTUS) can be used to gauge public support for the current administration. Public support, in turn, is highly dynamic and erratic, and can be influenced by current events, including political/economic policy announcements, ongoing scandals, treatment in the media, and general propaganda. The current POTUS, Donald Trump, is unique because, for the first time, the office of POTUS has direct access to social media platforms that offer a direct avenue of communication with the general population. Can the social media presence of POTUS influence the public approval of the administration? In this paper, we analyze the relationship between tweets generated by POTUS and his approval rating using sentiment-analytics and data visualization tools. The twitter feed of POTUS is mined, cleaned, and given a quantitative measure based on word content, called the “sentiment score”. By comparing tweets before the election, between election and inauguration, and after the inauguration, we find that the sentiment score for Mr. Trump's feed has increased on average with time by a factor of 60%. Using cross-correlation analysis, we find a preliminary causative relationship between POTUS twitter activity and approval rating. The findings provide a new perspective on the forces that influences public opinion, and the general strategy can be used for other analyses in the future.

[1]  Vadlamani Ravi,et al.  A survey on opinion mining and sentiment analysis: Tasks, approaches and applications , 2015, Knowl. Based Syst..

[2]  Hernán A. Makse,et al.  CUNY Academic Works , 2022 .

[3]  Madhavi Devaraj,et al.  Analytical mapping of opinion mining and sentiment analysis research during 2000-2015 , 2017, Inf. Process. Manag..

[4]  Fabrício Benevenuto,et al.  A Benchmark Comparison of State-of-the-Practice Sentiment Analysis Methods , 2015, ArXiv.

[5]  Flaviano Morone,et al.  Validation of Twitter opinion trends with national polling aggregates: Hillary Clinton vs Donald Trump , 2016, Scientific Reports.

[6]  Mark Dredze,et al.  A large-scale quantitative analysis of latent factors and sentiment in online doctor reviews , 2014, J. Am. Medical Informatics Assoc..

[7]  Mika V. Mäntylä,et al.  The evolution of sentiment analysis - A review of research topics, venues, and top cited papers , 2016, Comput. Sci. Rev..

[8]  M. Sorice,et al.  Populism between direct democracy and the technological myth , 2018, Palgrave Communications.

[9]  Finn Årup Nielsen,et al.  A New ANEW: Evaluation of a Word List for Sentiment Analysis in Microblogs , 2011, #MSM.

[10]  Fabrício Benevenuto,et al.  Comparing and combining sentiment analysis methods , 2013, COSN '13.

[11]  Timothy O'Keefe.  Feature Selection and Weighting Methods in Sentiment Analysis , 2009 .

[12]  Anabel Quan-Haase,et al.  A Model of Social Media Engagement: User Profiles, Gratifications, and Experiences , 2016, Why Engagement Matters.

[13]  Johanna D. Moore,et al.  Twitter Sentiment Analysis: The Good the Bad and the OMG! , 2011, ICWSM.

[14]  Yen-Liang Chen,et al.  Opinion mining from online hotel reviews - A text summarization approach , 2017, Inf. Process. Manag..

[15]  Yezheng Liu,et al.  The Competition of Homophily and Popularity in Growing and Evolving Social Networks , 2018, Scientific Reports.

[16]  Huan Liu,et al.  Unsupervised sentiment analysis with emotional signals , 2013, WWW.

[17]  Harith Alani,et al.  Semantic Sentiment Analysis of Twitter , 2012, SEMWEB.

[18]  Maite Taboada,et al.  Lexicon-Based Methods for Sentiment Analysis , 2011, CL.

[19]  David A. Ellis,et al.  Beyond Self-Report: Tools to Compare Estimated and Real-World Smartphone Use , 2015, PloS one.

[20]  Muhammad Anshari,et al.  Smartphones habits, necessities, and big data challenges , 2015 .

[21]  Erik Cambria,et al.  Affective Computing and Sentiment Analysis , 2016, IEEE Intelligent Systems.