“It’s modern day presidential! An evaluation of the effectiveness of sentiment analysis tools on president donald trump’s tweets”

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper reports on an evaluation of five commonly used, lexicon-based sentiment analysis tools (Mean-ingCloud, ParallelDots, Repustate, RSentiment for R, SentiStrength), tested for accuracy against a collection of Trump’s tweets spanning from election day November 2016 to one year post inauguration (January 2018). Repustate was found to be the most accurate at 67.53%. Our preliminary analysis suggests that this percentage reflects Trump’s frequent inclusion of both positive and negative sentiments in a single tweet. Additionally to providing an evaluative comparison of sentiment analysis tools, a summary of shared features of a number of existing datasets containing Twitter content along with a comprehensive discussion is also provided.

Original languageEnglish
Title of host publicationICEIS 2019 - Proceedings of the 21st International Conference on Enterprise Information Systems
EditorsJoaquim Filipe, Michal Smialek, Alexander Brodsky, Slimane Hammoudi
PublisherSciTePress
Pages632-639
Number of pages8
ISBN (Electronic)9789897583728
DOIs
Publication statusPublished - 2019
Event21st International Conference on Enterprise Information Systems, ICEIS 2019 - Heraklion, Crete, Greece
Duration: 3 May 20195 May 2019

Publication series

NameICEIS 2019 - Proceedings of the 21st International Conference on Enterprise Information Systems
Volume1

Conference

Conference21st International Conference on Enterprise Information Systems, ICEIS 2019
Country/TerritoryGreece
CityHeraklion, Crete
Period3/05/195/05/19

Fingerprint

Dive into the research topics of '“It’s modern day presidential! An evaluation of the effectiveness of sentiment analysis tools on president donald trump’s tweets”'. Together they form a unique fingerprint.

Cite this