Opinions from tweets as good indicators of leadership and followership status
Scores of public opinion about two popular world leaders collected from tweets based on the sentiment they exhibited were classified using two Machine learning techniques (Naïve Bayes and Support vector machines), and four features (Words, unigrams, bigrams and negation) for the classification, we f...
Main Authors: | , |
---|---|
Format: | Article |
Published: |
Asian Research Publishing Network
2015
|
Subjects: |
_version_ | 1796860559395651584 |
---|---|
author | Osanga, I. S. Salim N., N. |
author_facet | Osanga, I. S. Salim N., N. |
author_sort | Osanga, I. S. |
collection | ePrints |
description | Scores of public opinion about two popular world leaders collected from tweets based on the sentiment they exhibited were classified using two Machine learning techniques (Naïve Bayes and Support vector machines), and four features (Words, unigrams, bigrams and negation) for the classification, we found that the Naïve bayes with unigram features attained a high accuracy of up to 90% therefore indicating that tweets can be used to suggest potential candidates in political election and ways to improve a leaders reputation. © 2006-2015 Asian Research Publishing Network (ARPN. |
first_indexed | 2024-03-05T19:43:11Z |
format | Article |
id | utm.eprints-58694 |
institution | Universiti Teknologi Malaysia - ePrints |
last_indexed | 2024-03-05T19:43:11Z |
publishDate | 2015 |
publisher | Asian Research Publishing Network |
record_format | dspace |
spelling | utm.eprints-586942021-12-07T03:20:49Z http://eprints.utm.my/58694/ Opinions from tweets as good indicators of leadership and followership status Osanga, I. S. Salim N., N. QA75 Electronic computers. Computer science Scores of public opinion about two popular world leaders collected from tweets based on the sentiment they exhibited were classified using two Machine learning techniques (Naïve Bayes and Support vector machines), and four features (Words, unigrams, bigrams and negation) for the classification, we found that the Naïve bayes with unigram features attained a high accuracy of up to 90% therefore indicating that tweets can be used to suggest potential candidates in political election and ways to improve a leaders reputation. © 2006-2015 Asian Research Publishing Network (ARPN. Asian Research Publishing Network 2015 Article PeerReviewed Osanga, I. S. and Salim N., N. (2015) Opinions from tweets as good indicators of leadership and followership status. ARPN Journal Of Engineering And Applied Sciences, 10 (3). pp. 1045-1050. ISSN 1819-6608 |
spellingShingle | QA75 Electronic computers. Computer science Osanga, I. S. Salim N., N. Opinions from tweets as good indicators of leadership and followership status |
title | Opinions from tweets as good indicators of leadership and followership status |
title_full | Opinions from tweets as good indicators of leadership and followership status |
title_fullStr | Opinions from tweets as good indicators of leadership and followership status |
title_full_unstemmed | Opinions from tweets as good indicators of leadership and followership status |
title_short | Opinions from tweets as good indicators of leadership and followership status |
title_sort | opinions from tweets as good indicators of leadership and followership status |
topic | QA75 Electronic computers. Computer science |
work_keys_str_mv | AT osangais opinionsfromtweetsasgoodindicatorsofleadershipandfollowershipstatus AT salimnn opinionsfromtweetsasgoodindicatorsofleadershipandfollowershipstatus |