Home // HUSO 2019, The Fifth International Conference on Human and Social Analytics // View article

Sentiment Analysis of French Political Tweets: #MacronPrésident

Authors:
Antoine Vanrysselberghe
Els Lefever

Keywords: sentiment analysis; French political tweets; social media analysis

Abstract:
The perpetual democratization of the Internet has made web user opinions on a wide range of topics continuously grow in value. As a result, many approaches to automatically analyse this user generated data have emerged over the last two decades. Sentiment analysis, in particular, aims to detect the presence of positive or negative sentiment within text. In this pilot study, we implement sentiment analysis on 615 political French tweets that all relate to the current French president, Emmanuel Macron. The experimental results show a satisfying performance of the supervised machine learning approach given the moderate size of the corpus. At the same time, the results reveal that the unequal distribution of the sentiments within the corpus (66% negative sentiment labels) considerably impacts the performance of the system for the positive and neutral sentiment labels. This pilot study shows, however, that supervised machine learning is a viable way to detect the global opinion of the French citizens on their president.

Pages: 5 to 10

Copyright: Copyright (c) IARIA, 2019

Publication date: June 30, 2019

Published in: conference

ISSN: 2519-8351

ISBN: 978-1-61208-725-2

Location: Rome, Italy

Dates: from June 30, 2019 to July 4, 2019