With the emergence of smarthphones and social networks, a very large proportion of communication takes place on short texts. This type of communication, often anonymous, has allowed a new public participation in political issues. In particular, electoral phenomena all over the world have been greatly influenced by these networks. In the recent elections in Mexico, Twitter became a virtual place to bring together scientists, artists, politicians, adults, youth and students trying to persuade people about the candidate: Andres Manuel Lopez Obrador (AMLO). Our research is based on the collection of all tweets sent before, during and after the presidential elections of July 1, 2012 in Mexico containing the hashtag #AMLO. The aim of this study is to analyze the behavior of users on three different times. We apply SentiWordNet 3.0 in order to know how user behavior changes depending of the political situation and whether this is reflected on the tweets.
[1]
Johan Bollen,et al.
Modeling Public Mood and Emotion: Twitter Sentiment and Socio-Economic Phenomena
,
2009,
ICWSM.
[2]
Andrea Esuli,et al.
SENTIWORDNET: A Publicly Available Lexical Resource for Opinion Mining
,
2006,
LREC.
[3]
Brendan T. O'Connor,et al.
From Tweets to Polls: Linking Text Sentiment to Public Opinion Time Series
,
2010,
ICWSM.
[4]
Parag A. Pathak,et al.
Massachusetts Institute of Technology
,
1964,
Nature.
[5]
Isabell M. Welpe,et al.
Predicting Elections with Twitter: What 140 Characters Reveal about Political Sentiment
,
2010,
ICWSM.