Balotage in Argentina 2015, a sentiment analysis of tweets

TL;DR

This paper presents a sentiment analysis methodology applied to Twitter data to predict voting trends during Argentina's 2015 presidential election, achieving higher accuracy than traditional surveys.

Contribution

It introduces a novel NLP-based sentiment analysis approach combined with Big Data architecture for social trend prediction in electoral contexts.

Findings

Effective detection of voting intention trends from Twitter data.

Higher prediction accuracy compared to traditional survey methods.

Successful integration of NLP sentiment analysis with Big Data tools.

Abstract

Twitter social network contains a large amount of information generated by its users. That information is composed of opinions and comments that may reflect trends in social behavior. There is talk of trend when it is possible to identify opinions and comments geared towards the same shared by a lot of people direction. To determine if two or more written opinions share the same address, techniques Natural Language Processing (NLP) are used. This paper proposes a methodology for predicting reflected in Twitter from the use of sentiment analysis functions NLP based on social behaviors. The case study was selected the 2015 Presidential in Argentina, and a software architecture Big Data composed Vertica data base with the component called Pulse was used. Through the analysis it was possible to detect trends in voting intentions with regard to the presidential candidates, achieving greater accuracy in predicting that achieved with traditional systems surveys.