A survey on the use of data and opinion mining in social media to political electoral outcomes prediction

Santos, Jéssica Soares dos; Bernardini, Flávia; Paes, Aline

doi:10.1007/s13278-021-00813-4

Cited by 18 publications

(6 citation statements)

References 88 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we present some previous works related to sentiment analysis of Twitter discussions on elections. According to [12], social media emerge as an important tool for people to express their opinions about candidates in electoral scenarios. In this context, there is an increasing number of election prediction approaches using social media and opinion mining; modeling this problem in different ways.…”

Section: Related Workmentioning

confidence: 99%

Untitled

2023

IJNLC

View full text Add to dashboard Cite

Nigeria president Buhari defeated his closest rival Atiku Abubakar by over 3 million votes. He was issued a Certificate of Return and was sworn in on 29 May 2019. However, there were claims of widespread hoax by the opposition. The sentiment analysis captures the opinions of the masses over social media for global events. In this paper, we use 2019 Nigeria presidential election tweets to perform sentiment analysis through the application of a voting ensemble approach (VEA) in which the predictions from multiple techniques are combined to find the best polarity of a tweet (sentence). This is to determine public views on the 2019 Nigeria Presidential elections and compare them with actual election results. Our sentiment analysis experiment is focused on location-based viewpoints where we used Twitter location data. For this experiment, we live-streamed Nigeria 2019 election tweets via Twitter API to create tweets dataset of 583816 size, pre-processed the data, and applied VEA by utilizing three different Sentiment Classifiers to obtain the choicest polarity of a given tweet. Furthermore, we segmented our tweets dataset into Nigerian states and geopolitical zones, then plotted state-wise and geopolitical-wise user sentiments towards Buhari and Atiku and their political parties. The overall objective of the use of states/geopolitical zones is to evaluate the similarity between the sentiment of location-based tweets compared to actual election results. The results reveal that whereas there are election outcomes that coincide with the sentiment expressed on Twitter social media in most cases as shown by the polarity scores of different locations, there are also some election results where our location analysis similarity test failed.

show abstract

Section: Related Workmentioning

confidence: 99%

Untitled

2023

IJNLC

View full text Add to dashboard Cite

show abstract

“…This section presents a brief overview of some previous works related to sentiment analysis of Twitter discussions on elections. According to [34], social media emerge as an important tool for people to express their opinions about candidates in electoral scenarios. In this context, there is an increasing number of election prediction approaches using social media and opinion mining; modelling this problem in different ways.…”

Section: Related Workmentioning

confidence: 99%

Location-based Sentiment Analysis of 2019 Nigeria Presidential Election Using A Voting Ensemble Approach

Onyenwe

Nwagbo

Orji

et al. 2022

Preprint

View full text Add to dashboard Cite

Sentiment analysis is a natural language processing (NLP) tool that uses automatic methods to capture the opinions of the masses over social media such as Twitter, especially for election monitoring and predictions. However, recent researches have explored mining of public sentiment in tweets neglecting using tweets location features and ensemble learning of NLP. In this paper, we use 2019 Nigeria presidential election tweets to perform sentiment analysis through the application of a voting ensemble approach (VEA) in which the predictions from multiple techniques are combined to find the best polarity of a tweet (sentence). This is to determine public views on the 2019 Nigeria Presidential elections and compare them with actual election results. Our sentiment analysis experiment is focused on location-based viewpoints using Twitter location features. For this experiment, we live-streamed Nigeria 2019 election tweets via Twitter API to create tweets dataset of 583816 size, pre-processed the data, and applied VEA by utilizing three different Sentiment Classifiers to obtain the choicest polarity of a given tweet. Furthermore, we segmented our tweets dataset into Nigerian states and geopolitical zones, then plotted state-wise and geopolitical-wise user sentiments towards the major candidates (Buhari and Atiku) and their political parties. The overall objective of the use of states/geopolitical zones is to evaluate the similarity between the sentiment of location-based tweets compared to actual election results. The results reveal that whereas there are election outcomes that coincide with the sentiment expressed on Twitter social media in most cases as shown by the polarity scores of different locations, there are also some election results where our location analysis similarity test failed.

show abstract

“…This communication network has over a billion logins and millions of active users who post 500 million tweets daily (Messaoudi et al, 2022). Twitter users may transmit information known as "tweets," with each tweet having a character restriction of 140 characters until October 2018 and 280 characters presently (Santos et al, 2021). Tweets are publicly visible unless the author decides to make them confidential.…”

Section: Literature Reviewmentioning

confidence: 99%

The Good, the Bad, and the Neutral: Twitter Users’ Opinion on the ASUU Strike

Muhammad

Nat

2022

InformingSciJ

View full text Add to dashboard Cite

Aim/Purpose: Nigeria’s university education goes through incessant strikes by the Academic Staff Union of Universities (ASUU). This strike has led to shared emotion on micro-blogging sites like Twitter. This study analyzed selected historical tweets from the “ASUU” to understand citizens’ opinions. Background: The researchers conducted sentiment analysis and topic modelling to understand Twitter users’ opinions on the strike. Methodology: The researchers used the Valence Aware Dictionary for Sentiment Reasoning (VADER) technique for sentiment analysis, and the Latent Dirichlet allocation (LDA) was used for topic modelling. A total of 10,000 tweets were first extracted for the study. After data cleaning, 1323 tweets were left. Contribution: To the researcher’s best knowledge, no published study has presented a sentiment analysis on the topic of the ASUU strike using the Twitter dataset. This research will fill this gap by providing a sentiment analysis and drawing out subjects by exploring the tweets on the phrase “ASUU.” Findings: The sentiment analysis result using VADER returned 567 tweets as ‘Negative,’ with the remaining 544 and 212 categorized as Positive and Neutral. The result of the LDA returned six topics, all comprising seven keywords. The topics were the solution to the strike, ASUU strike effect, strike Call-off, appeal to ASUU, student protest and student appeal. Recommendation for Researchers: Researchers can use this study’s findings to compare with other contexts of opinion mining. Practitioners may also use the research to understand better the attitudes of their staff and students about the strikes to create actionable solutions before the suspension of the strike. Future Research: Future studies can collect information from other social networking and blogging sites.

show abstract

A survey on the use of data and opinion mining in social media to political electoral outcomes prediction

Cited by 18 publications

References 88 publications

Untitled

Untitled

Location-based Sentiment Analysis of 2019 Nigeria Presidential Election Using A Voting Ensemble Approach

The Good, the Bad, and the Neutral: Twitter Users’ Opinion on the ASUU Strike

Contact Info

Product

Resources

About