Tweets and Votes: A Study of the 2011 Singapore General Election

Škorić, Marko M.; Poor, Nathaniel; Achananuparp, Palakorn; Lim, Ee-Peng; Jiang, Jing

doi:10.1109/hicss.2012.607

Cited by 107 publications

(75 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…So far, it has received little attention in Twitter data research. In fact, a number of studies involving Twitter have collected only geo-tagged tweets and analyzed those tweets in different domains such as public health (Paul and Dredze 2011), societal events (Ciulla et al 2012), political elections (Skoric et al 2012), tourist spots (Oku et al 2014), and earthquakes (Sakaki et al 2010). However, Cheng et al (2010) reported that only 0.42% tweets are geo-tagged, whereas Morstatter et al (2013) reported that around 3.17% tweets are geo-tagged.…”

Section: Related Workmentioning

confidence: 99%

Event classification and location prediction from tweets during disasters

et al. 2017

View full text Add to dashboard Cite

Social media is a platform to express one's view in real time. This real time nature of social media makes it an attractive tool for disaster management, as both victims and officials can put their problems and solutions at the same place in real time. We investigate the Twitter post in a flood related disaster and propose an algorithm to identify victims asking for help. The developed system takes tweets as inputs and categorizes them into high or low priority tweets. User location of high priority tweets with no location information is predicted based on historical locations of the users using the Markov model. The system is working well, with its classification accuracy of 81%, and location prediction accuracy of 87%. The present system can be extended for use in other natural disaster situations, such as earthquake, tsunami, etc., as well as man-made disasters such as riots, terrorist attacks etc. The present system is first of its kind, aimed at helping victims during disasters based on their tweets.

show abstract

Section: Related Workmentioning

confidence: 99%

Event classification and location prediction from tweets during disasters

et al. 2017

View full text Add to dashboard Cite

show abstract

“…Social media-based prediction has been widely studied [17], [26], [33]. The main motivation of these studies is the acquisition of large-scale user information (e.g., comments and opinions) from social media at low cost.…”

Section: Social Media Based Predictionmentioning

confidence: 99%

Predicting movie Box-office revenues by exploiting large-scale social media content

Liu

Ding

Chen

et al. 2014

Multimed Tools Appl

View full text Add to dashboard Cite

Predicting the box-office revenue of a movie before its theatrical release is an important but challenging problem that requires a high level of Artificial Intelligence. Nowadays, social media has shown its predictive power in various domains, which motivates us to exploit social media content to predict box-office revenues. In this study, we employ both linear and non-linear regression models, which are based on the crowd wisdom of social media, especially the posts of users, to predict movie box-office revenues. More specifically, the attention and popularity of the movie, purchase intention of users, and comments of users are automatically mined from social media data. In our model, the use of Linear Regression and Support Vector Regression in predicting the boxoffice revenue of a movie before its theatrical release is explored. To evaluate the effectiveness of the proposed approach, a cross-validation experiment is conducted. The experimental results show that large-scale social media content is correlated with movie box-office revenues and that the purchase intention of users can lead to more accurate movie box-office revenue predictions. Both the linear and non-linear prediction models have the advantage of predicting movie grosses in our experiments.

show abstract

“…In computer science, machine learning has been applied for topic classification during elections (Livne, Simmons et al 2011, Skoric, Poor et al 2012 as well as used for election forecasting (Tumasjan, Sprenger et al 2010). Most of this work has found tweets are poor predictor of electoral success.…”

Section: Twitter and Electionsmentioning

confidence: 99%

Twitter and elections: are tweets, predictive, reactive, or a form of buzz?

Murthy

2015

Information, Communication & Society

View full text Add to dashboard Cite

Abstract:The popular microblogging social media platform Twitter has been prominently covered in the press for its perceived role in activism, disaster recovery, and elections amongst other things. In the case of elections, Twitter has been used actively by candidates and voters alike in a diverse range of elections around the world including the 2010 UK elections, the 2012 US presidential elections, and the 2013 Italian elections. However, Twitter has often been found to be a poor predictor of electoral success. This article investigates what role tweets play during elections and whether they are more reactive than predictive. Using the specific case of the 2012 US Republican presidential primary elections, this article explores how candidate's Twitter presence affects electoral outcomes and whether the sentiment and frequency of candidate-related tweets is related to campaign success and offline success at the ballot box. This study finds that tweets were more reactive rather than predictive. Additionally, sentiment analysis revealed that tweets were generally neutral towards candidates. An interesting finding of our study is how candidates used Twitter to generate 'buzz', political capital that did not translate to success at the ballot box. We specifically explore how Huntsman's daughters used YouTube videos and tweets that were perceived as a 'backstage' look into the campaign and ultimately generated high levels of buzz. Though tweets do not seem to be reflective or predictive of an election campaign offline, they are being used for social media campaigns which can and do get covered by traditional media.

show abstract

Tweets and Votes: A Study of the 2011 Singapore General Election

Cited by 107 publications

References 9 publications

Event classification and location prediction from tweets during disasters

Event classification and location prediction from tweets during disasters

Predicting movie Box-office revenues by exploiting large-scale social media content

Twitter and elections: are tweets, predictive, reactive, or a form of buzz?

Contact Info

Product

Resources

About