Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form
D-Scholarship @ Pitt Banner and Links to Homepage

Sentiment Analysis and Political Party Classification in 2016 U.S. President Debates in Twitter

Ding, Tianyu and Deng, Junyi and Li, Jingting and Lin, Yu-Ru (2017) Sentiment Analysis and Political Party Classification in 2016 U.S. President Debates in Twitter. In: 2017 International Conference on Social Computing, Behavioral-Cultural Modeling & Prediction and Behavior Representation in Modeling and Simulation, 5-8 Jul 2017, Washington DC, USA.

[img]
Preview
 PDF
Download (197kB) | Preview

Abstract

We introduce a framework of combining tweet sentiment analysis with available default user profiles to classify political party of users who posted tweets in 2016 U.S. president debates. The main works focus on extracting event-related information in short event period instead of collecting tweets in a long-time period as most previous works do. Our framework is not limited in debate event, it can be used by researchers to build rationale of other events study. In sentiment analysis, we show that all three Naïve Bayes classifiers with different distributions obtain accuracy above 75% and the results reveal positive tweets most likely follow Gaussian or Multinomial distributions while negative tweets most likely follow Bernoulli distribution in our training data. We also show that under unbalanced sparse term document setting, instead of using “Add-1” parameter, tuning Laplace smoothing parameter to adjust the weights of new terms in a tweet can help improve the classifier’s performance in targeted direction. Finally, we show sentiment might help classifying political party

Share

Citation/Export:
Social Networking:
Share |

Details

Item Type: Conference or Workshop Item (Paper)
Status: Published
Creators/Authors:
CreatorsEmailPitt UsernameORCID
Ding, Tianyu
Deng, Junyi
Li, Jingting
Lin, Yu-Ruyurulin@pitt.eduYURULIN
Contributors:
ContributionContributors NameEmailPitt UsernameORCID
CorrespondentLin, Yu-RuUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Date: July 2017
Event Title: 2017 International Conference on Social Computing, Behavioral-Cultural Modeling & Prediction and Behavior Representation in Modeling and Simulation
Event Dates: 5-8 Jul 2017
Event Type: Conference
Refereed: Yes
Date Deposited: 06 Jul 2018 15:26
Last Modified: 16 Aug 2018 19:22
URI: http://d-scholarship.pitt.edu/id/eprint/34716

Metrics

Monthly Views for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item