An analysis of sentiments on facebook during the 2016 U.S. presidential election

Saud Alashri, Srinivasa Srivatsav Kandala, Vikash Bajaj, Roopek Ravi, Kendra L. Smith, Kevin C. Desouza

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

Social networking sites (SNS), such as Facebook and Twitter, are important spaces for political engagement. SNS have become common elements in political participation, campaigns, and elections. However, little is known about the dynamics between candidate posts and commentator sentiment in response to those posts on SNS. This study enriches computational political science by studying the 2016 U.S. elections and how candidates and commentators engage on Facebook. This paper also examines how online activity might be connected to offline activity and vice versa. We extracted 9,700 Facebook posts by five presidential candidates (Hillary Clinton, Donald Trump, Bernie Sanders, Ted Cruz, and John Kasich) from their official Facebook pages and 12,050,595 comments on those posts. We employed topic modeling, sentiment analysis, and trends detection using wavelet transforms to discover topics, trends, and reactions. Our findings suggest that Republican candidates are more likely to share information on controversial events that have taken place during the election cycle, while Democratic candidates focus on social policy issues. As expected, commentators on Republican candidate pages express negative sentiments toward current public policies as they seldom support decisions made by the Obama administration, while commentators on democratic candidate pages are more likely to express support for continuation or advancement of existing policies. However, the significance (strong/weak) and nature (positive/negative) of sentiments varied between candidates within political parties based on perceived credibility of the candidate's degree of credibility on a given issue. Additionally, we explored correlation between online trends of comments/sentiment and offline events. When analyzing the trend patterns, we found that changes in online trends are driven by three factors: 1) popular post, 2) offline debates, and 3) candidates dropping out of the race.

Original languageEnglish (US)
Title of host publicationProceedings of the 2016 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages795-802
Number of pages8
ISBN (Electronic)9781509028467
DOIs
StatePublished - Nov 21 2016
Event2016 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2016 - San Francisco, United States
Duration: Aug 18 2016Aug 21 2016

Other

Other2016 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2016
CountryUnited States
CitySan Francisco
Period8/18/168/21/16

Fingerprint

Sanders
facebook
presidential election
Wavelet transforms
candidacy
networking
trend
election
credibility
event
twitter
political participation
political science
public policy
campaign

Keywords

  • Facebook
  • Sentiment Analysis
  • Social Networking Sites
  • Time Series Analysis
  • Topic Inference
  • US Elections

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Sociology and Political Science
  • Communication

Cite this

Alashri, S., Kandala, S. S., Bajaj, V., Ravi, R., Smith, K. L., & Desouza, K. C. (2016). An analysis of sentiments on facebook during the 2016 U.S. presidential election. In Proceedings of the 2016 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2016 (pp. 795-802). [7752329] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ASONAM.2016.7752329

An analysis of sentiments on facebook during the 2016 U.S. presidential election. / Alashri, Saud; Kandala, Srinivasa Srivatsav; Bajaj, Vikash; Ravi, Roopek; Smith, Kendra L.; Desouza, Kevin C.

Proceedings of the 2016 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 795-802 7752329.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Alashri, S, Kandala, SS, Bajaj, V, Ravi, R, Smith, KL & Desouza, KC 2016, An analysis of sentiments on facebook during the 2016 U.S. presidential election. in Proceedings of the 2016 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2016., 7752329, Institute of Electrical and Electronics Engineers Inc., pp. 795-802, 2016 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2016, San Francisco, United States, 8/18/16. https://doi.org/10.1109/ASONAM.2016.7752329
Alashri S, Kandala SS, Bajaj V, Ravi R, Smith KL, Desouza KC. An analysis of sentiments on facebook during the 2016 U.S. presidential election. In Proceedings of the 2016 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 795-802. 7752329 https://doi.org/10.1109/ASONAM.2016.7752329
Alashri, Saud ; Kandala, Srinivasa Srivatsav ; Bajaj, Vikash ; Ravi, Roopek ; Smith, Kendra L. ; Desouza, Kevin C. / An analysis of sentiments on facebook during the 2016 U.S. presidential election. Proceedings of the 2016 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2016. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 795-802
@inproceedings{76500f6a0724480596cedbc63b8c83f5,
title = "An analysis of sentiments on facebook during the 2016 U.S. presidential election",
abstract = "Social networking sites (SNS), such as Facebook and Twitter, are important spaces for political engagement. SNS have become common elements in political participation, campaigns, and elections. However, little is known about the dynamics between candidate posts and commentator sentiment in response to those posts on SNS. This study enriches computational political science by studying the 2016 U.S. elections and how candidates and commentators engage on Facebook. This paper also examines how online activity might be connected to offline activity and vice versa. We extracted 9,700 Facebook posts by five presidential candidates (Hillary Clinton, Donald Trump, Bernie Sanders, Ted Cruz, and John Kasich) from their official Facebook pages and 12,050,595 comments on those posts. We employed topic modeling, sentiment analysis, and trends detection using wavelet transforms to discover topics, trends, and reactions. Our findings suggest that Republican candidates are more likely to share information on controversial events that have taken place during the election cycle, while Democratic candidates focus on social policy issues. As expected, commentators on Republican candidate pages express negative sentiments toward current public policies as they seldom support decisions made by the Obama administration, while commentators on democratic candidate pages are more likely to express support for continuation or advancement of existing policies. However, the significance (strong/weak) and nature (positive/negative) of sentiments varied between candidates within political parties based on perceived credibility of the candidate's degree of credibility on a given issue. Additionally, we explored correlation between online trends of comments/sentiment and offline events. When analyzing the trend patterns, we found that changes in online trends are driven by three factors: 1) popular post, 2) offline debates, and 3) candidates dropping out of the race.",
keywords = "Facebook, Sentiment Analysis, Social Networking Sites, Time Series Analysis, Topic Inference, US Elections",
author = "Saud Alashri and Kandala, {Srinivasa Srivatsav} and Vikash Bajaj and Roopek Ravi and Smith, {Kendra L.} and Desouza, {Kevin C.}",
year = "2016",
month = "11",
day = "21",
doi = "10.1109/ASONAM.2016.7752329",
language = "English (US)",
pages = "795--802",
booktitle = "Proceedings of the 2016 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - An analysis of sentiments on facebook during the 2016 U.S. presidential election

AU - Alashri, Saud

AU - Kandala, Srinivasa Srivatsav

AU - Bajaj, Vikash

AU - Ravi, Roopek

AU - Smith, Kendra L.

AU - Desouza, Kevin C.

PY - 2016/11/21

Y1 - 2016/11/21

N2 - Social networking sites (SNS), such as Facebook and Twitter, are important spaces for political engagement. SNS have become common elements in political participation, campaigns, and elections. However, little is known about the dynamics between candidate posts and commentator sentiment in response to those posts on SNS. This study enriches computational political science by studying the 2016 U.S. elections and how candidates and commentators engage on Facebook. This paper also examines how online activity might be connected to offline activity and vice versa. We extracted 9,700 Facebook posts by five presidential candidates (Hillary Clinton, Donald Trump, Bernie Sanders, Ted Cruz, and John Kasich) from their official Facebook pages and 12,050,595 comments on those posts. We employed topic modeling, sentiment analysis, and trends detection using wavelet transforms to discover topics, trends, and reactions. Our findings suggest that Republican candidates are more likely to share information on controversial events that have taken place during the election cycle, while Democratic candidates focus on social policy issues. As expected, commentators on Republican candidate pages express negative sentiments toward current public policies as they seldom support decisions made by the Obama administration, while commentators on democratic candidate pages are more likely to express support for continuation or advancement of existing policies. However, the significance (strong/weak) and nature (positive/negative) of sentiments varied between candidates within political parties based on perceived credibility of the candidate's degree of credibility on a given issue. Additionally, we explored correlation between online trends of comments/sentiment and offline events. When analyzing the trend patterns, we found that changes in online trends are driven by three factors: 1) popular post, 2) offline debates, and 3) candidates dropping out of the race.

AB - Social networking sites (SNS), such as Facebook and Twitter, are important spaces for political engagement. SNS have become common elements in political participation, campaigns, and elections. However, little is known about the dynamics between candidate posts and commentator sentiment in response to those posts on SNS. This study enriches computational political science by studying the 2016 U.S. elections and how candidates and commentators engage on Facebook. This paper also examines how online activity might be connected to offline activity and vice versa. We extracted 9,700 Facebook posts by five presidential candidates (Hillary Clinton, Donald Trump, Bernie Sanders, Ted Cruz, and John Kasich) from their official Facebook pages and 12,050,595 comments on those posts. We employed topic modeling, sentiment analysis, and trends detection using wavelet transforms to discover topics, trends, and reactions. Our findings suggest that Republican candidates are more likely to share information on controversial events that have taken place during the election cycle, while Democratic candidates focus on social policy issues. As expected, commentators on Republican candidate pages express negative sentiments toward current public policies as they seldom support decisions made by the Obama administration, while commentators on democratic candidate pages are more likely to express support for continuation or advancement of existing policies. However, the significance (strong/weak) and nature (positive/negative) of sentiments varied between candidates within political parties based on perceived credibility of the candidate's degree of credibility on a given issue. Additionally, we explored correlation between online trends of comments/sentiment and offline events. When analyzing the trend patterns, we found that changes in online trends are driven by three factors: 1) popular post, 2) offline debates, and 3) candidates dropping out of the race.

KW - Facebook

KW - Sentiment Analysis

KW - Social Networking Sites

KW - Time Series Analysis

KW - Topic Inference

KW - US Elections

UR - http://www.scopus.com/inward/record.url?scp=85006815884&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85006815884&partnerID=8YFLogxK

U2 - 10.1109/ASONAM.2016.7752329

DO - 10.1109/ASONAM.2016.7752329

M3 - Conference contribution

SP - 795

EP - 802

BT - Proceedings of the 2016 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -