Location
Online
Event Website
https://hicss.hawaii.edu/
Start Date
3-1-2023 12:00 AM
End Date
7-1-2023 12:00 AM
Description
Social media is used for online political discourse. Voter opinions have different sentiments associated with them. Understanding the factors behind these sentiments can help policymakers to take actions that align with voter needs and priorities. This research focuses on identifying the drivers (keywords) of sentiments while also investigating the relationship between these keywords and how fast the related message (the tweet) spreads. Sentiment Analysis (SA) of 779,169 tweets related to the 2021 Canadian Federal election was followed by text clustering to identify sentiment-driving topics. The results suggest some keywords common in opposite sentiment types (positive and negative), which shows polarization in Twitter while some keywords unique to a sentiment type suggest concepts to invest in or mitigate. Chi-Square tests suggest a significant relationship between keywords and the number of retweets for extremely negative tweets.
Recommended Citation
Noor, Hiba Mohammad and Turetken, Ozgur, "What Drives Sentiments on Social Media? An Exploratory Study on the 2021 Canadian Federal Election" (2023). Hawaii International Conference on System Sciences 2023 (HICSS-56). 8.
https://aisel.aisnet.org/hicss-56/dsm/data_analytics/8
What Drives Sentiments on Social Media? An Exploratory Study on the 2021 Canadian Federal Election
Online
Social media is used for online political discourse. Voter opinions have different sentiments associated with them. Understanding the factors behind these sentiments can help policymakers to take actions that align with voter needs and priorities. This research focuses on identifying the drivers (keywords) of sentiments while also investigating the relationship between these keywords and how fast the related message (the tweet) spreads. Sentiment Analysis (SA) of 779,169 tweets related to the 2021 Canadian Federal election was followed by text clustering to identify sentiment-driving topics. The results suggest some keywords common in opposite sentiment types (positive and negative), which shows polarization in Twitter while some keywords unique to a sentiment type suggest concepts to invest in or mitigate. Chi-Square tests suggest a significant relationship between keywords and the number of retweets for extremely negative tweets.
https://aisel.aisnet.org/hicss-56/dsm/data_analytics/8