Clustering Twitter Users based on Changes in Sentiment in Response to Conflict

Abstract Number:

3183 

Submission Type:

Contributed Abstract 

Contributed Abstract Type:

Paper 

Participants:

Xiaoxia Champon (1), Leonard Stefanski (1), Ana-Maria Staicu (1), Chathura Jayalah (2), William Rand (1), Ivan Garibay (3)

Institutions:

(1) North Carolina State University, N/A, (2) University of Central Florida, Orlando, FL, (3) University of Central Florida, N/A

Co-Author(s):

Leonard Stefanski  
North Carolina State University
Ana-Maria Staicu  
North Carolina State University
Chathura Jayalah  
University of Central Florida
William Rand  
North Carolina State University
Ivan Garibay  
University of Central Florida

First Author:

Xiaoxia Champon  
North Carolina State University

Presenting Author:

Xiaoxia Champon  
North Carolina State University

Abstract Text:

Posts from social media users during major events reflect real-time reactions to topics discussed on the platform. Capturing the shift in sentiment over time can effectively detect public perceptions of a particular event and help guide public responses. Assessing changes in sentiment from opinion leaders, who are ordinary users, can help evaluate the impact of information disseminated in the cycle. We use continuous-time Markov decision processes combined with non-parametric intensity functions from Poisson point processes to model the immediate effects of information diffusion. The method is applied to data related to the Israel-Hamas conflict from Twitter. Rather than solely considering users' sentiment over time, this work focuses on changes that reflect the effect of the information consumed from social media platforms. We aim to provide interpretable clustering memberships representing reactions over information from different opinion on a specific event over time. This approach can be generalized to cluster users from any social media platform for any event and will be implemented in the mkpoisson function from the R package catfda.

Keywords:

shift|crisis event|markov chain|sparse multivariate functional data|Social Media|

Sponsors:

Section on Nonparametric Statistics

Tracks:

Applications of nonparametric methods

Can this be considered for alternate subtype?

Yes

Are you interested in volunteering to serve as a session chair?

Yes

I have read and understand that JSM participants must abide by the Participant Guidelines.

Yes

I understand that JSM participants must register and pay the appropriate registration fee by June 1, 2024. The registration fee is non-refundable.

I understand