Embeddings-Based Clustering for Target Specific Stances: The Case of a Polarized Turkey

05/19/2020
by   Ammar Rashed, et al.
0

On June 24, 2018, Turkey conducted a highly consequential election in which the Turkish people elected their president and parliament in the first election under a new presidential system. During the election period, the Turkish people extensively shared their political opinions on Twitter. One aspect of polarization among the electorate was support for or opposition to the reelection of Recep Tayyip Erdoğan. In this paper, we present an unsupervised method for target-specific stance detection in a polarized setting, specifically Turkish politics, achieving 90 user stances, while maintaining more than 80 representing users in an embedding space using Google's Convolutional Neural Network (CNN) based multilingual universal sentence encoder. The representations are then projected onto a lower dimensional space in a manner that reflects similarities and are consequently clustered. We show the effectiveness of our method in properly clustering users of divergent groups across multiple targets that include political figures, different groups, and parties. We perform our analysis on a large dataset of 108M Turkish election-related tweets along with the timeline tweets of 168k Turkish users, who authored 213M tweets. Given the resultant user stances, we are able to observe correlations between topics and compute topic polarization.

READ FULL TEXT
research
04/07/2020

A Few Topical Tweets are Enough for Effective User-Level Stance Detection

Stance detection entails ascertaining the position of a user towards a t...
research
10/12/2021

Prediction of Political Leanings of Chinese Speaking Twitter Users

This work presents a supervised method for generating a classifier model...
research
07/21/2020

Inferring Political Preferences from Twitter

Sentiment analysis is the task of automatic analysis of opinions and emo...
research
05/04/2022

Semi-supervised learning approaches for predicting South African political sentiment for local government elections

This study aims to understand the South African political context by ana...
research
12/22/2015

Topical differences between Chinese language Twitter and Sina Weibo

Sina Weibo, China's most popular microblogging platform, is currently us...
research
05/18/2021

Divided We Rule: Influencer Polarization on Twitter During Political Crises in India

Influencers are key to the nature and networks of information propagatio...
research
03/21/2023

Wearing Masks Implies Refuting Trump?: Towards Target-specific User Stance Prediction across Events in COVID-19 and US Election 2020

People who share similar opinions towards controversial topics could for...

Please sign up or login with your details

Forgot password? Click here to reset