Ideology Detection for Twitter Users via Link Analysis

Abstract

The problem of ideology detection is to study the latent (political) placement for people, which is traditionally studied on politicians according to their voting behaviors. Recently, more and more studies begin to address the ideology detection problem for ordinary users based on their online behaviors that can be captured by social media, e.g., Twitter. As far as we are concerned, however, the vast majority of the existing methods on ideology detection on social media have oversimplified the problem as a binary classification problem (i.e., liberal vs. conservative). Moreover, though social links can play a critical role in deciding one's ideology, most of the existing work ignores the heterogeneous types of links in social media. In this paper we propose to detect numerical ideology positions for Twitter users, according to their follow, mention, and retweet links to a selected set of politicians. A unified probabilistic model is proposed that can (1) explain the reasons why links are built among people in terms of their ideology, (2) integrate heterogeneous types of links together in determining people's ideology, and (3) automatically learn the quality of each type of links in deciding one's ideology. Experiments have demonstrated the advantages of our model in terms of both ranking and political leaning classification accuracy. It is shown that (1) using multiple types of links is better than using any single type of links alone to determine one's ideology, and (2) our model is even more superior than baselines when dealing with people that are sparsely linked in one type of links. We also show that the detected ideology for Twitter users aligns with our intuition quite well.

Your Stance is Exposed! Analysing Possible Factors for Stance Detection on Social Media

“…With the widespread of social media, they soon become a rich source of argumentative data, which has attracted many researchers to study stance detection on these platforms. As these platforms foster the real-time engagements with the new events, many studies used data collected from social media to predict people stances towards different topics [28,36,56]. For instance, the study done by [56] designed a stance detection model using YouTube's comments data.…”

Timme

“…Ideology detection in general could be naturally divided into two directions, based on the targets to predict: of the politicians [7,24,28], and of the ordinary citizens [1, 2, 5, 8, 13, 15-17, 20, 23, 29]. The work conducted on ordinary citizens could also be categorized into two types according to the source of data being used: intentionally collected via strategies like survey [1,20], and directly collected such as from news articles [2] or from social networks [13,15,17]. Some studies take advantages from both sides, asking self-reported responses from a group of users selected from social networks [29], and some researchers admitted the limitations of survey experiments [23].…”

“…Some studies take advantages from both sides, asking self-reported responses from a group of users selected from social networks [29], and some researchers admitted the limitations of survey experiments [23]. Emerging from social science, probabilistic models have been widely used for such kinds of analysis since the early 1980s [2,13,28]. On the other hand, on social network datasets, it is quite intuitive trying to extract information from text data to do ideology-detection [5,8,[15][16][17], only a few paid attention to links [9,13].…”

“…Most of their methodologies based on probabilistic models, following the long-lasting tradition started by social scientists. Some others [2,13,17,29] noticed the advantages of neural networks, but seldom do they focus on links. We will show that the social-network links' contribution to ideology detection has been under-estimated.…”

“…Existing works can not address the above challenges well. Even though some realized the importance of links [9,13], they failed to provide an embedding. Most people learn an embedding by separating the heterogeneous graph into different homogeneous views entirely, and combine them in the very end.…”