Predicting User’s Political Party Using Ideological Stances

Gottipati, Swapna; Qiu, Minghui; Liu, Yang; Zhu, Feida; Jiang, Jing

doi:10.1007/978-3-319-03260-3_16

Cited by 20 publications

(19 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Related work on capturing political orientation uses techniques such as examining the follow graph of politicians [7], measuring volume, sentiment, or mood [3], or looking for explicit Term Count Term Count marriage+gay 588644 married+gay 92319 marriage+equal 181677 #noh8 81585 marriage+state 145929 marriage+man+woman 61020 marriage+same+sex 138667 marry+gay 57175 marriage+right 96483 doma 50480 Table 1. Top search terms for same-sex marriage for/against statements regarding an issue [15]. We believe our approach allows us to capture greater nuance in text and to characterize a larger volume of data, improving accuracy over other approaches.…”

Section: Background and Related Workmentioning

confidence: 96%

Modeling Ideology and Predicting Policy Change with Social Media

Zhang

Counts

2015

Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

Social media has emerged as a prominent platform where people can express their feelings about social and political issues of our time. We study the many voices discussing an issue within a constituency and how they reflect ideology and may signal the outcome of important policy decisions. Focusing on the issue of same-sex marriage legalization, we examine almost 2 million public Twitter posts related to same-sex marriage in the U.S. states over the course of 4 years starting from 2011. Among other findings, we find evidence of moral culture wars between ideologies and show that constituencies that express higher levels of emotion and have fewer actively engaged participants often precede legalization efforts that fail. From our measures, we build statistical models to predict the outcome of potential policy changes, with our best model achieving 87% accuracy. We also achieve accuracies of 70%, comparable to public opinion surveys, many months before a policy decision. We discuss how these analyses can augment traditional political science techniques as well as assist activists and policy analysts in understanding discussions on important issues at a population scale.

show abstract

Section: Background and Related Workmentioning

confidence: 96%

Modeling Ideology and Predicting Policy Change with Social Media

Zhang

Counts

2015

Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

show abstract

“…Boutet et al [4] analyze the characteristics of three main parties in UK election, and predict which party a user supports by the amount of Twitter messages referring to political accounts. Based on debate records on various political topics, Gottipati et al [10] adopt a matrix factorization approach to discover users' attitudes towards different political issues, and use k-means on the user feature vector to congregate users into several clusters. Some researchers extract text features such as hashtags and latent semantic analysis of a conversion and feed them into a standard classifier in order to classify users [25,6,20].…”

Section: Ideology Detection In Social Networkmentioning

confidence: 99%

Ideology Detection for Twitter Users via Link Analysis

Chen

Sun

et al. 2017

Social, Cultural, and Behavioral Modeling

View full text Add to dashboard Cite

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.

show abstract

“…Degenerative Models: To examine the effectiveness of the three extracted matrices studied in our model, we compare our model with a set of its degenerative models. We construct degenerative models by considering each matrix separately: PMF-UT used in [15,12], PMF-UU used in [12] and PMF-AD.…”

Section: Probabilistic Matrix Factorizationmentioning

confidence: 99%

“…Where as, we proposed an unsupervised approach and studied on data without special text characteristics. In our previous work [15], we exploited feedback behavior for the same task. However, the model performance degrades with high sparsity rate.…”

Section: Related Workmentioning

confidence: 99%

“…We then apply clustering algorithms on users to detect the communities of users Lastly, we evaluated our method on data set collected from the CreateDebate site 1 , and compared against state-of-the-art baselines as well as degenerative versions of our model. Among the various demographic attributes, the rapidly growing attention for user political affiliation is probably the most noticeable [3,14,15]. Therefore in this paper we study our model's performance on party affiliation detection problem.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An Integrated Model for User Attribute Discovery: A Case Study on Political Affiliation Identification

Gottipati

Qiu

Liu

et al. 2014

Advances in Knowledge Discovery and Data Mining

Self Cite

View full text Add to dashboard Cite

Discovering user demographic attributes from social media is a problem of considerable interest. The problem setting can be generalized to include three components-users, topics and behaviors. In recent studies on this problem, however, the behavior between users and topics are not effectively incorporated. In our work, we proposed an integrated unsupervised model which takes into consideration all the three components integral to the task. Furthermore, our model incorporates collaborative filtering with probabilistic matrix factorization to solve the data sparsity problem, a computational challenge common to all such tasks. We evaluated our method on a case study of user political affiliation identification, and compared against state-of-the-art baselines. Our model achieved an accuracy of 70.1% for user party detection task.

show abstract

Predicting User’s Political Party Using Ideological Stances

Cited by 20 publications

References 25 publications

Modeling Ideology and Predicting Policy Change with Social Media

Modeling Ideology and Predicting Policy Change with Social Media

Ideology Detection for Twitter Users via Link Analysis

An Integrated Model for User Attribute Discovery: A Case Study on Political Affiliation Identification

Contact Info

Product

Resources

About