Unsupervised User Stance Detection on Twitter

@article{Darwish2019UnsupervisedUS,
  title={Unsupervised User Stance Detection on Twitter},
  author={Kareem Darwish and Peter Stefanov and Micha{\"e}l Aupetit and Preslav Nakov},
  journal={ArXiv},
  year={2019},
  volume={abs/1904.02000}
}
We present a highly effective unsupervised framework for detecting the stance of prolific Twitter users with respect to controversial topics. In particular, we use dimensionality reduction to project users onto a low-dimensional space, followed by clustering, which allows us to find core users that are representative of the different stances. Our framework has three major advantages over pre-existing methods, which are based on supervised or semi-supervised classification. First, we do not… 

Figures and Tables from this paper

A Few Topical Tweets are Enough for Effective Stance Detection

  • Computer Science
  • 2020
This paper improves user-level stance detection on vocal Twitter users by representing tweets using contextualized embeddings, which capture latent meanings of words in context and performs unsupervised classification of the user, which entails clustering a user with other users in the training set.

A Few Topical Tweets are Enough for Effective User Stance Detection

This paper improves user-level stance detection on vocal Twitter users by representing tweets using contextualized embeddings, which capture latent meanings of words in context and performs unsupervised classification of the user, which entails clustering a user with other users in the training set.

Tweets2Stance: Users stance detection exploiting Zero-Shot Learning Algorithms on Tweets

A completely unsupervised stance detection framework that predicts the user’s stance (along with levels of agreement) about social-political statements by exploiting content-based analysis of its Twitter timeline by exploiting what the Twitter Party account wrote on Twitter.

Semi-supervised Stance Detection of Tweets Via Distant Network Supervision

This work presents SANDS, a new semi-supervised stance detector that starts from very few labeled tweets, and achieves a macro-F1 score of 0.55 (0.49) on US (India)-based datasets, outperforming 17 baselines substantially, particularly for minority stance labels and noisy text.

Predicting the Topical Stance of Media and Popular Twitter Users

This paper proposes a method that uses unsupervised learning and is able to characterize both the general political leaning of online media and popular Twitter users, as well as their stances with respect to controversial topics, by leveraging on the retweet behavior of users.

Predicting the Topical Stance and Political Leaning of Media using Tweets

A cascaded method that uses unsupervised learning to ascertain the stance of Twitter users with respect to a polarizing topic by leveraging their retweet behavior; then, it uses supervised learning based on user labels to characterize both the general political leaning of online media and of popular Twitter users.

Relational Embeddings for Language Independent Stance Detection

A new method to leverage social information such as friends and retweets by generating relational embeddings, namely, dense vector representations of interaction pairs based on social network data available on social networks is proposed.

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

These findings have distinct privacy implications, where they highlight that stance is strongly embedded in user's online social network that, in principle, individuals can be profiled from their interactions and connections even when they do not post about the topic.

Automatic Stance Detection for Twitter Data

This paper focuses on identifying user stance for the 2019 Indian General election by applying machine learning classifier and neural network approaches to detect user stance.

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

This paper presents an unsupervised method for target-specific stance detection in a polarized setting, specifically Turkish politics, achieving 90% precision in identifying user stances, while maintaining more than 80% recall.
...

References

SHOWING 1-10 OF 38 REFERENCES

Classifying latent user attributes in twitter

A novel investigation of stacked-SVM-based classification algorithms over a rich set of original features, applied to classifying these four user attributes, as distinct from the other primarily spoken genres previously studied in the user-property classification literature.

Classifying Political Orientation on Twitter: It's Not Easy!

Standard techniques for inferring political orientation show that methods which previously reported greater than 90% inference accuracy, actually achieve barely 65% accuracy on normal users, and show that classifiers cannot be used to classify users outside the narrow range of political orientation on which they were trained.

Predicting the Topical Stance and Political Leaning of Media using Tweets

A cascaded method that uses unsupervised learning to ascertain the stance of Twitter users with respect to a polarizing topic by leveraging their retweet behavior; then, it uses supervised learning based on user labels to characterize both the general political leaning of online media and of popular Twitter users.

A Machine Learning Approach to Twitter User Classification

This paper automatically infer the values of user attributes such as political orientation or ethnicity by leveraging observable information such as the user behavior, network structure and the linguistic content of the user’s Twitter feed through a machine learning approach.

Graph-based collective classification for tweets

Extensive experiment results show that the graph-based tweet classification approach remarkably improves the performance, while the ICA model with relationship of sharing the same #hashtag gives the best result on separate tweet graph.

Predicting the Political Alignment of Twitter Users

Several methods for predicting the political alignment of Twitter users based on the content and structure of their political communication in the run-up to the 2010 U.S. midterm elections are described and a practical application of this machinery to web-based political advertising is outlined.

Predicting political preference of Twitter users

This work builds prediction models based on a variety of contextual and behavioral features, training the models by resorting to a distant supervision approach and considering party candidates to have a predefined preference towards their respective parties, and uses the model to analyze the preference changes over the course of the election campaign.

Political Polarization on Twitter

It is demonstrated that the network of political retweets exhibits a highly segregated partisan structure, with extremely limited connectivity between left- and right-leaning users, and surprisingly this is not the case for the user-to-user mention network, which is dominated by a single politically heterogeneous cluster of users.

SemEval-2016 Task 6: Detecting Stance in Tweets

A shared task on detecting stance from tweets: given a tweet and a target entity (person, organization, etc.), automatic natural language systems must determine whether the tweeter is in favor of the given target, against thegiven target, or whether neither inference is likely.

Birds of a Feather Tweet Together: Integrating Network and Content Analyses to Examine Cross-Ideology Exposure on Twitter

It is found that Twitter users are unlikely to be exposed to cross-ideological content from the clusters of users they followed, as these were usually politically homogeneous.