Knowledge Enhanced Masked Language Model for Stance Detection

Kawintiranon, Kornraphop; Singh, Lisa

doi:10.18653/v1/2021.naacl-main.376

Cited by 49 publications

(30 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous studies of stance detection largely focus on target-specific stance detection, where the training and inference stages share the same pre-defined set of targets [3,11,19,22,33,36]. In previous research, a task similar to ZSSD is the cross-target stance detection, where the learning ability of the classifier is adaptive to the unseen but related targets in the light of training on a known one [23,41,43,45].…”

Section: Related Work 21 Zero-shot Stance Detectionmentioning

confidence: 99%

Zero-Shot Stance Detection via Contrastive Learning

Liang

Chen

Gui

et al. 2022

Proceedings of the ACM Web Conference 2022

View full text Add to dashboard Cite

show abstract

Section: Related Work 21 Zero-shot Stance Detectionmentioning

confidence: 99%

Zero-Shot Stance Detection via Contrastive Learning

Liang

Chen

Gui

et al. 2022

Proceedings of the ACM Web Conference 2022

View full text Add to dashboard Cite

show abstract

“…Moreover, the occurrence of sentimental content along with the entities also signal stances (Mohammad et al, 2016b). Therefore, we take a masking strategy that upsamples entity tokens (Sun et al, 2019;Guu et al, 2020;Kawintiranon and Singh, 2021) and sentiment words to be masked for the MLM objective, which improves from prior pretraining work that only considers article-level comparison (Baly et al, 2020).…”

Section: Entity-and Sentiment-aware Mlmmentioning

confidence: 99%

POLITICS: Pretraining with Same-story Article Comparison for Ideology Prediction and Stance Detection

Liu¹,

Zhang²,

Wegsman³

et al. 2022

Preprint

View full text Add to dashboard Cite

Ideology is at the core of political science research. Yet, there still does not exist generalpurpose tools to characterize and predict ideology across different genres of text. To this end, we study Pretrained Language Models using novel ideology-driven pretraining objectives that rely on the comparison of articles on the same story written by media of different ideologies. We further collect a large-scale dataset, consisting of more than 3.6M political news articles, for pretraining. Our model POLITICS outperforms strong baselines and the previous state-of-the-art models on ideology prediction and stance detection tasks. Further analyses show that POLITICS is especially good at understanding long or formally written texts, and is also robust in few-shot learning scenarios.

show abstract

“…Inspired by prior research (Kawintiranon and Singh 2021), we pre-trained BERT on a large corpus of ∼5 M posts from Parler and added the most important stance tokens towards/against QAnon to the original BERT vocabulary. Overall, this should allow our model to capture Parler-specific language more accurately compared to using standard BERT for the downstream task of stance detection (Kawintiranon and Singh 2021). Subsequently, we finetuned the new language model on a sample of 1250 stance labeled posts and computed the average stance of a user towards QAnon (details are in our GitHub).…”

Section: Feature Extractionmentioning

confidence: 99%

Finding Qs: Profiling QAnon Supporters on Parler

Bär¹,

Pröllochs²,

Feuerriegel³

2022

Preprint

View full text Add to dashboard Cite

The social media platform "Parler" has emerged into a prominent fringe community where a significant part of the user base are self-reported supporters of QAnon, a far-right conspiracy theory alleging that a cabal of elites controls global politics. QAnon is considered to have had an influential role in the public discourse during the 2020 U.S. presidential election. However, little is known about QAnon supporters on Parler and what sets them aside from other users. Building up on social identity theory, we aim at profiling the characteristics of QAnon supporters on Parler. We analyze a large-scale dataset with more than 600,000 profiles of English-speaking users on Parler. Based on users' profiles, posts, and comments, we then extract a comprehensive set of user features, linguistic features, network features, and content features. This allows us to perform user profiling and understand to what extent these features discriminate between QAnon and non-QAnon supporters on Parler. Our analysis is three-fold:(1) We quantify the number of QAnon supporters on Parler, finding that 34,913 users (5.5 % of all users) openly report to support the conspiracy. (2) We examine differences between QAnon vs. non-QAnon supporters. We find that QAnon supporters differ statistically significantly from non-QAnon supporters across multiple dimensions. For example, they have, on average, a larger number of followers, followees, and posts, and thus have a large impact on the Parler network.(3) We use machine learning to identify which user characteristics discriminate QAnon from non-QAnon supporters. We find that user features, linguistic features, network features, and content features, can -to a large extent -discriminate QAnon vs. non-QAnon supporters on Parler. In particular, we find that user features are highly discriminatory, followed by content features and linguistic features.

show abstract

Knowledge Enhanced Masked Language Model for Stance Detection

Cited by 49 publications

References 34 publications

Zero-Shot Stance Detection via Contrastive Learning

Zero-Shot Stance Detection via Contrastive Learning

POLITICS: Pretraining with Same-story Article Comparison for Ideology Prediction and Stance Detection

Finding Qs: Profiling QAnon Supporters on Parler

Contact Info

Product

Resources

About