mlsanityData to 7 Oct 2026

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

arXiv 2205.00619 ↗First posted 2 May 2022cs.CLcited by 50

Not on the map. Why?

Abstract (arXiv)

Ideology is at the core of political science research. Yet, there still does not exist general-purpose 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.

Key facts. Cited by 50 papers in the map (data through 7 Oct 2026). Builds on 30 of its 114 references that are in the map. First posted on arXiv 2 May 2022.

Builds on

30 of 114 references.

References · 30

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  5. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  6. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  7. 2019BioBERT: a pre-trained biomedical language representation model for biomedical text miningcited by 1,935
  8. 2020Don't Stop Pretraining: Adapt Language Models to Domains and Taskscited by 1,548
  9. 2019SciBERT: A Pretrained Language Model for Scientific Textcited by 1,404
  10. 2019What Does BERT Look At? An Analysis of BERT's Attentioncited by 994
  11. 2020Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inferencecited by 934
  12. 2019Defending Against Neural Fake Newscited by 553
18 more
  1. 2019ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmissioncited by 487
  2. 2019ERNIE: Enhanced Representation through Knowledge Integrationcited by 301
  3. 2019BERT has a Mouth, and It Must Speak: BERT as a Markov Random Field Language Modelcited by 184
  4. 2020FinBERT: A Pretrained Language Model for Financial Communicationscited by 161
  5. 2020Zero-Shot Stance Detection: A Dataset and Model using Generalized Topic Representationscited by 97
  6. 2016Stance Detection with Bidirectional Conditional Encodingcited by 93
  7. 2020We Can Detect Your Bias: Predicting the Political Ideology of News Articlescited by 92
  8. 2021Mitigating Political Bias in Language Models Through Reinforced Calibrationcited by 73
  9. 2019In Plain Sight: Media Bias Through the Lens of Factual Reportingcited by 68
  10. 2016Stance and Sentiment in Tweetscited by 62
  11. 2019Unsupervised User Stance Detection on Twittercited by 45
  12. 2016MITRE at SemEval-2016 Task 6: Transfer Learning for Stance Detectioncited by 27
  13. 2021Inference Time Style Control for Summarizationcited by 13
  14. 2018Stance Detection on Tweets: An SVM-based Approachcited by 8
  15. 2020Incorporating Count-Based Features into Pre-Trained Models for Improved Stance Detectioncited by 6
  16. 2021Identifying hidden coalitions in the US House of Representatives by optimally partitioning signed networks based on generalized balancecited by 4
  17. 2020Deep Learning for Political Sciencecited by 3
  18. 2021Cross-Partisan Discussions on YouTube: Conservatives Talk to Liberals but Liberals Don't Talk to Conservativescited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 15; 2024: 16; 2025: 11; 2026: 5.

50 papers.

Sort:

By area:

  1. 2023From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Modelscited by 257
  2. 2023Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language Modelscited by 46
  3. 2024MoralBERT: A Fine-Tuned Language Model for Capturing Moral Values in Social Discussionscited by 23
  4. 2023Introducing MBIB -- the first Media Bias Identification Benchmark Task and Dataset Collectioncited by 17
  5. 2024The Power of LLM-Generated Synthetic Data for Stance Detection in Online Political Discussionscited by 16
  6. 2024IndiVec: An Exploration of Leveraging Large Language Models for Media Bias Detection with Fine-Grained Bias Indicatorscited by 15
  7. 2024Modelling Political Coalition Negotiations Using LLM-based Agentscited by 13
  8. 2024ULTRA: Unleash LLMs' Potential for Event Argument Extraction through Hierarchical Modeling and Pair-wise Self-Refinementcited by 12
  9. 2023The Media Bias Taxonomy: A Systematic Literature Review on the Forms and Automated Detection of Media Biascited by 11
  10. 2024Quantifying Generative Media Bias with a Corpus of Real-world and Generated News Articlescited by 9
  11. 2023MOKA: Moral Knowledge Augmentation for Moral Event Extractioncited by 7
  12. 2024When Neutral Summaries are not that Neutral: Quantifying Political Neutrality in LLM-Generated News Summariescited by 7
38 more
  1. 2022Generative Entity-to-Entity Stance Detection with Knowledge Graph Augmentationcited by 6
  2. 2023Predicting Sentence-Level Factuality of News and Bias of Media Outletscited by 6
  3. 2023Disentangling Structure and Style: Political Bias Detection in News by Inducing Document Hierarchycited by 6
  4. 2023Connecting the Dots in News Analysis: Bridging the Cross-Disciplinary Disparities in Media Bias and Framingcited by 6
  5. 2022PAR: Political Actor Representation Learning with Social Context and Expert Knowledgecited by 5
  6. 2023Discourse Structures Guided Fine-grained Propaganda Identificationcited by 5
  7. 2024Benchmarking zero-shot stance detection with FlanT5-XXL: Insights from training data, prompting, and decoding strategies into its near-SoTA performancecited by 5
  8. 2025PRISM: A Framework for Producing Interpretable Political Bias Embeddings with Political-Aware Cross-Encodercited by 5
  9. 2023P^3SUM: Preserving Author's Perspective in News Summarization with Diffusion Language Modelscited by 4
  10. 2025Neutralizing the Narrative: AI-Powered Debiasing of Online News Articlescited by 4
  11. 2025Talking Point based Ideological Discourse Analysis in News Eventscited by 4
  12. 2024Sentence-level Media Bias Analysis with Event Relation Graphcited by 3
  13. 2024A Survey on Moral Foundation Theory and Pre-Trained Language Models: Current Advances and Challengescited by 3
  14. 2023All Things Considered: Detecting Partisan Events from News Media with Cross-Article Comparisoncited by 2
  15. 2024Encoding Hierarchical Schema via Concept Flow for Multifaceted Ideology Detectioncited by 2
  16. 2024Enabling Contextual Soft Moderation on Social Media through Contrastive Textual Deviationcited by 2
  17. 2024MGM: Global Understanding of Audience Overlap Graphs for Predicting the Factuality and the Bias of News Mediacited by 2
  18. 2025Conflicts in Texts: Data, Implications and Challengescited by 2
  19. 2025Multi-document Summarization through Multi-document Event Relation Graph Reasoning in LLMs: a case study in Framing Bias Mitigationcited by 2
  20. 2023Crossing the Aisle: Unveiling Partisan and Counter-Partisan Events in News Reportingcited by 1
  21. 2023Mitigating Framing Bias with Polarity Minimization Losscited by 1
  22. 2023PELMS: Pre-training for Effective Low-Shot Multi-Document Summarizationcited by 1
  23. 2024Zero-shot Cross-lingual Stance Detection via Adversarial Language Adaptationcited by 1
  24. 2024Coverage-based Fairness in Multi-document Summarizationcited by 1
  25. 2025Journalism-Guided Agentic In-Context Learning for News Stance Detectioncited by 1
  26. 2025Are LLMs Enough for Hyperpartisan, Fake, Polarized and Harmful Content Detection? Evaluating In-Context Learning vs. Fine-Tuningcited by 1
  27. 2026The Proxy Presumption: From Semantic Embeddings to Valid Social Measurescited by 1
  28. 2022Late Fusion with Triplet Margin Objective for Multimodal Ideology Prediction and Analysiscited by 0
  29. 2023Party Prediction for Twittercited by 0
  30. 2024DocNet: Semantic Structure in Inductive Bias Detection Modelscited by 0
  31. 2025Tracing Partisan Bias to Its Emotional Fingerprints: A Computational Approach to Mitigationcited by 0
  32. 2025Strategies for political-statement segmentation and labelling in unstructured textcited by 0
  33. 2025Political Leaning and Politicalness Classification of Textscited by 0
  34. 2025Comparative Personalization for Multi-document Summarizationcited by 0
  35. 2026LLM Active Alignment: A Nash Equilibrium Perspectivecited by 0
  36. 2026A Multi-View Media Profiling Suite: Resources, Evaluation, and Analysiscited by 0
  37. 2026Graph-Augmented LLMs for Swiss MP Ideology Predictioncited by 0
  38. 2026Ideology Prediction of German Political Textscited by 0