mlsanityData to 7 Oct 2026

Language Models Trained on Media Diets Can Predict Public Opinion

arXiv 2303.16779 ↗First posted 28 Mar 2023cs.CL cs.LGcited by 30

Not on the map. Why?

Abstract (arXiv)

Public opinion reflects and shapes societal behavior, but the traditional survey-based tools to measure it are limited. We introduce a novel approach to probe media diet models -- language models adapted to online news, TV broadcast, or radio show content -- that can emulate the opinions of subpopulations that have consumed a set of media. To validate this method, we use as ground truth the opinions expressed in U.S. nationally representative surveys on COVID-19 and consumer confidence. Our studies indicate that this approach is (1) predictive of human judgements found in survey response distributions and robust to phrasing and channels of media exposure, (2) more accurate at modeling people who follow media more closely, and (3) aligned with literature on which types of opinions are affected by media consumption. Probing language models provides a powerful new method for investigating media effects, has practical applications in supplementing polls and forecasting public opinion, and suggests a need for further study of the surprising fidelity with which neural language models can predict human responses.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). Builds on 11 of its 67 references that are in the map. First posted on arXiv 28 Mar 2023.

Builds on

11 of 67 references.

References · 11

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  4. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
  5. 2019Language Models as Knowledge Bases?cited by 1,922
  6. 2017Understanding Black-box Predictions via Influence Functionscited by 1,714
  7. 2021Ethical and social risks of harm from Language Modelscited by 957
  8. 2020AdapterHub: A Framework for Adapting Transformerscited by 441
  9. 2021Surface Form Competition: Why the Highest Probability Answer Isn't Always Rightcited by 256
  10. 2019Linking artificial and human neural representations of languagecited by 37
  11. 2014The effect of wording on message propagation: Topic- and author-controlled natural experiments on Twittercited by 21

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 7; 2024: 12; 2025: 7; 2026: 4.

30 papers.

Sort:

By area:

  1. 2023Can Large Language Models Transform Computational Social Science?cited by 245
  2. 2023Do LLMs exhibit human-like response biases? A case study in survey designcited by 176
  3. 2023Generative Language Models Exhibit Social Identity Biasescited by 107
  4. 2023Aligning Language Models to User Opinionscited by 98
  5. 2025Language Model Fine-Tuning on Scaled Survey Data for Predicting Distributions of Public Opinionscited by 64
  6. 2024Large Language Models Assume People are More Rational than We Really arecited by 49
  7. 2024Virtual Personas for Language Models via an Anthology of Backstoriescited by 49
  8. 2024Random Silicon Sampling: Simulating Human Sub-Population Opinion Using a Large Language Model Based on Group-Level Demographic Informationcited by 48
  9. 2023Opportunities and Risks of LLMs for Scalable Deliberation with Poliscited by 41
  10. 2024Evaluating Cultural Adaptability of a Large Language Model via Simulation of Synthetic Personascited by 36
  11. 2025Finetuning LLMs for Human Behavior Prediction in Social Science Experimentscited by 35
  12. 2024AI for social science and social science of AI: A Surveycited by 29
18 more
  1. 2024A Large-Scale Study of Relevance Assessments with Large Language Models: An Initial Lookcited by 18
  2. 2023Improving Interpersonal Communication by Simulating Audiences with Language Modelscited by 14
  3. 2024Vox Populi, Vox AI? Using Language Models to Estimate German Public Opinioncited by 13
  4. 2024COMMUNITY-CROSS-INSTRUCT: Unsupervised Instruction Generation for Aligning Large Language Models to Online Communitiescited by 12
  5. 2023Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Modelscited by 7
  6. 2024Reading Between the Tweets: Deciphering Ideological Stances of Interconnected Mixed-Ideology Communitiescited by 7
  7. 2024Can LLMs Learn Macroeconomic Narratives from Social Media?cited by 7
  8. 2024United in Diversity? Contextual Biases in LLM-Based Predictions of the 2024 European Parliament Electionscited by 5
  9. 2024Assessing Generalization for Subpopulation Representative Modeling via In-Context Learningcited by 4
  10. 2026Identity, Cooperation and Framing Effects within Groups of Real and Simulated Humanscited by 4
  11. 2025Learning from Convenience Samples: A Case Study on Fine-Tuning LLMs for Survey Non-response in the German Longitudinal Election Studycited by 2
  12. 2025Graph-Based Alternatives to LLMs for Human Simulationcited by 1
  13. 2025A Conceptual Model for Attributions in Event-Centric Knowledge Graphscited by 0
  14. 2025Recalibrating the Compass: Integrating Large Language Models into Classical Research Methodscited by 0
  15. 2025What Helps Language Models Predict Human Beliefs: Demographics or Prior Stances?cited by 0
  16. 2026Language Model Goal Selection Differs from Humans' in a Self-Directed Learning Taskcited by 0
  17. 2026From Demographics to Survey Anchors: Evaluating LLM Agents for Modeling Retirement Attitudescited by 0
  18. 2026Understanding Reliability in LLM-based Human Behavior Simulationcited by 0