Can Large Language Models Transform Computational Social Science?
Open accessThe DOI matches its Crossref record; 320 of the 324 references it cites were found in a registry or an index; none of the 111 sources its claims cite is checked for support yet.
Abstract
Large language models (LLMs) are capable of successfully performing many language processing tasks zero-shot (without training data). If zero-shot LLMs can also reliably classify and explain social phenomena like persuasiveness and political ideology, then LLMs could augment the computational social science (CSS) pipeline in important ways. This work provides a road map for using LLMs as CSS tools. Towards this end, we contribute a set of prompting best practices and an extensive evaluation pipeline to measure the zero-shot performance of 13 language models on 25 representative English CSS benchmarks. On taxonomic labeling tasks (classification), LLMs fail to outperform the best fine-tuned models but still achieve fair levels of agreement with humans. On free-form coding tasks (generation), LLMs produce explanations that often exceed the quality of crowdworkers’ gold references. We conclude that the performance of today’s LLMs can augment the CSS research pipeline in two ways: (1) serving as zero-shot data annotators on human annotation teams, and (2) bootstrapping challenging creative generation tasks (e.g., explaining the underlying attributes of a text). In summary, LLMs are posed to meaningfully participate in social science analysis in partnership with humans.
Overview
CoChat Summary
TL;DR
This paper evaluates whether zero-shot large language models can augment the Computational Social Science pipeline by benchmarking 13 LLMs on 25 English CSS tasks. It concludes that LLMs can assist with annotation and generation but cannot fully replace fine-tuned models or human analysis.
Key findings
- On classification, zero-shot LLMs fail to outperform the best fine-tuned models but still achieve fair agreement with humans: 8/17 tasks reach moderate-to-good agreement (κ = 0.40–0.65), while 5/17 (29.5%) show poor agreement. Best zero-shot performance reaches 77.4 F1 on misinformation detection, with κ = 0.55 versus the original paper’s κ = 0.51 inter-human agreement.
- On generation, LLMs often exceed crowdworkers’ gold references: model generations outrank the dataset’s gold human reference at least 38% of the time across five tasks. For COVIDET, Misinformation Explanation, and Social Bias Inference, gpt-3.5-turbo produces more faithful, coherent, and fluent text than both gold references and the fine-tuned baseline; for Positive Reframing and Figurative Language explanation, text-davinci-003 matches gold-standard levels.
- Model selection matters: larger instruction-tuned open-source FLAN models are preferable for classification, while gpt-3.5-turbo is the clear leading LLM for generation. FLAN performance scales nearly logarithmically, with a median improvement of 5.0 absolute percentage points per order-of-magnitude size increase; OpenAI models do not monotonically benefit from scale, and RLHF improves average F1 by 3.5 absolute points over text-davinci-002.
- Performance is not tied to academic discipline, but document-level tasks are hardest, with all F1 scores near or below 50%; complex expert taxonomies also perform poorly, e.g., implicit hate 32.3 F1, empathy 35.9 F1, and dialect feature detection 32.9 F1.
Methods
- The authors evaluate zero-shot performance of 13 language models on 25 representative English CSS benchmarks: 10 utterance-level classification tasks, 6 conversation-level tasks, 4 document-level tasks, and 5 generation tasks. Models include FLAN-T5 sizes from 80M to 11B, FLAN-UL2 (20B), OpenAI GPT-3 text-001/002/003, gpt-3.5-turbo, and GPT-4.
- They use prompt engineering guidelines, generate five semantically equivalent prompt perturbations per task, set temperature to zero, and constrain decoding to valid output classes or use logit bias. Classification and structured parsing are evaluated with macro F1 averaged over prompt perturbations; supervised baselines use RoBERTa-large for classification and T5-base for generation, tuned by grid search and averaged over three random seeds.
- For each task, they evaluate a class-stratified sample of at most 500 instances from the designated test set. Generation is evaluated by domain experts on 1–5 Likert scales for faithfulness, relevance, coherence, and fluency, and by ranking model outputs against gold human references; ranking annotations were performed by two authors blind, with unanimous voting.
Limitations
- The paper states that its task selection is not exhaustive; sensitive domains such as mental health and cultural studies are largely outside scope, and available data resources are dominated by standard dialects and WEIRD populations. It also notes data leakage concerns for proprietary models, that it explores predictive rather than causal explanations, that bias and fairness could not be systematically analyzed with available datasets, and that proprietary LLMs carry opacity, privacy, and intellectual-property risks.
- The paper states that generation diversity may be limited and that human evaluation is costly and hard to reproduce; it also notes that exact model sizes and training data for OpenAI models are trade secrets, so scaling analyses rely on estimates.
- Evident from the text: classification results are based on class-stratified samples capped at 500 instances per task, prompt variance is addressed with only five perturbations, and the human ranking evaluation used the authors as blind annotators rather than independent crowdworkers. Some dataset categories with fewer than 10 examples were omitted from evaluation, and automatic generation metrics such as BLEU, BERTScore, and BLEURT produced uninterpretable scores.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures





Verification
Claims the paper makes
0 Valid · 14 Not valid · 77 Not checked · 179 Own results and interpretations
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“On free-form coding tasks (generation), LLMs produce explanations that often exceed the quality of crowdworkers' gold references.”
§ Can Large Language Models Transform Computational Social Science? > Abstract
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“All other document-level accuracies are at or below 50%.”
§ Can Large Language Models Transform Computational Social Science? > 5.3 Domain-Utility (RQ3)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This is confirmed by our error analysis in Figure 2 where GPT3.5 often defaults to the neutral, more colloquially recognizable label stereotype (64% of errors) rather than use a more taxonomy-specific label like white grievance.”
§ Can Large Language Models Transform Computational Social Science? > 5.1 Viability (RQ1) 5.1.1 Zero-Shot Viability.
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Figure 3 shows FLAN classification performances scaling nearly logarithmically with the parameter count.”
§ Can Large Language Models Transform Computational Social Science? > 5.2 Model-Selection (RQ2)
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In particular, documents encode complex sequences of ideas or temporal events, and overall, the two lowest task performances are on the document-level tasks: character trope classification and event argument extraction.”
§ Can Large Language Models Transform Computational Social Science? > 5.3 Domain-Utility (RQ3)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
114 more claims
Create a free account to see all 270 claims and to verify the 92 references still open.
- It may state two separate claims as one. 80
- Probably not a substantial claim. 91
- The quote only partly states this claim. 1
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“For the domain of psychology, LLM-based agents can be leveraged for conducting simulation experiments, providing mental health support and so on [102-105].”
From A survey on large language model based autonomous agents (2024) · cites this paper as [105]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Research assistant: Beyond their application in specialized domains, LLM-based agents are increasingly adopted as versatile assistants in the broad field of social science research [105,114].”
From A survey on large language model based autonomous agents (2024) · cites this paper as [105]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Political science and economy: LLM-based agents can also be utilized to study political science and economy [29,105,106].”
From A survey on large language model based autonomous agents (2024) · cites this paper as [105]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Researchers have also recently noted GPT’s ability to help with computational social science tasks (49–54), detect misinformation (55), infer politicians’ ideologies (56), write persuasive political arguments (57), respond to patient questions (58), simulate human research participants (59–61), and model collective behavior (56).”
From GPT is an effective tool for multilingual psychological text analysis (2024) · cites this paper as [49]
In the citing paper
“Specifically, commentary has focused on large language models (LMs), which rely on minimal researcher input and model training for the classification of different types of data [Ziems et al., 2024, Törnberg, 2023a].”
From Prompt Stability Scoring for Text Annotation with Large Language Models (2024) · cites this paper as Ziems et al., 2024
1 more claim about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated major: it would touch a result — a value a result rests on, reported and recomputed p-values on opposite sides of the significance level, two passages that conflict with no sign which is right, or a cited work retracted before this paper was published.
In the paper
§ Can Large Language Models Transform Computational Social Science? > Causality and Explanations.
“Stance | gpt-3.5-turbo 72.0 0.58 | moderate”
§ Can Large Language Models Transform Computational Social Science? > 5.1 Viability (RQ1) 5.1.1 Zero-Shot Viability.
“These tasks also correspond to the highest absolute performances on Stance (76.0 F1)”
Rated major: it would touch a result — a value a result rests on, reported and recomputed p-values on opposite sides of the significance level, two passages that conflict with no sign which is right, or a cited work retracted before this paper was published.
In the paper
§ Can Large Language Models Transform Computational Social Science? > Causality and Explanations.
“Power Toxicity | gpt-4 gpt-4 | 59.7 0.26 55.4 0.11”
§ Can Large Language Models Transform Computational Social Science? > 5. Classification Results
“Power 49.5 72.7 46.6 48.0 40.8 55.6 52.6 56.9 43.1 39.8 37.5 36.9 39.2 51.9 56.5 42.0”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Can Large Language Models Transform Computational Social Science? > Causality and Explanations.
“Ideology Event Det. gpt-4 gpt-4 | 51.5 0.51 23.0 n/a”
§ Can Large Language Models Transform Computational Social Science? > 5. Classification Results
“Event Det.0.4 75.8 9.8 7.0 1.0 10.9 41.8 50.6 29.8 47.3 47.4 44.4 48.8 52.4 51.3 14.8”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Can Large Language Models Transform Computational Social Science? > 5.3 Domain-Utility (RQ3)
“All other document-level accuracies are at or below 50%.”
§ Can Large Language Models Transform Computational Social Science? > 5. Classification Results
“Event Det.0.4 75.8 9.8 7.0 1.0 10.9 41.8 50.6 29.8 47.3 47.4 44.4 48.8 52.4 51.3 14.8”
Citations
Cites
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
The Structure of Scientific Revolutions: 50th Anniversary Edition
Kuhn, T. S., & Hacking, I. (2012) · doi:10.7208/chicago/9780226458144.001.0001 · Cited by 21,170
RoBERTa: A Robustly Optimized BERT Pretraining Approach
Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019) · arXiv · doi:10.48550/arxiv.1907.11692 · Cited by 16,515
Framing: toward clarification of a fractured paradigm
Entman, R. M. (1993) · Journal of Communication · doi:10.1111/j.1460-2466.1993.tb01304.x · Cited by 16,203 · cited 1×
“Political scientists study how political actors move agendas (Grimmer, 2010) by persuasively framing their discourse “to promote a particular problem definition, causal interpretation, moral evaluation, and/or treatment recommendation” (Entman, 1993).”
BackgroundExploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1910.10683 · Cited by 10,929
Politeness: Some Universals in Language Usage
Brown, P., Levinson, S. C., & Gumperz, J. J. (1987) · Cambridge University Press eBooks · doi:10.1017/cbo9780511813085 · Cited by 10,438
Scaling Laws for Neural Language Models
Kaplan, J., McCandlish, S., Henighan, T., Brown, T. B., Chess, B., Child, R., Gray, S., Radford, A., Wu, J., & Amodei, D. (2020) · arXiv · doi:10.48550/arxiv.2001.08361 · Cited by 9,550 · cited 1×
“LLMs generally follow scaling laws (Kaplan et al., 2020; Hoffmann et al., 2022) where performance increases with the size of the model and training data.”
BackgroundThe spread of true and false news online
Vosoughi, S., Roy, D., & Aral, S. (2018) · Science · doi:10.1126/science.aap9559 · Cited by 8,847 · cited 1×
“…analyses of social norms and conventions (Centola et al., 2018; Bicchieri, 2005), information diffusion (Leskovec et al., 2009; Tan et al., 2014; Vosoughi et al., 2018; Cheng et al., 2016), emotional contagion (Bail, 2016), collective behaviors (Barberá et al., 2015), and social movements…”
BackgroundSpeech Genres and Other Late Essays
Bakhtin, M. M. (1986) · University of Texas Press eBooks · doi:10.7560/720466 · Cited by 8,470
“Risk, Ambiguity, and the Savage Axioms.”
Ellsberg, D. (1961) · The Quarterly Journal of Economics · doi:10.2307/1884324 · Cited by 7,891
Research works printed but not linked: 12
- Cialdini, 2003, Influence
- 73. Dang, Hoa Trang. 2005. Overview of duc 2005. In Proceedings of the document understanding conference, volume 2005, pages 1-12, Citeseer.
- 77. Ziems, Held, Shaikh, Chen, Zhang, Yang Can LLMs Transform CSS? Workshop held in conjunction with ACL 2016 (LAW-X 2016), pages 188-198, Association for Computational Linguistics, Berlin, Germany.
- 100. Garfinkel, Harold. 2016. Studies in ethnomethodology. In Social Theory Re-Wired. Routledge, pages 85-95.
- 109. Gross, Justin H, Brice Acree, Yanchuan Sim, and Noah A Smith. 2013. Testing the etch-a-sketch hypothesis: a computational analysis of mitt romney's ideological makeover during the 2012 primary vs. general elections. In APSA 2013 Annual Meeting Paper, American Political Science Association 2013 Annual Meeting.
- 152. Kuhn, Thomas S. 1962. The structure of Scientific Revolutions. The University of Chicago Press.
- 156. Ziems, Held, Shaikh, Chen, Zhang, Yang Can LLMs Transform CSS? Conference on Human Factors in Computing Systems, CHI 2015, Seoul, Republic of Korea, April 18-23, 2015, pages 3739-3748, ACM.
- 172. Luo, Yiwei, Dallas Card, and Dan Jurafsky. 2020b. Detecting stance in media on global warming. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 3296-3315, Association for Computational Linguistics, Online. · DOI
- 188. Murray, Michael et al. 2015. Narrative psychology. Qualitative psychology: A practical guide to research methods, pages 85-107.
- Omitaomu, 2022, Empathic conversations: A multi-level dataset of contextualized conversations, ArXiv preprint
- Rothbaum, 2000, Cognitive-behavioral therapy, 320
- 227. Sacks, Harvey. 1992. Lectures on conversation: Volume i. Malden, Massachusetts: Blackwell.
Cited by
Items 201–300 of 609
Mitigating Biases in Hate Speech Detection from A Causal Perspective
Zhang, Z., Chen, J., & Yang, D. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.440 · Cited by 22
Self-citationLuke, H. (2025) · Land Use Policy · doi:10.1016/j.landusepol.2025.107526 · Cited by 9
Chang, C. H., Cook‐Patton, S. C., Erbaugh, J. T., Lu, L., Masuda, Y. J., Molnár, I. D., Papp, D., & Robinson, B. E. (2025) · Conservation Biology · doi:10.1111/cobi.14464 · Cited by 13
Political expression of academics on Twitter
Garg, P., & Fetzer, T. (2025) · Nature Human Behaviour · doi:10.1038/s41562-025-02199-1 · Cited by 20
GPT-4V shows human-like social perceptual capabilities at phenomenological and neural levels
Santavirta, S., Wu, Y., Suominen, L., & Nummenmaa, L. (2025) · Imaging Neuroscience · doi:10.1162/imag.a.134 · Cited by 12
Zheng, E., Fu, H., Thelwall, M. A., & Fang, Z. (2025) · Journal of the Association for Information Science and Technology · doi:10.1002/asi.70028 · Cited by 13
Generative Psychometrics—An Emerging Frontier in Mental Health Measurement
Galatzer‐Levy, I. R., Tomašev, N., Chung, S., & Williams, G. (2025) · JAMA Psychiatry · doi:10.1001/jamapsychiatry.2025.3258 · Cited by 11
Zhang, P., Wei, Z., & Kong, F. (2026) · International Journal of Disaster Risk Science · doi:10.1007/s13753-026-00693-2 · Cited by 12
Choi, D., Peskoff, D., & Stewart, B. (2026) · Political Science Research and Methods · doi:10.1017/psrm.2025.10086 · Cited by 9
Large Language Models for Market Research: A Data-Augmentation Approach
Wang, M., Zhang, D., & Zhang, H. (2026) · Marketing Science · doi:10.1287/mksc.2025.0009 · Cited by 37
CH-Wang, S., Saakyan, A., Li, O., Zhou, Y., & Muresan, S. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.215 · Cited by 33
Beyond the Screen: Exploring Moral Understanding via User Comments on YouTube Short Films
Malik, M., Youk, S., & Weber, R. (2024) · Journal of Media Psychology Theories Methods and Applications · doi:10.1027/1864-1105/a000430 · Cited by 10
Decoding Real-World Artificial Intelligence Incidents
Velázquez, J. D. M., Šćepanović, S., Gvirtz, A., & Quercia, D. (2024) · Computer · doi:10.1109/mc.2024.3432492 · Cited by 25
Fairness identification of large language models in recommendation
Liu, W., Liu, B., Qin, J., Zhang, X., Huang, W., & Wang, Y. (2025) · Scientific Reports · doi:10.1038/s41598-025-89965-3 · Cited by 15
Zhang, Y., Huang, B., Yuan, W., Jiang, Z., Peng, L., Chen, S., & Tan‐Soo, J. (2025) · Information Processing & Management · doi:10.1016/j.ipm.2025.104090 · Cited by 8
LLaMALoop: Enhancing Information Retrieval in LLaMA with Semantic Relevance Feedback LoopPreprint
Tsai, H.-C., Kuo, C.-W., & Huang, Y.-F. (2023) · Research Square · doi:10.21203/rs.3.rs-3810235/v1 · Cited by 8
Revolutionizing Marketing Research with a Large Language Model: A Hybrid AI-Human ApproachPreprint
Arora, N. K., Chakraborty, I., & Nishimura, Y. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4683054 · Cited by 7
LLMs as Research Tools: A Large Scale Survey of Researchers' Usage and Perceptions
Liao, Z., Antoniak, M., Cheong, I., Cheng, E. Y.-Y., Lee, A.-H., Lo, K., Chang, J. C., & Zhang, A. X. (2024) · arXiv · doi:10.48550/arxiv.2411.05025 · Cited by 7
Meng, H., Zhang, R., Wang, G., Yang, Y., Qin, P., Lee, J., & Lee, Y. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3714255 · Cited by 19
Zhu, D. (2025) · Scientific Reports · doi:10.1038/s41598-025-04171-5 · Cited by 12
OD-Mind: An ocean drilling expert knowledge query system driven by knowledge graph
Yang, Y., Cao, W., Li, Y., Chang, R., Yang, G., Gan, C., & Wu, M. (2025) · Ocean Engineering · doi:10.1016/j.oceaneng.2025.122135 · Cited by 7
Generative AI-Destination Marketing: Do Privacy Concerns and Justification Matter?
Yhee, Y., Kim, J. Y., Kim, J., & Koo, C. (2025) · Journal of Travel Research · doi:10.1177/00472875251349235 · Cited by 11
Stoll, A., Yu, J., Andrich, A., & Domahidi, E. (2025) · Communication Methods and Measures · doi:10.1080/19312458.2025.2551693 · Cited by 9
Chen, H., Zhao, J., Zheng, S., Zhang, X., Duan, H., & Lü, X. (2025) · BMC Medical Research Methodology · doi:10.1186/s12874-025-02674-3 · Cited by 8
Large Language Models as Psychological Simulators: A Methodological Guide
Lin, Z. (2026) · Advances in Methods and Practices in Psychological Science · doi:10.1177/25152459251410153 · Cited by 29
The AI-Reflexivity Checklist (ARC): A Pre-Analysis Pause for LLM-Assisted Coding
Prahl, A. (2025) · Qualitative Health Research · doi:10.1177/10497323251401503 · Cited by 10
Chew, Y. J., Yin, O. S., Pang, Y. H., & Lim, Z. Y. (2024) · Forests · doi:10.3390/f15060923 · Cited by 8
Securing Against Deception: Exploring Phishing Emails Through ChatGPT and Sentiment Analysis
Sayyafzadeh, S., Weatherspoon, M. H., Yan, J., & Chi, H. (2024) · IEEE/ACIS International Conference on Software Engineering Research, Management and Applications (SERA) · doi:10.1109/sera61261.2024.10685564 · Cited by 7
Don’t Do That! Reverse Role Prompting Helps Large Language Models Stay in Personality Traits
Chen, S., Taveekitworachai, P., Xia, Y., Li, X., Gursesli, M. C., Lanatà, A., Guazzini, A., & Thawonmas, R. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-78453-8_7 · Cited by 9
AstroMLab 2: AstroLLaMA-2-70B Model and Benchmarking Specialised LLMs for Astronomy
Pan, R., Nguyen, T. D., Arora, H., Accomazzi, A., Ghosal, T., & Ting, Y.-S. (2024) · International Conference for High Performance Computing, Networking, Storage and Analysis (SC) · doi:10.1109/scw63240.2024.00019 · Cited by 20
LLM Chain Ensembles for Scalable and Accurate Data Annotation
Farr, D., Manzonelli, N., Cruickshank, I. J., Starbird, K., & West, J. D. (2024) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata62323.2024.10826109 · Cited by 22
Twitter communities are associated with changing user’s opinion towards COVID-19 vaccine in Japan
Wu, Q., Sano, Y., Takayasu, H., Havlin, S., & Takayasu, M. (2025) · Scientific Reports · doi:10.1038/s41598-025-95595-6 · Cited by 11
Reinforcement Learning for Optimized Information Retrieval in LLaMAPreprint
Tu, C.-H., Hsu, H.-J., & Chen, S.-W. (2024) · Research Square · doi:10.21203/rs.3.rs-3847100/v1 · Cited by 50
How do Generative Language Models Answer Opinion Polls?Preprint
Boelaert, J., Coavoux, S., Ollion, É., Petev, I. D., & Präg, P. (2024) · SocArXiv (OSF Preprints) · doi:10.31235/osf.io/r2pnb · Cited by 15
Best practices for responsibly using AI tools in social sciences research
Feng, G. C. (2024) · Cogent Social Sciences · doi:10.1080/23311886.2024.2420484 · Cited by 29
Chen, Z., Jiang, Z., Yang, F., He, Z., Hou, Y., Cho, E., McAuley, J., Galstyan, A., Hu, X., & Yang, J. (2023) · Proceedings of the 32nd ACM International Conference on Information and Knowledge Management · doi:10.1145/3583780.3615314 · Cited by 5
CRT-QA: A Dataset of Complex Reasoning Question Answering over Tabular Data
Zhang, Z., Li, X., Gao, Y., & Lou, J. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.132 · Cited by 36
Self-citationSpain, R. D., Min, W., Kumaran, V., Pande, J., Saville, J. D., & Lester, J. C. (2025) · International Journal of Artificial Intelligence in Education · doi:10.1007/s40593-025-00479-5 · Cited by 9
The impact of language models on the humanities and vice versa
Underwood, T. (2025) · Nature Computational Science · doi:10.1038/s43588-025-00819-4 · Cited by 8
Zhou, J., Shen, R., You, Y., DiSalvo, C. F., Dombrowski, L. S., & MacLellan, C. J. (2025) · Designing Interactive Systems Conference · doi:10.1145/3715336.3735831 · Cited by 12
Using language models to label clusters of scientific documents
Murray, D., Ni, C., Gu, W., & Hubbard, T. (2025) · Scientometrics · doi:10.1007/s11192-025-05445-5 · Cited by 8
Liu, D., Long, Y., Zuoqiu, S., Liu, D., Li, K., Lin, Y., Liu, H., Yin, R., & Tang, T. (2026) · Journal of Medical Internet Research · doi:10.2196/85206 · Cited by 5
Systematic partisan content skews in TikTok during the 2024 US elections
Ibrahim, H., Jang, H. D., AlDahoul, N., Kaufman, A. R., Rahwan, T., & Zaki, Y. (2026) · Nature · doi:10.1038/s41586-026-10447-1 · Cited by 40
Task-Agnostic Low-Rank Adapters for Unseen English Dialects
Xiao, Z., Held, W., Liu, Y., & Yang, D. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.487 · Cited by 21
Self-citationVIBE: Topic-Driven Temporal Adaptation for Twitter Classification
Zhang, Y., Li, J., & Li, W. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.203 · Cited by 25
Topal, M. B., Bozanta, A., & Basar, A. (2024) · IEEE International Conference on Collaborative Advances in Software and Computing (CASCON) · doi:10.1109/cascon62161.2024.10838185 · Cited by 6
Tsaruk, O. (2025) · Long Range Planning · doi:10.1016/j.lrp.2025.102514 · Cited by 6
Socially Aware Language Technologies: Perspectives and Practices
Yang, D., Hovy, D., Jurgens, D., & Plank, B. (2025) · Computational Linguistics · doi:10.1162/coli_a_00556 · Cited by 36
Self-citationThe Strong Pull of Prior Knowledge in Large Language Models and Its Impact on Emotion Recognition
Chochlakis, G., Potamianos, A., Lerman, K., & Narayanan, S. S. (2024) · International Conference on Affective Computing and Intelligent Interaction and workshops · doi:10.1109/acii63134.2024.00041 · Cited by 15
Does ChatGPT simplify texts like expert teachers? Linguistic features of simplified texts
Liu, F., Lu, X., Jin, T., Kang, M., & Zhang, H. S. (2025) · Reading and Writing · doi:10.1007/s11145-025-10676-2 · Cited by 6
Narratives of Collective Action in YouTube’s Discourse on Veganism
Pera, A., & Aiello, L. M. (2024) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v18i1.31384 · Cited by 12
Law, T. L., & Roberto, E. (2025) · Sociological Methods & Research · doi:10.1177/00491241251339673 · Cited by 11
The Strong Pull of Prior Knowledge in Large Language Models and Its Impact on Emotion Recognition
Chochlakis, G., Potamianos, A., Lerman, K., & Narayanan, S. (2024) · arXiv · doi:10.48550/arxiv.2403.17125 · Cited by 5
AI Pattern Recognition and its Features
Individual Researcher, E., & Bansal, P. (2025) · International Journal of Engineering and Advanced Technology · doi:10.35940/ijeat.c4562.14030225 · Cited by 5
Lin, Z. (2026) · Annual Review of Psychology · doi:10.1146/annurev-psych-100925-034807 · Cited by 4
Configurational impacts of government policies on electric vehicle diffusion: A global analysis
Yang, C., Qian, L., & Liu, M. (2025) · Transportation Research Part D Transport and Environment · doi:10.1016/j.trd.2025.105144 · Cited by 5
Lin, J., Chen, C., Feng, T., Huo, S. G., Zhang, K., Dong, B., Xiang, S., Wang, K., & Huang, L. (2026) · Landscape and Urban Planning · doi:10.1016/j.landurbplan.2026.105602 · Cited by 5
Yang, G., Su, Y., Zhao, M., Li, C., & Wu, C. (2026) · Cities · doi:10.1016/j.cities.2026.107227 · Cited by 5
ILTS: Inducing Intention Propagation in Decentralized Multi-Agent Tasks with Large Language Models
Qiu, X., Wang, H., Tan, X., & Qu, C. (2024) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3627673.3679942 · Cited by 7
Public attitudes towards social media field experiments
Straub, V. J., Burton, J. W., Geers, M., & Lorenz-Spreen, P. (2024) · Scientific Reports · doi:10.1038/s41598-024-76948-z · Cited by 5
MacGeorge, R. B. (2024) · World Futures Review · doi:10.1177/19467567251330210 · Cited by 6
Maranca, A. R. P., Chung, J., Hinck, M., Wolsky, A. D., Egami, N., & Stewart, B. (2025) · Sociological Methods & Research · doi:10.1177/00491241251333372 · Cited by 19
Bao, H., Zhang, J., Cao, M., & Evans, J. A. (2025) · International World Wide Web Conference (WWW) · doi:10.1145/3701716.3715502 · Cited by 6
Applications of GPT in Political Science Research: Extracting Information from Unstructured Text
Lee, K., Paci, S., Park, J., You, H. Y., & Zheng, S. (2025) · PS Political Science & Politics · doi:10.1017/s1049096525000046 · Cited by 8
Bai, S. Y., & Lee, E. W. J. (2024) · Frontiers in Public Health · doi:10.3389/fpubh.2024.1411345 · Cited by 4
Chochlakis, G., Pandiyan, N. M., Lerman, K., & Narayanan, S. S. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10887804 · Cited by 21
AI-Empowered Human Research Integrating Brain Science and Social Sciences Insights
Xiong, F., Yu, X., & Leong, H. W. (2024) · International Conference on Intelligent Education and Intelligent Research (IEIR) · doi:10.1109/ieir62538.2024.10960181 · Cited by 8
SkillScope: A Tool to Predict Fine-Grained Skills Needed to Solve Issues on GitHub
Carter, B. C., Contreras, J. R., Villegas, C. A. L., Acharya, P., Utzerath, J., Farner, A. O., Jenkins, H., Johnson, D., Penney, J., Steinmacher, I., et al. (2025) · IEEE/ACM International Workshop on Natural Language-Based Software Engineering (NLBSE) · doi:10.1109/nlbse66842.2025.00007 · Cited by 5
Henry, J. A. (2025) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2025.1496948 · Cited by 4
Schepens, J. J., Woloszyn, H., Marx, N., & Gagl, B. (2023) · PsyArXiv (OSF Preprints) · doi:10.31234/osf.io/gm9b6 · Cited by 10
Lu, T., Hu, J., & Chen, P. (2024) · doi:10.36227/techrxiv.171742386.68305769/v1 · Cited by 33
Xiao, B., Yin, Z., & Shan, Z. (2023) · arXiv · doi:10.48550/arxiv.2311.06957 · Cited by 4
“This potential has attracted attention in computational social science [10].”
BackgroundMethodGPT-4o for Visual Political Communication: Toward Automated Image Type Analysis
Achmann-Denkler, M., Haim, M., & Wolff, C. G. (2025) · ACM Web Science Conference (WebSci) · doi:10.1145/3717867.3717881 · Cited by 4
Understanding the Effects of Explaining Predictive but Unintuitive Features in Human-XAI Interaction
Qu, J., Arguello, J., & Wang, Y. (2025) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3715275.3732021 · Cited by 7
A bias towards neutrality? How LLM guardrail sensitivity affects classification
Rogers, R., & Zhang, X. (2025) · Communication and Change · doi:10.1007/s44382-025-00013-0 · Cited by 10
Understanding Large Language Model Driven Social Bots: A Behavioral Analysis and Impact Assessment
Li, S., Yang, J., Zhao, K., & Jia, D. (2025) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2025.3605278 · Cited by 70
Exploring the Human-LLM Synergy in Advancing Theory-driven Qualitative Analysis
Meng, H., Yang, Y., Fu, W., Lee, J., Li, Y., & Lee, Y. (2026) · ACM Transactions on Computer-Human Interaction · doi:10.1145/3778354 · Cited by 39
Suh, J., Le, L., Shayegani, E., Ramos, G., Amores, J., Ong, D. C., Czerwinski, M. P., & Hernandez, J. (2026) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2026.3656531 · Cited by 18
Semantic stability protocol: intercoder reliability for zero-shot classification via AI coders
Hsu, H.-Y., & Hsu, M. (2026) · Quality & Quantity · doi:10.1007/s11135-026-02832-9 · Cited by 4
Mining for Meaning : using computational text analysis for social inquiry
Bodell, M. H. (2024) · Institute for Analytical Sociology dissertation series · doi:10.3384/9789180756181 · Cited by 5
Reinforcement Learning with Large Language Models (LLMs) Interaction for Network Services
Du, H., Zhang, R., Niyato, D. T., Kang, J., Xiong, Z., & Kim, D. I. (2024) · 2012 International Conference on Computing, Networking and Communications (ICNC) · doi:10.1109/icnc59896.2024.10555960 · Cited by 8
Yuan, R., Hao, W., & Yuan, C. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-78104-9_24 · Cited by 2
Measuring criticism of the police in the local news media using large language models
Crowl, L., Dutta, S., KhudaBukhsh, A. R., Severnini, E., & Nagin, D. S. (2025) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2418821122 · Cited by 9
Large language models for identifying social determinants of health
Wang, Y. (2025) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2501506122 · Cited by 3
Stromer‐Galley, J., McKernan, B., Zaman, S., Maganur, C., & Regmi, S. (2025) · Social Science Computer Review · doi:10.1177/08944393251334977 · Cited by 10
Farr, D. T., Ng, L. H. X., Cruickshank, I. J., Manzonelli, N., Clark, N., Starbird, K., Bastian, N. D., & West, J. D. (2025) · IEEE Access · doi:10.1109/access.2025.3585414 · Cited by 3
Applying large language models to extract information from crop trait prioritization studies
Farmer, E. E., Brown, D., Gore, M. A., & Tufan, H. (2025) · Plants People Planet · doi:10.1002/ppp3.70075 · Cited by 4
Chen, H., Wang, Z., & Ren, M. (2025) · Data and Information Management · doi:10.1016/j.dim.2025.100107 · Cited by 13
Paiva, I. C., & Diecke, J. (2024) · Journal of Cultural Analytics · doi:10.22148/001c.118497 · Cited by 4
Ha, T. (2024) · IEEE Access · doi:10.1109/access.2024.3488903 · Cited by 3
Evaluating Human-Large Language Model Alignment in Group Process
He, Y., Liu, Y., Ouyang, C., Liu, H., Han, W., Gao, Y., Zhu, C., Tang, Y., Zhong, J., Zhou, S., et al. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-9434-8_32 · Cited by 4
Wu, X., Whittington, D., Chen, Y. J., & Zuo, R. (2024) · Journal of Asian Public Policy · doi:10.1080/17516234.2024.2425874 · Cited by 5
Understanding Student Sentiment on Mental Health Support in Colleges Using Large Language Models
Sood, P., He, C., Gupta, D., Ning, Y., & Wang, P. (2024) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata62323.2024.10826043 · Cited by 6
Liu, G., Bono, C. A., & Pierri, F. (2025) · PeerJ Computer Science · doi:10.7717/peerj-cs.2694 · Cited by 14
Bao, H., He, K., Wang, Y., & Gao, Z. (2025) · Cognitive Computation · doi:10.1007/s12559-025-10466-6 · Cited by 4
Updating “The Future of Coding”: Qualitative Coding with Generative Large Language ModelsPreprint
Than, N., Fan, L., Law, T. L., Nelson, L. K., & McCall, L. (2024) · SocArXiv (OSF Preprints) · doi:10.31235/osf.io/wg82k · Cited by 4
Large language models struggle with ethnographic text annotation
Goodall, L. S., Shilton, D., Mullins, D. A., & Whitehouse, H. (2026) · arXiv · doi:10.48550/arxiv.2601.12099 · Cited by 3
Breuer, J. (2023) · AI critique · doi:10.1515/9783839467664-014 · Cited by 4
Collaborative Growth: When Large Language Models Meet Sociolinguistics
Nguyen, D. (2025) · Language and Linguistics Compass · doi:10.1111/lnc3.70010 · Cited by 17
GenAI vs. Human Fact-Checkers: Accurate Ratings, Flawed Rationales
Tai, Y. C., Patni, K. N., Hemauer, N., Desmarais, B. A., & Lin, Y. (2025) · ACM Web Science Conference (WebSci) · doi:10.1145/3717867.3717896 · Cited by 7
Metadata
- Authors
- Ziems, C., Held, W., Shaikh, O., Chen, J., Zhang, Z., & Yang, D.
- Affiliations
- Stanford University (US)
- Georgia Institute of Technology (US)
- Dartmouth College (US)
- Venue
- Computational Linguistics
- Publisher
- MIT Press
- Published
- 2024
- Volume
- 50
- Issue
- 1
- Pages
- 237-291
- ISSN
- 0891-2017 (ISSN-L)
- 1530-9312
- OpenAlex
- W4389636360
- Semantic Scholar
- 93752cae0d4ecd2d09d6660feb3c1860af973f18
- Cited by
- 585
- References
- 311
- Citations by year
- 2026: 201 · 2025: 197 · 2024: 146
- FWCI
- 271.63
- Type
- journal article
- Language
- en
- Open access
- diamond
- doi.org
- Licence
- Locations
- Computational Linguistics (publishedVersion, cc-by-nc-nd)
- arXiv (Cornell University) (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- arXiv (Cornell University)
- Funders
- National Science Foundation (2247357, 2308994, 2039655)
- Topics
- Social Sciences › General Social Sciences › Computational and Text Analysis Methods
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Sentiment Analysis and Opinion Mining
- Keywords
- large language models, computational social science, zero-shot learning, persuasion detection, text classification, text generation, manual annotation, evaluation pipeline
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-11-21, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-11-21 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.