The DOI matches its Crossref record; 53 of the 53 references it cites were found in a registry or an index.
Analyzing Polarization in Social Media: Method and Application to Tweets on 21 Mass Shootings
Open accessAbstract
Dorottya Demszky, Nikhil Garg, Rob Voigt, James Zou, Jesse Shapiro, Matthew Gentzkow, Dan Jurafsky. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). 2019.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The text we found for this paper looks like another document, so the self-check wasn’t run.
Citations
Cites
Glove: Global Vectors for Word Representation
Pennington, J., Socher, R., & Manning, C. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1162 · Cited by 34,071 · cited 2×
“Train GloVe embeddings (Pennington et al., 2014) on V based on 11-50k random samples of tweets from each event.”
BackgroundMethodAustin, J. L. (1975) · doi:10.1093/acprof:oso/9780198245537.001.0001 · Cited by 21,496
Critical race theory: an introduction
Delgado, R., Stefancic, J., & Harris, A. (2013) · Choice Reviews Online · doi:10.5860/choice.50-2938 · Cited by 5,992
Exposure to ideologically diverse news and opinion on Facebook
Bakshy, E., Messing, S., & Adamic, L. A. (2015) · Science · doi:10.1126/science.aaa1160 · Cited by 3,245 · cited 3×
“com/ddemszky/framing-twitter 2016) and Facebook (Bakshy et al., 2015).”
BackgroundIyengar, S., Sood, G., & Lelkes, Y. (2012) · Public Opinion Quarterly · doi:10.1093/poq/nfs038 · Cited by 2,996 · cited 1×
“, 2009), and so emotional expression represents another semantic layer relevant to polarization (Iyengar et al., 2012; Suhay, 2015).”
Background(2009) · Cited by 1,900
Political Polarization in the American Public
Fiorina, M. P., & Abrams, S. J. (2008) · Annual Review of Political Science · doi:10.1146/annurev.polisci.11.053106.153836 · Cited by 1,798 · cited 1×
“, forthcoming), and the propagation of partisan frames can influence public opinion (Chong and Druckman, 2007) and party identification (Fiorina and Abrams, 2008).”
BackgroundFraming Bias: Media in the Distribution of Power
Entman, R. M. (2007) · Journal of Communication · doi:10.1111/j.1460-2466.2006.00336.x · Cited by 1,781 · cited 1×
“The strategy of highlighting particular aspects within topics as a means of framing (Entman, 2007) has also been quantified in the NLP literature (Boydstun et al.”
BackgroundPolitical Polarization on Twitter
Conover, M., Ratkiewicz, J., Francisco, M., Goncalves, B., Flammini, A., & Menczer, F. (2011) · Zenodo · doi:10.5281/zenodo.4589064 · Cited by 1,254
A biterm topic model for short texts
Yan, X., Guo, J., Lan, Y., & Cheng, X. (2013) · International World Wide Web Conference (WWW) · doi:10.1145/2488388.2488514 · Cited by 1,165 · cited 3×
“We build on the ability of vector space models to represent higher-level semantics to develop our own embedding-based topic assignment approach, comparing it with two traditional LDAbased methods: MALLET8 and the Biterm Topic Model (BTM) (Yan et al., 2013); BTM was developed specifically for tweets.”
MethodInfluential
Research works printed but not linked: 3
- Analyzing Polarization in Social Media: Method and Application to Tweets on 21 Mass Shootings https://aclanthology.org/N19-1304/ (Demszky et al., NAACL 2019)
- Analyzing Polarization in Social Media: Method and Application to Tweets on 21 Mass Shootings (Demszky et al., NAACL 2019)
- ACL materials are Copyright © 1963–2026 ACL; other materials are copyrighted by their respective copyright holders. Materials prior to 2016 here are licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 3.0 International License. Permission is granted to make copies for the purposes of teaching and research. Materials published in or after 2016 are licensed on a Creative Commons Attribution 4.0 International License.
Cited by
Sorted by citations
Items 101–164 of 164
Conversational Inequality Through the Lens of Political Interruption
Yoo, C. H., Wang, J., Luo, Y., Khadilkar, K., & KhudaBukhsh, A. R. (2022) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2022/724 · Cited by 3
“Multiple research disciplines have analyzed this growing political polarization [Poole and Rosenthal, 1984; Demszky et al., 2019; KhudaBukhsh et al., 2021] with several studies analyzing its manifestation in mainstream news media [Hyun and Moon, 2016; KhudaBukhsh et al., 2021; KhudaBukhsh et al.,…”
BackgroundLanguage and Factional Polarity in the Movement for Democratic Change in Zimbabwe
Sithole, E. (2022) · Journal of Asian and African Studies · doi:10.1177/00219096221137670 · Cited by 3
“Words have direct implications on race, class, sex, gender, and ethnicity (Demszky et al., 2019).”
BackgroundMore than Votes? Voting and Language based Partisanship in the US Supreme Court
Fang, B., Cohn, T., Baldwin, T., & Frermann, L. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.306 · Cited by 2
Disengaging from Reality: Online Behavior and Unpleasant Political NewsPreprint
D'Amico, L., & Tabellini, G. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4305223 · Cited by 3
Grisham, E. L., Dashtgard, P., Relihan, D. P., Holman, E. A., & Silver, R. C. (2023) · Personality and Social Psychology Bulletin · doi:10.1177/01461672231185605 · Cited by 1
“That is, Republicans concentrated more on the shooter and news updates, whereas Democrats focused on the victims and advocated for policy changes (Demszky et al., 2019).”
Awais, M., & Gharaibeh, F. A. (2025) · Women s Studies International Forum · doi:10.1016/j.wsif.2025.103219 · Cited by 1
Krupenkin, M., Zhu, K., Walker, D., & Rothschild, D. M. (2022) · Journal of Quantitative Description Digital Media · doi:10.51685/jqd.2022.011 · Cited by 1
“, how much the terms differ) within a topic (Gentzkow et al., 2019; Demszky et al., 2019).”
BackgroundMethodInfluentialTheory-Grounded Computational Text Analysis
McCarthy, A. D., & Dore, G. M. D. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-short.136 · Cited by 2
“Descriptive papers may refer to social science theories or make generalizable claims, as when Demszky et al. (2019) write, “The shooter’s race appears to play a role in topic preference: if the shooter is white, Democrats become more likely to focus on shooter’s identity,” but they do not link to…”
BackgroundA Transfer Learning Analysis of Political Leaning Classification in Cross-domain Content
Caled, D., & Silva, M. J. (2022) · Lecture notes in computer science · doi:10.1007/978-3-030-98305-5_25 · Cited by 1
Understanding Misinformation About COVID-19 in WhatsApp Messages
Martins, A. D. F., Monteiro, J. M., & Machado, J. C. (2022) · Communications in computer and information science · doi:10.1007/978-3-031-15743-1_2 · Cited by 1
Automatically Inferring Gender Associations from LanguagePreprint
Chang, S. Y., & McKeown, K. R. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.00091 · Cited by 1
“Clustering word embeddings has proven useful for discovering salient patterns in text corpora (Wilson et al., 2018; Demszky et al., 2019).”
BackgroundKnowBias: Detecting Political Polarity in Long Text ContentPreprint
Saligrama, A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.12230 · Cited by 1
“While tweets have been analyzed for political sentiment (Demszky et al. 2019), no research has focused on domain adaptation from short to long text in this context.”
BackgroundBrunila, M., Zhao, R., Mircea, A., Lumley, S., & Sieber, R. E. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.11835 · Cited by 3
“The use of embeddings for clustering in the field of crisis management has been explored by Demszky et al. (2019) using trained GloVe embed-dings.”
MethodKnowBias: Detecting Political Polarity in Long Text Content (Student Abstract)
Saligrama, A. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i10.7224
“While tweets have been analyzed for political sentiment (Demszky et al. 2019), no research has focused on domain adaptation from short to long text in this context.”
BackgroundCOVID-19 and mass-media: the weight of the words
Spulber, D. (2020) · Geopolitical, Social Security and Freedom Journal · doi:10.2478/gssfj-2020-0012
Polarization and toxicity in political discourse online
Saveski, M. (2020) · DSpace@MIT (Massachusetts Institute of Technology)
Palakodety, S., KhudaBukhsh, A. R., & Jayachandran, G. (2021) · SpringerBriefs in computer science · doi:10.1007/978-981-16-5625-5_3
Understanding Politics via Contextualized Discourse ProcessingPreprint
Pujari, R., & Goldwasser, D. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.15784 · Cited by 4
“Of late, several works attempted to solve such tasks (Iyyer et al., 2016; Han et al., 2019; Demszky et al., 2019; Kulkarni et al., 2018; PreoţiucPietro et al., 2017; Diermeier et al., 2012).”
BackgroundA Heterophily-Based Polarization Measure for Multi-community Networks
Nair, S., & Iamnitchi, A. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19097-1_32 · Cited by 1
Using Knowledge Graphs to Detect Partisanship in Online Political Discourse
Decter-Frain, A., & Barash, V. (2023) · Studies in computational intelligence · doi:10.1007/978-3-031-21127-0_5 · Cited by 1
Dore, G. M. D., McCarthy, A. D., & Scharf, J. A. (2023) · SpringerBriefs in political science · doi:10.1007/978-3-031-27584-5_4
Durrheim, K. L., & Schuld, M. (2023) · doi:10.31234/osf.io/n47xe
Towards Open-Domain Twitter User Profile Inference
Wen, H., Xiao, Z., Hovy, E., & Hauptmann, A. (2023) · Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2023.findings-acl.198 · Cited by 1
“…such as gender (Rao et al., 2011; Liu et al., 2012; Liu and Ruths, 2013; Sakaki et al., 2014), age (Rosenthal and McKeown, 2011; Sap et al., 2014; Chen et al., 2015; Fang et al., 2015; Kim et al., 2017), and political polarity (Rao et al., 2010; Al Zamal et al., 2012; Demszky et al., 2019).”
BackgroundEbeling, R., & Becker, K. E. (2023) · doi:10.5753/sbbd_estendido.2023.232220
“Tipicamente usam a ligação de parti-dos com os usuários, e exploram classes de palavras para entender posicionamentos como violência em massa [Demszky et al. 2019], violência racial [De Choudhury et al. 2016], ou ideologia política e complexidade cognitiva [Pennycook et al. 2020].”
BackgroundGoal-Directed Target Discovery in Social Network
Wu, K., Liu, J., Ma, J., et al. (2023) · International Conference on Computer Engineering and Intelligent Control (ICCEIC) · doi:10.1109/icceic60201.2023.10426688
“Most used the language-based model to classify users’ political stances from their posts [15-17].”
MethodAnttuaneth, V. (2023) · Universidad Peruana de Ciencias Aplicadas (UPC) · doi:10.19083/tesis/671503
Characterizing Online Criticism of Partisan News Media Using Weakly Supervised Learning
Shivaram, K., Bilgic, M., Shapiro, M. A., & Culotta, A. (2024) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v18i1.31400
Curated and Asymmetric Exposure: A Case Study of Partisan Talk during COVID on Twitter
An, Z., Breuhaus, J., Niu, J., Sarıyüce, A. E., & Joseph, K. (2024) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v18i1.31298
“For the term-based approach, we use the Leave-Out Estima-tor, proposed by Gentzkow, Shapiro, and Taddy (2016) and used by Demszky et al. (2019), which provides a statistical method to estimate the salience of differences in unigram usage across (e.g.) partisan lines.”
MethodPlay to your strengths: Incumbency effect and issue emphasis in Brazilian local elections
Pereira, L. (2026) · Journal of Economic Behavior & Organization · doi:10.1016/j.jebo.2026.107619
Deceptively simple: An outsider's perspective on natural language processing
KhudaBukhsh, A. R. (2024) · AI Magazine · doi:10.1002/aaai.12204
You Must Be a Trump Supporter: Political Identity Projections on the Social Web
Mittal, S., Chawla, T., & KhudaBukhsh, A. R. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-78541-2_24
Does News Coverage of Hate-motivated Mass Shootings Generate More Hatred?Preprint
Cao, A. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5098805
Blameocracy: Causal Attribution in Political CommunicationPreprint
Bilotta, F., Binetti, A., & Manferdini, G. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5211231
Gaillac, C., & L’Hour, J. (2025) · Oxford University Press eBooks · doi:10.1093/9780198918868.003.0015
Inference on heterogeneous effects
Gaillac, C., & L’Hour, J. (2025) · Oxford University Press eBooks · doi:10.1093/9780198918868.003.0008
Gaillac, C., & L’Hour, J. (2025) · Oxford University Press eBooks · doi:10.1093/9780198918868.003.0001
Generalization and methodology
Gaillac, C., & L’Hour, J. (2025) · Oxford University Press eBooks · doi:10.1093/9780198918868.003.0005
Gaillac, C., & L’Hour, J. (2025) · Oxford University Press eBooks · doi:10.1093/9780198918868.003.0014
High dimension and endogeneity
Gaillac, C., & L’Hour, J. (2025) · Oxford University Press eBooks · doi:10.1093/9780198918868.003.0006
Gaillac, C., & L’Hour, J. (2025) · Oxford University Press eBooks · doi:10.1093/9780198918868.003.0013
Gaillac, C., & L’Hour, J. (2025) · Oxford University Press eBooks · doi:10.1093/9780198918868.003.0002
Gaillac, C., & L’Hour, J. (2025) · Oxford University Press eBooks · doi:10.1093/9780198918868.002.0004
Gaillac, C., & L’Hour, J. (2025) · Oxford University Press eBooks · doi:10.1093/9780198918868.003.0007
Gaillac, C., & L’Hour, J. (2025) · Oxford University Press eBooks · doi:10.1093/9780198918868.003.0010
Gaillac, C., & L’Hour, J. (2025) · Oxford University Press eBooks · doi:10.1093/9780198918868.003.0012
Gaillac, C., & L’Hour, J. (2025) · Oxford University Press eBooks · doi:10.1093/9780198918868.002.0005
Gaillac, C., & L’Hour, J. (2025) · Oxford University Press eBooks · doi:10.1093/9780198918868.003.0009
Gaillac, C., & L’Hour, J. (2025) · Oxford University Press eBooks · doi:10.1093/9780198918868.003.0003
Gaillac, C., & L’Hour, J. (2025) · Oxford University Press eBooks · doi:10.1093/9780198918868.003.0004
Gaillac, C., & L’Hour, J. (2025) · Oxford University Press eBooks · doi:10.1093/9780198918868.003.0011
Multilingualism, Transnationality, and K-pop in the Online #StopAsianHate Movement
Masis, T., Duan, Z., Xu, W. W., et al. (2025) · ACM Web Science Conference (WebSci) · doi:10.1145/3717867.3717869
“Our use of clustering follows from the consensus that clustering embeddings with k-means has better performance than LDA topic modeling for tweets [12], and clustering contextualized embeddings has comparable or better performance than LDA [48, 51] or neural topic modeling [61] for traditional…”
Ashok, V., Vervilles, W. J. K., Kellom, K. S., et al. (2025) · doi:10.2196/preprints.80397
Firearm Violence and Health in Policymaker Discourse: Mixed Methods Social Media Analysis
Ashok, V., Vervilles, W. J. K., Kellom, K. S., et al. (2025) · JMIR Formative Research · doi:10.2196/80397
“For example, we included any post including the terms “gun(s),” “firearm(s),” “shooting(s),” AND “violence,” “safety,” etc (full list of search terms is provided in Figure 1) [43].”
Mapping social media analytics in firearm injury exposure research: a scoping review
Flynch, M., He, L., Badurak, M., & Henry, S. B. (2025) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocaf202
Social Media Post Detection using Natural Language Processing and Machine Learning Classifiers
Haque, T., Uddin, S., Mondal, T., Hasan, M. M., Rana, M. S., & Tahmiduzzaman, K. B. M. (2025) · International Conference on IoT Based Control Networks and Intelligent Systems (ICICNIS) · doi:10.1109/icicnis66685.2025.11315819
PRISM: A Framework for Multi-Level Modeling and Analysis of Polarization Knowledge
Paschalides, D., Pallis, G., & Dikaiakos, M. D. (2025) · IEEE International Conference on Knowledge Graph (ICKG) · doi:10.1109/ickg66886.2025.00049
“Within entity-level polarization, a key challenge is identifying primary entities that drive polarization by occupying central positions in the narrative landscape [9], [11], [18], [19].”
InfluentialFraming of health-related narratives in conspiracy versus mainstream media
Reiter-Haas, M., Klösch, B., Hadler, M., et al. (2026) · Behavioral Science & Policy · doi:10.1177/23794607261431053
“6 In a previous work, 7 we highlighted moral frames behind particular political viewpoints.”
Vorakitphan, V. (2021) · theses.fr (ABES) · doi:10.70675/8e4ff520za56ez4028z8581z7d87d05e0469 · Cited by 1
Anatomy of the Suburban Metropolis : Labor Earnings, Large Scale Commuting, and Social Discontent
Delemotte, T. (2022) · theses.fr (ABES) · doi:10.70675/f1575380z9444z48f6zb3c6z6b14b26b5712
Gauthier, G. (2023) · theses.fr (ABES) · doi:10.70675/950f4696z6651z4992z895az1f9ded1c545b
Unintended politics: Opinion expression and incivility in incidental political discussion
Fan, Y., Hill, B. M., & Moy, P. (2026) · New Media & Society · doi:10.1177/14614448261441875
Durrheim, K., & Schuld, M. (2025) · Political Psychology · doi:10.1111/pops.70000 · Cited by 8
“…communities focus the attention of different topics and concerns, frame issues differently, vary in their sentiments (e.g., Alamsyah et al., 2024; Demszky et al., 2019; Falkenberg et al., 2022; Karjus & Cuskley, 2024; KhudaBukhsh et al., 2021; Kutlu et al., 2019; Ojea Quintana et al., 2022;…”
Metadata
- Authors
- Demszky, D., Garg, N., Voigt, R., Zou, J., Shapiro, J., Gentzkow, M., & Jurafsky, D.
- Affiliations
- Stanford University (US)
- Brown University (US)
- Venue
- Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
- Published
- 2019
- Pages
- 2970-3005
- OpenAlex
- W2963834345
- Semantic Scholar
- 3475876c3f5e624587181744bc5acf4223aecd00
- Cited by
- 164
- References
- 52
- Citations by year
- 2026: 3 · 2025: 35 · 2024: 10 · 2023: 24 · 2022: 35 · 2021: 29 · 2020: 22 · 2019: 6
- FWCI
- 9.21
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) (publishedVersion, cc-by)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Sentiment Analysis and Opinion Mining
- Physical Sciences › Computer Science › Artificial Intelligence › Hate Speech and Cyberbullying Detection
- Social Sciences › Communication › Social Media and Politics
- Keywords
- polarization, social media, tweets, mass shootings, sentiment analysis, political polarization, online discourse
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 second model labelled each claim on 2026-10-13 (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
