Classifying latent user attributes in twitter
Abstract
Social media outlets such as Twitter have become an important forum for peer interaction. Thus the ability to classify latent user attributes, including gender, age, regional origin, and political orientation solely from Twitter user language or similar highly informal content has important applications in advertising, personalization, and recommendation. This paper includes a novel investigation of stacked-SVM-based classification algorithms over a rich set of original features, applied to classifying these four user attributes. It also includes extensive analysis of features and approaches that are effective and not effective in classifying user attributes in Twitter-style informal written genres as distinct from the other primarily spoken genres previously studied in the user-property classification literature. Our models, singly and in ensemble, significantly outperform baseline models in all cases. A detailed analysis of model components and features provides an often entertaining insight into distinctive language-usage variation across gender, age, regional origin and political orientation in modern informal communication.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
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?
Multiple studies report that emoticons are used more often by females, but Huffaker & Calvert found males use them more in a sample of 100 teenage bloggers.
“For example, multiple studies report that emoticons (i.e. ‘:)’ ‘:-(‘) are used more often by females [34], [36], [38], but Huffaker & Calvert found males use them more in a sample of 100 teenage bloggers [39].”
From Personality, Gender, and Age in the Language of Social Media: The Open-Vocabulary Approach (2013) · cites this paper as [36]
Cites
The Social Stratification of English in New York City.
Crockett, H. J., & Labov, W. (1968) · American Sociological Review · doi:10.2307/2092899 · Cited by 3,091 · see citing works
Eckert, P., & McConnell‐Ginet, S. (2013) · Cambridge University Press eBooks · doi:10.1017/cbo9781139245883 · Cited by 1,454 · see citing works
Learning to Classify Text Using Support Vector Machines
Joachims, T. (2002) · Springer eBooks · doi:10.1007/978-1-4615-0907-3 · Cited by 1,379 · see citing works
Learning to Classify Text Using Support Vector Machines: Methods, Theory and Algorithms
Joachims, T. (2002) · Cited by 933 · see citing works
Eckert, P., & McConnell‐Ginet, S. (2003) · Cambridge University Press eBooks · doi:10.1017/cbo9780511791147 · Cited by 802 · see citing works
Coates, J. (2011) · Cited by 742 · see citing works
Social Influences on the Choice of a Linguistic Variant
Fischer, J. L. (1958) · WORD · doi:10.1080/00437956.1958.11659655 · Cited by 502 · see citing works
Thomas, M., Pang, B., & Lee, L. (2006) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/1610075.1610122 · Cited by 497 · see citing works
Gender and genre variation in weblogs
Herring, S. C., & Paolillo, J. C. (2006) · Journal of Sociolinguistics · doi:10.1111/j.1467-9841.2006.00287.x · Cited by 407 · see citing works
(1922) · doi:10.1093/library/s4-iii.1.66 · Cited by 164 · see citing works
Talk that Counts: Age, Gender, and Social Class Differences in Discourse
Macaulay, R. K. S. (2005) · Cited by 119 · see citing works
Modeling latent biographic attributes in conversational genres
Garera, N., & Yarowsky, D. (2009) · doi:10.3115/1690219.1690245 · Cited by 92 · see citing works
Self-citationThe Identity of Bloggers: Openness and Gender in Personal Weblogs.
Nowson, S., & Oberlander, J. (2006) · Cited by 91 · see citing works
An Exploration of Observable Features Related to Blogger Age.
Burger, J. D., & Henderson, J. C. (2006) · Cited by 63 · see citing works
A quantitative analysis of lexical differences between genders in telephone conversations
Boulis, C., & Ostendorf, M. (2005) · Annual Meeting of the Association for Computational Linguistics (ACL) · doi:10.3115/1219840.1219894 · Cited by 58 · see citing works
A pilot study on gender differences in conversational speech on lexical in richness measures
Singh, S. (2001) · Literary and Linguistic Computing · doi:10.1093/llc/16.3.251 · Cited by 47 · see citing works
Bocklet, T., Maier, A., & Nöth, E. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-87391-4_33 · Cited by 22 · see citing works
Computational approaches to analyzing weblogs : papers from the AAAI Spring Symposium
Nicolov, N., Salvetti, F., Liberman, M. Y., et al. (2006) · AAAI Press eBooks · Cited by 21 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Personality, Gender, and Age in the Language of Social Media: The Open-Vocabulary Approach
Schwartz, H. A., Eichstaedt, J. C., Kern, M. L., Dziurzynski, L., Ramones, S. M., Agrawal, M., Shah, A., Kosinski, M., Stillwell, D., Seligman, M. E. P., et al. (2013) · PLoS ONE · doi:10.1371/journal.pone.0073791 · Cited by 1,700 · see citing works
Social Data: Biases, Methodological Pitfalls, and Ethical Boundaries
Olteanu, A., Castillo, C., Diaz, F., & Kıcıman, E. (2019) · Frontiers in Big Data · doi:10.3389/fdata.2019.00013 · Cited by 763 · see citing works
“For instance, using data samples biased toward users whose gender (Rao et al., 2010) or political identity (Cohen and Ruths, 2013) are easy to discern, leads to overoptimistic performance estimations that do not reflect those obtained on balanced or representative samples) (Cohen and Ruths, 2013;…”
BackgroundMethod” How old do you think I am?” A study of language and age in Twitter
Nguyen, D., Gravel, R., Trieschnigg, D., & Meder, T. (2021) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v7i1.14381 · Cited by 287 · see citing works
Studying user income through language, behaviour and affect in social media
Preoţiuc-Pietro, D., Volkova, S., Lampos, V., Bachrach, Y., & Aletras, N. (2015) · PLOS ONE · doi:10.1371/journal.pone.0138717 · Cited by 219 · see citing works
Gender as a Variable in Natural-Language Processing: Ethical Considerations
Larson, B. (2017) · Proceedings of the First ACL Workshop on Ethics in Natural Language Processing · doi:10.18653/v1/w17-1601 · Cited by 111 · see citing works
Social Data: Biases, Methodological Pitfalls, and Ethical Boundaries
Olteanu, A., Castillo, C., Diaz, F., & Kiciman, E. (2016) · doi:10.2139/ssrn.2886526 · Cited by 763 · see citing works
Rossi, R., Nairn, A., Smith, J., & Inskip, C. (2021) · Journal of Public Policy & Marketing · doi:10.1177/0743915621999674 · Cited by 50 · see citing works
Same Author or Just Same Topic? Towards Content-Independent Style Representations
Wegmann, A., Schraagen, M., & Nguyen, D. (2022) · arXiv · doi:10.48550/arxiv.2204.04907 · Cited by 25
A socialbots analysis-driven graph-based approach for identifying coordinated campaigns in twitter
Fazil, M., & Abulaish, M. (2020) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-182895 · Cited by 14 · see citing works
- Authors
- Rao, D., Yarowsky, D., Shreevats, A., & Gupta, M.
- Affiliations
- Johns Hopkins University (US)
- ORCID
- Rao, Delip
- Venue
- Proceedings of the 2nd international workshop on Search and mining user-generated contents
- Publisher
- ACM
- Published
- 2010-10-30
- Pages
- 37-44
- OpenAlex
- W2017729405
- Cited by
- 655
- References
- 18
- Citations by year
- 2026: 9 · 2025: 9 · 2024: 18 · 2023: 13 · 2022: 24 · 2021: 40 · 2020: 48 · 2019: 59 · 2018: 60 · 2017: 77 · 2016: 85 · 2015: 72 · 2014: 78 · 2013: 42 · 2012: 15
- FWCI
- 16.25
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- International Workshop on Search and Mining User-Generated Contents (SMUC) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Authorship Attribution and Profiling
- Social Sciences › Psychology › Social Psychology › Mental Health via Writing
- Physical Sciences › Computer Science › Human-Computer Interaction › Digital Communication and Language
- Keywords
- Twitter, gender classification, age estimation, regional origin, political orientation, ensemble learning, feature analysis
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.
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
