---
title: "Demographic Factors Improve Classification — Hovy 2015"
description: "The paper asks whether NLP needs \"demographic adaptation\" in the way it already uses domain adaptation."
authors: ["Dirk Hovy"]
year: 2015
venue: "Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)"
source: "https://aclanthology.org/P15-1073/"
doi: "10.3115/v1/p15-1073"
licence: "CC BY-NC-SA 3.0 (ACL Anthology, before 2016)"
licence_url: "https://creativecommons.org/licenses/by-nc-sa/3.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/hovy-2015-demographic-factors-improve-classification-performance/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/hovy-2015-demographic-factors-improve-classification-performance/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2015](https://md.research.elamur.ai/free/en/papers/2015/) / Demographic Factors Improve Classification Performance

# Demographic Factors Improve Classification Performance

**Authors:** [Dirk Hovy](https://md.research.elamur.ai/free/en/authors/dirk-hovy/) · **Year:** 2015 · **Venue:** Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · **Licence:** [CC BY-NC-SA 3.0 (ACL Anthology, before 2016)](https://creativecommons.org/licenses/by-nc-sa/3.0/)

**Links:** [Publisher's page](https://aclanthology.org/P15-1073/) · [PDF](https://aclanthology.org/P15-1073.pdf) · [DOI 10.3115/v1/p15-1073](https://doi.org/10.3115/v1/p15-1073) · [OpenAlex](https://openalex.org/W2252241921)

**Citations:** 146 citations (openalex-snapshot · 2026-10-14) · [98](#cited-by) in our library, of the 140884 papers whose bibliographies we read

## Summary
The paper asks whether NLP needs "demographic adaptation" in the way it already uses domain adaptation. Most models treat language as uniform, yet speakers' age and gender shape word choice and meaning. This matters especially for social media and review text, where author profiles are often available. Using reviews from Trustpilot in five countries (Denmark, France, Germany, UK, US), the author trains separate word2vec embeddings for male vs. female authors and for under-35 vs. over-45 authors. As the demographic-agnostic baseline, he also trains embeddings on a size-matched mixed corpus. These embeddings feed off-the-shelf classifiers with default settings for three tasks: sentiment analysis, topic identification, and author attribute prediction. Models that are aware of the demographic group beat agnostic ones in F1 consistently, though by small margins, and 8 of 30 comparisons reach significance. Gender gives larger gains than age. The work suggests that systems ignoring demographics lose accuracy and may systematically underserve groups whose language differs from the norm.

## Key points
- Data comes from Trustpilot reviews and profiles in five countries. The UK has the most users (about 1,424k). Denmark has unusually rich profile information.
- Missing gender values were filled in from first names. A name was used only if one gender covered 95% of its mentions and it had at least 3 attributed instances.
- Embeddings were trained with word2vec using skip-gram and hierarchical softmax. There is one model per subgroup plus a mixed model built from half of each subgroup's corpus, and all three corpora are balanced to equal size.
- Each task's labeled data is split 60:40 into train and test, with no development tuning.
  - Sentiment uses 1, 3, and 5 star ratings, with balanced labels.
  - Author attribute identification predicts age from gender-conditioned embeddings, and gender from age-conditioned ones.
- Demographic-aware models improve F1 across all tasks and languages. Gains are small, and 8/30 are significant at p \< 0.05 by bootstrap sampling. Age helps less than gender.

## Interesting ideas
- **Group-specific embeddings instead of explicit features.** Training a separate representation per population lets a standard pipeline absorb group differences without redesigning the model. The same trick could apply to regional dialects or user communities.
- **Size-balanced control corpus.** The "mixed" baseline is built from equal halves of each subgroup and matched in size. Any gain can then be attributed to group conditioning rather than to having more data, which is a clean ablation design for many comparison studies.
- **Deliberately simple, untuned models.** The paper uses default classifiers and general-purpose rather than task-specific embeddings. This isolates the effect of one factor and lowers the risk of overfitting the comparison, so it works well when the goal is measuring relative rather than absolute performance.
- **Balancing labels to remove confounds.** Women and older reviewers tend to give higher ratings, so sentiment classes are balanced per group. Without this, models could exploit group-specific label priors and inflate apparent gains.
- **Filtered name-based gender imputation.** Missing gender is inferred from first names only when the evidence is strong (a clear majority and minimum support). This is a cheap way to extend metadata coverage in other user-generated corpora.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

Fields: [Natural language processing](https://md.research.elamur.ai/free/en/shelves/nlp/)

## Cited by

Cited by

98 papers of our library cite it (of the 140884 whose bibliographies we read); 11 of them have a page here, 87 not yet.

- [Identifying and Reducing Gender Bias in Word-Level Language Models](https://md.research.elamur.ai/free/en/papers/bordia-2019-identifying-reducing-gender-bias-word/)
- [Toward Gender-Inclusive Coreference Resolution](https://md.research.elamur.ai/free/en/papers/cao-2020-gender-inclusive-coreference-resolution/)
- [Toward Gender-Inclusive Coreference Resolution: An Analysis of Gender and Bias Throughout the Machine Learning Lifecycle*](https://md.research.elamur.ai/free/en/papers/cao-2021-gender-inclusive-coreference-resolution-analysis/)
- [CONAN - COunter NArratives through Nichesourcing: a Multilingual Dataset of Responses to Fight Online Hate Speech](https://md.research.elamur.ai/free/en/papers/chung-2019-conan-counter-narratives-through-nichesourcing/)
- [Inducing Domain-Specific Sentiment Lexicons from Unlabeled Corpora](https://md.research.elamur.ai/free/en/papers/hamilton-2016-inducing-domain-specific-sentiment-lexicons/)
- [The Social Impact of Natural Language Processing](https://md.research.elamur.ai/free/en/papers/hovy-2016-social-impact-natural-language-processing/)
- [The Importance of Modeling Social Factors of Language: Theory and Practice](https://md.research.elamur.ai/free/en/papers/hovy-2021-importance-modeling-social-factors-language/)
- [Examining Gender and Race Bias in Two Hundred Sentiment Analysis Systems](https://md.research.elamur.ai/free/en/papers/kiritchenko-2018-examining-gender-race-bias-two/)
- [Neural Unsupervised Domain Adaptation in NLP–-A Survey](https://md.research.elamur.ai/free/en/papers/ramponi-2020-neural-unsupervised-domain-adaptation-nlp/)
- [SemEval-2017 Task 4: Sentiment Analysis in Twitter](https://md.research.elamur.ai/free/en/papers/rosenthal-2017-semeval-2017-task-4-sentiment/)
- [Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview](https://md.research.elamur.ai/free/en/papers/shah-2019-predictive-biases-natural-language-processing/)

## Cite

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{hovy2015demographic,
  title = {{Demographic Factors Improve Classification Performance}},
  author = {Hovy, Dirk},
  booktitle = {Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)},
  year = {2015},
  doi = {10.3115/v1/p15-1073},
  url = {https://doi.org/10.3115/v1/p15-1073}
}
```

- [← previous Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://md.research.elamur.ai/free/en/papers/sohl-2015-dickstein-deep-unsupervised-learning-using-nonequilibrium/)
- [next → Dialog Act Annotation for Twitter Conversations](https://md.research.elamur.ai/free/en/papers/zarisheva-2015-dialog-act-annotation-twitter-conversations/)
- [↑ back to papers of 2015](https://md.research.elamur.ai/free/en/papers/2015/)

## References

48 references, 5 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Jalal S Alowibdi, Ugo A Buy, and Philip Yu. 2013. Empirical evaluation of profile characteristics for gender classification on twitter. In Machine Learning and Applications (ICMLA), 2013 12th International Conference on, volume 1, pages 365–369. IEEE. [find](https://scholar.google.com/scholar?q=Jalal+S+Alowibdi%2C+Ugo+A+Buy%2C+and+Philip+Yu%2E+2013%2E+Empirical+evaluation+of+profile+characteristics+for+gender+classification+on+twitter%2E+In+Machine+Learning+and+Applications+%28ICMLA%29%2C+2013+12th+Internat)
2. David Bamman, Chris Dyer, and Noah A. Smith. 2014a. Distributed representations of geographically situated language. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, pages 828–834. Proceedings of ACL. [find](https://scholar.google.com/scholar?q=David+Bamman%2C+Chris+Dyer%2C+and+Noah+A%2E+Smith%2E+2014a%2E+Distributed+representations+of+geographically+situated+language%2E+In+Proceedings+of+the+52nd+Annual+Meeting+of+the+Association+for+Computational+Ling)
3. David Bamman, Jacob Eisenstein, and Tyler Schnoebelen. 2014b. Gender identity and lexical variation in social media. Journal of Sociolinguistics, 18(2):135–160. [find](https://scholar.google.com/scholar?q=David+Bamman%2C+Jacob+Eisenstein%2C+and+Tyler+Schnoebelen%2E+2014b%2E+Gender+identity+and+lexical+variation+in+social+media%2E+Journal+of+Sociolinguistics%2C+18%282%29%3A135%E2%80%93160%2E)
4. Federica Barbieri. 2008. Patterns of age-based linguistic variation in American English. Journal of sociolinguistics, 12(1):58–88. [find](https://scholar.google.com/scholar?q=Federica+Barbieri%2E+2008%2E+Patterns+of+age%2Dbased+linguistic+variation+in+American+English%2E+Journal+of+sociolinguistics%2C+12%281%29%3A58%E2%80%9388%2E)
5. Andrew J Barke. 2000. The Effect of Age on the Style of Discourse among Japanese Women. In Proceedings of the 14th Pacific Asia Conference on Language, Information and Computation, pages 23–34. [find](https://scholar.google.com/scholar?q=Andrew+J+Barke%2E+2000%2E+The+Effect+of+Age+on+the+Style+of+Discourse+among+Japanese+Women%2E+In+Proceedings+of+the+14th+Pacific+Asia+Conference+on+Language%2C+Information+and+Computation%2C+pages+23%E2%80%9334%2E)
6. Taylor Berg-Kirkpatrick, David Burkett, and Dan Klein. 2012. An empirical investigation of statistical significance in NLP. In Proceedings of EMNLP. [find](https://scholar.google.com/scholar?q=Taylor+Berg%2DKirkpatrick%2C+David+Burkett%2C+and+Dan+Klein%2E+2012%2E+An+empirical+investigation+of+statistical+significance+in+NLP%2E+In+Proceedings+of+EMNLP%2E)
7. Shane Bergsma, Mark Dredze, Benjamin Van Durme, Theresa Wilson, and David Yarowsky. 2013. [find](https://scholar.google.com/scholar?q=Shane+Bergsma%2C+Mark+Dredze%2C+Benjamin+Van+Durme%2C+Theresa+Wilson%2C+and+David+Yarowsky%2E+2013%2E)
8. Broadly improving user classification via communication-based name and location clustering on twitter. In HLT-NAACL, pages 1010–1019. [find](https://scholar.google.com/scholar?q=Broadly+improving+user+classification+via+communication%2Dbased+name+and+location+clustering+on+twitter%2E+In+HLT%2DNAACL%2C+pages+1010%E2%80%931019%2E)
9. John Blitzer, Ryan McDonald, and Fernando Pereira. 2006. Domain adaptation with structural correspondence learning. In Proceedings of EMNLP. [find](https://scholar.google.com/scholar?q=John+Blitzer%2C+Ryan+McDonald%2C+and+Fernando+Pereira%2E+2006%2E+Domain+adaptation+with+structural+correspondence+learning%2E+In+Proceedings+of+EMNLP%2E) [our card](https://md.research.elamur.ai/free/en/papers/blitzer-2006-domain-adaptation-structural-correspondence-learning/)
10. John Blitzer, Mark Dredze, and Fernando Pereira. 2007. Biographies, Bollywood, Boom-boxes and Blenders: Domain Adaptation for Sentiment Classification. In Proceedings of ACL. [find](https://scholar.google.com/scholar?q=John+Blitzer%2C+Mark+Dredze%2C+and+Fernando+Pereira%2E+2007%2E+Biographies%2C+Bollywood%2C+Boom%2Dboxes+and+Blenders%3A+Domain+Adaptation+for+Sentiment+Classification%2E+In+Proceedings+of+ACL%2E) [our card](https://md.research.elamur.ai/free/en/papers/blitzer-2007-biographies-bollywood-boom-boxes-blenders/)
11. Bo Chen, Wai Lam, Ivor Tsang, and Tak-Lam Wong. 2009. Extracting discriminative concepts for domain adaptation in text mining. In KDD. [find](https://scholar.google.com/scholar?q=Bo+Chen%2C+Wai+Lam%2C+Ivor+Tsang%2C+and+Tak%2DLam+Wong%2E+2009%2E+Extracting+discriminative+concepts+for+domain+adaptation+in+text+mining%2E+In+KDD%2E)
12. Minmin Chen, Killiang Weinberger, and John Blitzer. 2011. Co-training for domain adaptation. In NIPS. [find](https://scholar.google.com/scholar?q=Minmin+Chen%2C+Killiang+Weinberger%2C+and+John+Blitzer%2E+2011%2E+Co%2Dtraining+for+domain+adaptation%2E+In+NIPS%2E)
13. Morgane Ciot, Morgan Sonderegger, and Derek Ruths. 2013. Gender inference of twitter users in non-english contexts. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, Seattle, Wash, pages 18–21. [find](https://scholar.google.com/scholar?q=Morgane+Ciot%2C+Morgan+Sonderegger%2C+and+Derek+Ruths%2E+2013%2E+Gender+inference+of+twitter+users+in+non%2Denglish+contexts%2E+In+Proceedings+of+the+2013+Conference+on+Empirical+Methods+in+Natural+Language+Proce)
14. Ronan Collobert, Jason Weston, Léon Bottou, Michael Karlen, Koray Kavukcuoglu, and Pavel Kuksa. 2011. Natural language processing (almost) from scratch. The Journal of Machine Learning Research, 12:2493–2537. [find](https://scholar.google.com/scholar?q=Ronan+Collobert%2C+Jason+Weston%2C+Le%CC%81on+Bottou%2C+Michael+Karlen%2C+Koray+Kavukcuoglu%2C+and+Pavel+Kuksa%2E+2011%2E+Natural+language+processing+%28almost%29+from+scratch%2E+The+Journal+of+Machine+Learning+Research%2C+12%3A2) [our card](https://md.research.elamur.ai/free/en/papers/collobert-2011-natural-language-processing-almost-scratch/)
15. Hal Daumé, Abhishek Kumar, and Avishek Saha. 2010. Frustratingly easy semi-supervised domain adaptation. In ACL Workshop on Domain Adaptation for NLP. [find](https://scholar.google.com/scholar?q=Hal+Daume%CC%81%2C+Abhishek+Kumar%2C+and+Avishek+Saha%2E+2010%2E+Frustratingly+easy+semi%2Dsupervised+domain+adaptation%2E+In+ACL+Workshop+on+Domain+Adaptation+for+NLP%2E)
16. Hal Daume III and Daniel Marcu. 2006. Domain adaptation for statistical classifiers. Journal of Artificial Intelligence Research, 26:101–126. [find](https://scholar.google.com/scholar?q=Hal+Daume+III+and+Daniel+Marcu%2E+2006%2E+Domain+adaptation+for+statistical+classifiers%2E+Journal+of+Artificial+Intelligence+Research%2C+26%3A101%E2%80%93126%2E)
17. Gabriel Doyle. 2014. Mapping dialectal variation by querying social media. In EACL. [find](https://scholar.google.com/scholar?q=Gabriel+Doyle%2E+2014%2E+Mapping+dialectal+variation+by+querying+social+media%2E+In+EACL%2E)
18. Jacob Eisenstein, Noah Smith, and Eric Xing. 2011. Discovering sociolinguistic associations with structured sparsity. In Proceedings of ACL. [find](https://scholar.google.com/scholar?q=Jacob+Eisenstein%2C+Noah+Smith%2C+and+Eric+Xing%2E+2011%2E+Discovering+sociolinguistic+associations+with+structured+sparsity%2E+In+Proceedings+of+ACL%2E)
19. Jacob Eisenstein. 2013a. Phonological factors in social media writing. In Workshop on Language Analysis in Social Media, NAACL. [find](https://scholar.google.com/scholar?q=Jacob+Eisenstein%2E+2013a%2E+Phonological+factors+in+social+media+writing%2E+In+Workshop+on+Language+Analysis+in+Social+Media%2C+NAACL%2E)
20. Jacob Eisenstein. 2013b. What to do about bad language on the internet. In Proceedings of NAACL. [find](https://scholar.google.com/scholar?q=Jacob+Eisenstein%2E+2013b%2E+What+to+do+about+bad+language+on+the+internet%2E+In+Proceedings+of+NAACL%2E) [our card](https://md.research.elamur.ai/free/en/papers/eisenstein-2013-what-do-about-bad-language/)
21. Jacob Eisenstein. to appear. Systematic patterning in phonologically-motivated orthographic variation. Journal of Sociolinguistics. [find](https://scholar.google.com/scholar?q=Jacob+Eisenstein%2E+to+appear%2E+Systematic+patterning+in+phonologically%2Dmotivated+orthographic+variation%2E+Journal+of+Sociolinguistics%2E)
22. Jakob Elming, Barbara Plank, and Dirk Hovy. 2014. Robust cross-domain sentiment analysis for low-resource languages. In Proceedings of the 5th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, pages 2–7, Baltimore, Maryland, June. Association for Computationa… [find](https://scholar.google.com/scholar?q=Jakob+Elming%2C+Barbara+Plank%2C+and+Dirk+Hovy%2E+2014%2E+Robust+cross%2Ddomain+sentiment+analysis+for+low%2Dresource+languages%2E+In+Proceedings+of+the+5th+Workshop+on+Computational+Approaches+to+Subjectivity%2C+Sen)
23. Sumit Goswami, Sudeshna Sarkar, and Mayur Rustagi. 2009. Stylometric analysis of bloggers’ age and gender. In Third International AAAI Conference on Weblogs and Social Media. [find](https://scholar.google.com/scholar?q=Sumit+Goswami%2C+Sudeshna+Sarkar%2C+and+Mayur+Rustagi%2E+2009%2E+Stylometric+analysis+of+bloggers%E2%80%99+age+and+gender%2E+In+Third+International+AAAI+Conference+on+Weblogs+and+Social+Media%2E)
24. Daniel Hardt and Julie Wulff. 2012. What is the meaning of 5*’s? an investigation of the expression and rating of sentiment. In Empirical Methods in Natural Language Processing, page 319. [find](https://scholar.google.com/scholar?q=Daniel+Hardt+and+Julie+Wulff%2E+2012%2E+What+is+the+meaning+of+5%2A%E2%80%99s%3F+an+investigation+of+the+expression+and+rating+of+sentiment%2E+In+Empirical+Methods+in+Natural+Language+Processing%2C+page+319%2E)
25. Janet Holmes. 1997. Women, language and identity. Journal of Sociolinguistics, 1(2):195–223. [find](https://scholar.google.com/scholar?q=Janet+Holmes%2E+1997%2E+Women%2C+language+and+identity%2E+Journal+of+Sociolinguistics%2C+1%282%29%3A195%E2%80%93223%2E)
26. Janet Holmes. 2013. An introduction to sociolinguistics. Routledge. [find](https://scholar.google.com/scholar?q=Janet+Holmes%2E+2013%2E+An+introduction+to+sociolinguistics%2E+Routledge%2E)
27. Dirk Hovy, Anders Johannsen, and Anders Søgaard. 2015a. User review-sites as a source for large-scale sociolinguistic studies. In Proceedings of WWW. [find](https://scholar.google.com/scholar?q=Dirk+Hovy%2C+Anders+Johannsen%2C+and+Anders+S%C3%B8gaard%2E+2015a%2E+User+review%2Dsites+as+a+source+for+large%2Dscale+sociolinguistic+studies%2E+In+Proceedings+of+WWW%2E)
28. Dirk Hovy, Barbara Plank, Héctor Martı́nez Alonso, and Anders Søgaard. 2015b. Mining for unambiguous instances to adapt pos taggers to new domains. In Proceedings of NAACL-HLT. [find](https://scholar.google.com/scholar?q=Dirk+Hovy%2C+Barbara+Plank%2C+He%CC%81ctor+Mart%C4%B1%CC%81nez+Alonso%2C+and+Anders+S%C3%B8gaard%2E+2015b%2E+Mining+for+unambiguous+instances+to+adapt+pos+taggers+to+new+domains%2E+In+Proceedings+of+NAACL%2DHLT%2E)
29. Moshe Koppel, Shlomo Argamon, and Anat Rachel Shimoni. 2002. Automatically categorizing written texts by author gender. Literary and Linguistic Computing, 17(4):401–412. [find](https://scholar.google.com/scholar?q=Moshe+Koppel%2C+Shlomo+Argamon%2C+and+Anat+Rachel+Shimoni%2E+2002%2E+Automatically+categorizing+written+texts+by+author+gender%2E+Literary+and+Linguistic+Computing%2C+17%284%29%3A401%E2%80%93412%2E)
30. William Labov. 1964. The social stratification of English in New York City. Ph.D. thesis, Columbia university. [find](https://scholar.google.com/scholar?q=William+Labov%2E+1964%2E+The+social+stratification+of+English+in+New+York+City%2E+Ph%2ED%2E+thesis%2C+Columbia+university%2E)
31. Wendy Liu and Derek Ruths. 2013. What’s in a name? using first names as features for gender inference in twitter. In Analyzing Microtext: 2013 AAAI Spring Symposium. [find](https://scholar.google.com/scholar?q=Wendy+Liu+and+Derek+Ruths%2E+2013%2E+What%E2%80%99s+in+a+name%3F+using+first+names+as+features+for+gender+inference+in+twitter%2E+In+Analyzing+Microtext%3A+2013+AAAI+Spring+Symposium%2E)
32. Ronald Macaulay. 2001. You’re like ‘why not?’ the quotative expressions of glasgow adolescents. Journal of Sociolinguistics, 5(1):3–21. [find](https://scholar.google.com/scholar?q=Ronald+Macaulay%2E+2001%2E+You%E2%80%99re+like+%E2%80%98why+not%3F%E2%80%99+the+quotative+expressions+of+glasgow+adolescents%2E+Journal+of+Sociolinguistics%2C+5%281%29%3A3%E2%80%9321%2E)
33. Ronald Macaulay. 2002. Extremely interesting, very interesting, or only quite interesting? adverbs and social class. Journal of Sociolinguistics, 6(3):398– 417. [find](https://scholar.google.com/scholar?q=Ronald+Macaulay%2E+2002%2E+Extremely+interesting%2C+very+interesting%2C+or+only+quite+interesting%3F+adverbs+and+social+class%2E+Journal+of+Sociolinguistics%2C+6%283%29%3A398%E2%80%93+417%2E)
34. Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781. [find](https://scholar.google.com/scholar?q=Tomas+Mikolov%2C+Kai+Chen%2C+Greg+Corrado%2C+and+Jeffrey+Dean%2E+2013%2E+Efficient+estimation+of+word+representations+in+vector+space%2E+arXiv+preprint+arXiv%3A1301%2E3781%2E)
35. Lesley Milroy and James Milroy. 1992. Social network and social class: Toward an integrated sociolinguistic model. Language in society, 21(01):1– 26. [find](https://scholar.google.com/scholar?q=Lesley+Milroy+and+James+Milroy%2E+1992%2E+Social+network+and+social+class%3A+Toward+an+integrated+sociolinguistic+model%2E+Language+in+society%2C+21%2801%29%3A1%E2%80%93+26%2E)
36. Dong Nguyen, Noah A Smith, and Carolyn P Rosé. 2011. Author age prediction from text using linear regression. In Proceedings of the 5th ACL-HLT Workshop on Language Technology for Cultural Heritage, Social Sciences, and Humanities, pages 115–123. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Dong+Nguyen%2C+Noah+A+Smith%2C+and+Carolyn+P+Rose%CC%81%2E+2011%2E+Author+age+prediction+from+text+using+linear+regression%2E+In+Proceedings+of+the+5th+ACL%2DHLT+Workshop+on+Language+Technology+for+Cultural+Heritage%2C+)
37. Dong Nguyen, Dolf Trieschnigg, A. Seza Dogruöz, Rilana Gravel, Mariet Theune, Theo Meder, and Franciska De Jong. 2014. Predicting Author Gender and Age from Tweets: Sociolinguistic Theories and Crowd Wisdom. In Proceedings of COLING 2014. [find](https://scholar.google.com/scholar?q=Dong+Nguyen%2C+Dolf+Trieschnigg%2C+A%2E+Seza+Dogruo%CC%88z%2C+Rilana+Gravel%2C+Mariet+Theune%2C+Theo+Meder%2C+and+Franciska+De+Jong%2E+2014%2E+Predicting+Author+Gender+and+Age+from+Tweets%3A+Sociolinguistic+Theories+and+Crowd)
38. Barbara Plank and Alessandro Moschitti. 2013. Embedding semantic similarity in tree kernels for domain adaptation of relation extraction. In Proceedings of ACL. [find](https://scholar.google.com/scholar?q=Barbara+Plank+and+Alessandro+Moschitti%2E+2013%2E+Embedding+semantic+similarity+in+tree+kernels+for+domain+adaptation+of+relation+extraction%2E+In+Proceedings+of+ACL%2E)
39. Barbara Plank, Dirk Hovy, Ryan McDonald, and Anders Søgaard. 2014. Adapting taggers to twitter with not-so-distant supervision. In Proceedings of COLING. COLING. [find](https://scholar.google.com/scholar?q=Barbara+Plank%2C+Dirk+Hovy%2C+Ryan+McDonald%2C+and+Anders+S%C3%B8gaard%2E+2014%2E+Adapting+taggers+to+twitter+with+not%2Dso%2Ddistant+supervision%2E+In+Proceedings+of+COLING%2E+COLING%2E)
40. Roi Reichart and Ari Rappoport. 2007. Self-training for enhancement and domain adaptation of statistical parsers trained on small datasets. In Proceedings of ACL. [find](https://scholar.google.com/scholar?q=Roi+Reichart+and+Ari+Rappoport%2E+2007%2E+Self%2Dtraining+for+enhancement+and+domain+adaptation+of+statistical+parsers+trained+on+small+datasets%2E+In+Proceedings+of+ACL%2E)
41. John Rickford and Mackenzie Price. 2013. Girlz ii women: Age-grading, language change and stylistic variation. Journal of Sociolinguistics, 17(2):143– 179. [find](https://scholar.google.com/scholar?q=John+Rickford+and+Mackenzie+Price%2E+2013%2E+Girlz+ii+women%3A+Age%2Dgrading%2C+language+change+and+stylistic+variation%2E+Journal+of+Sociolinguistics%2C+17%282%29%3A143%E2%80%93+179%2E)
42. Sara Rosenthal and Kathleen McKeown. 2011. Age prediction in blogs: A study of style, content, and online behavior in pre-and post-social media generations. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies-Volume 1, pages 763– 77… [find](https://scholar.google.com/scholar?q=Sara+Rosenthal+and+Kathleen+McKeown%2E+2011%2E+Age+prediction+in+blogs%3A+A+study+of+style%2C+content%2C+and+online+behavior+in+pre%2Dand+post%2Dsocial+media+generations%2E+In+Proceedings+of+the+49th+Annual+Meeting+o)
43. Ruchita Sarawgi, Kailash Gajulapalli, and Yejin Choi. 2011. Gender attribution: tracing stylometric evidence beyond topic and genre. In Proceedings of the Fifteenth Conference on Computational Natural Language Learning, pages 78–86. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Ruchita+Sarawgi%2C+Kailash+Gajulapalli%2C+and+Yejin+Choi%2E+2011%2E+Gender+attribution%3A+tracing+stylometric+evidence+beyond+topic+and+genre%2E+In+Proceedings+of+the+Fifteenth+Conference+on+Computational+Natural)
44. Anders Søgaard, Anders Johannsen, Barbara Plank, Dirk Hovy, and Héctor Martı́nez Alonso. 2014. What’s in a p-value in nlp? In Proceedings of the Eighteenth Conference on Computational Natural Language Learning, pages 1–10, Ann Arbor, Michigan, June. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Anders+S%C3%B8gaard%2C+Anders+Johannsen%2C+Barbara+Plank%2C+Dirk+Hovy%2C+and+He%CC%81ctor+Mart%C4%B1%CC%81nez+Alonso%2E+2014%2E+What%E2%80%99s+in+a+p%2Dvalue+in+nlp%3F+In+Proceedings+of+the+Eighteenth+Conference+on+Computational+Natural+Languag)
45. Duyu Tang, Furu Wei, Nan Yang, Ming Zhou, Ting Liu, and Bing Qin. 2014. Learning sentiment-specific word embedding for twitter sentiment classification. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, pages 1555–1565. [find](https://scholar.google.com/scholar?q=Duyu+Tang%2C+Furu+Wei%2C+Nan+Yang%2C+Ming+Zhou%2C+Ting+Liu%2C+and+Bing+Qin%2E+2014%2E+Learning+sentiment%2Dspecific+word+embedding+for+twitter+sentiment+classification%2E+In+Proceedings+of+the+52nd+Annual+Meeting+of+th) [our card](https://md.research.elamur.ai/free/en/papers/tang-2014-learning-sentiment-specific-word-embedding/)
46. Svitlana Volkova, Theresa Wilson, and David Yarowsky. 2013. Exploring demographic language variations to improve multilingual sentiment analysis in social media. In Proceedings of EMNLP, pages 1815–1827. [find](https://scholar.google.com/scholar?q=Svitlana+Volkova%2C+Theresa+Wilson%2C+and+David+Yarowsky%2E+2013%2E+Exploring+demographic+language+variations+to+improve+multilingual+sentiment+analysis+in+social+media%2E+In+Proceedings+of+EMNLP%2C+pages+1815%E2%80%9318)
47. Svitlana Volkova, Yoram Bachrach, Michael Armstrong, and Vijay Sharma. 2015. Inferring latent user properties from texts published in social media (demo). In Proceedings of the Twenty-Ninth Conference on Artificial Intelligence (AAAI), Austin, TX, January. [find](https://scholar.google.com/scholar?q=Svitlana+Volkova%2C+Yoram+Bachrach%2C+Michael+Armstrong%2C+and+Vijay+Sharma%2E+2015%2E+Inferring+latent+user+properties+from+texts+published+in+social+media+%28demo%29%2E+In+Proceedings+of+the+Twenty%2DNinth+Conference)
48. Martijn Wieling, John Nerbonne, and R Harald Baayen. 2011. Quantitative social dialectology: Explaining linguistic variation geographically and socially. PloS one, 6(9):e23613. [find](https://scholar.google.com/scholar?q=Martijn+Wieling%2C+John+Nerbonne%2C+and+R+Harald+Baayen%2E+2011%2E+Quantitative+social+dialectology%3A+Explaining+linguistic+variation+geographically+and+socially%2E+PloS+one%2C+6%289%29%3Ae23613%2E)