---
title: "Tweet Acts: A Speech Act Classifier for Twitter (2016)"
description: "The authors build a six-class taxonomy based on Searle: Assertion, Recommendation, Expression… 15 references, cited by 19 papers here."
authors: ["Soroush Vosoughi", "Deb Roy"]
year: 2016
venue: "arXiv:1605.05156"
source: "https://arxiv.org/abs/1605.05156"
doi: "10.48550/arxiv.1605.05156"
arxiv: "1605.05156"
licence: "arXiv non-exclusive distribution licence (read only, no redistribution)"
licence_url: "http://arxiv.org/licenses/nonexclusive-distrib/1.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/vosoughi-2016-tweet-acts-speech-act-classifier/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/vosoughi-2016-tweet-acts-speech-act-classifier/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2016](https://md.research.elamur.ai/free/en/papers/2016/page/3/) / Tweet Acts: A Speech Act Classifier for Twitter

# Tweet Acts: A Speech Act Classifier for Twitter

**Authors:** [Soroush Vosoughi](https://md.research.elamur.ai/free/en/authors/soroush-vosoughi/) and Deb Roy · **Year:** 2016 · **Venue:** arXiv:1605.05156 · **Licence:** [arXiv non-exclusive distribution licence (read only, no redistribution)](http://arxiv.org/licenses/nonexclusive-distrib/1.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/1605.05156) · [PDF](https://arxiv.org/pdf/1605.05156) · [DOI 10.48550/arxiv.1605.05156](https://doi.org/10.48550/arxiv.1605.05156) · [arXiv 1605.05156](https://arxiv.org/abs/1605.05156) · [OpenAlex](https://openalex.org/W2963681578)

**Citations:** 13 citations (OpenAlex, 2026-10-14) · [19](https://md.research.elamur.ai/free/en/papers/vosoughi-2016-tweet-acts-speech-act-classifier/cited-by/) in our library, of the 141,840 papers whose bibliographies we read

## Summary
Most computational work on tweets looks at literal content. This paper asks a pragmatic question instead: what is the author *doing* with the tweet? Earlier dialogue-act methods handle Twitter's noisy, informal language poorly. The authors build a six-class taxonomy based on Searle: Assertion, Recommendation, Expression, Question, Request and Miscellaneous. They gather tweets on six topics, two for each of three topic types (entity, event, long-standing), and have three annotators label them. Each tweet is encoded as 3,313 binary features. Some are semantic: opinion, vulgar and abbreviation lexicons, emoticons, speech act verbs and filtered n-grams. Others are syntactic: punctuation, Twitter symbols, POS tags and dependency sub-trees from TweeboParser. Several standard classifiers are compared, and logistic regression does best, reaching a weighted average F1 of about 0.70. That beats the only earlier supervised Twitter system (Zhang, 0.59). Classifiers trained per topic do slightly better than per-type or Twitter-wide ones. The work matters because speech-act labels feed downstream tasks such as rumor detection and gauging public attitude on a topic.

## Key points
- **Dataset:** 7,563 tweets, each labelled by majority vote of three annotators, with inter-annotator kappa of 0.78. Topics include the Boston Marathon bombings, Ferguson, the Red Sox and Ashton Kutcher.
- **Features:** 3,313 binary features, 1,647 semantic and 1,666 syntactic. Resources include:
  - the Harvard General Inquirer;
  - Wierzbicka's 229 speech act verbs in 37 groups, matched only on verbs tagged by the Owoputi et al. tagger and Porter-stemmed;
  - 1,415 n-grams and 1,655 dependency sub-trees of one or two edges.
- **Classifier comparison (20-fold cross-validation):** NB, DT, LR, SVM and a majority baseline were tested. LR scored 0.70 on average, versus 0.69 for SVM and 0.24 for the baseline.
- **Weak classes:** Questions are easy (F1 0.87) and Expressions strong (0.80). Requests (0.16) and Recommendations (0.30) remain hard.
- **Granularity and ablation:**
  - Topic-specific classifiers averaged 0.74, type-specific 0.71 and Twitter-wide 0.70.
  - Semantic-only features scored 0.64 and syntactic-only 0.62, both below the combined set.

## Interesting ideas
- Before matching a list of speech-act verbs, the authors first confirm that each candidate token was tagged as a verb, which avoids false hits on noun or adjective homographs; gating lexicon lookups by part of speech is a cheap precision gain wherever word lists are used.
- Small dependency fragments of one or two edges serve as cues for communicative intent, which shows that local tree shape carries pragmatic signal beyond word sequences.
- Candidate cue phrases and sub-trees are pruned so that ones containing topic-specific terms are dropped, which keeps the classifier from learning the subject matter instead of the act; this is a general guard against topical leakage.
- Training the same model at three scopes (whole platform, topic type, single topic) makes the generalization-versus-overfitting trade-off something you measure rather than assume.
- An ablation that trains on semantic-only and syntactic-only features shows that each family covers classes the other misses; for example, syntax alone nails questions but fails on Miscellaneous.

## For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

- **I1** (frames): prag could detect performative verbs (ask, demand, promise, report) only on UD heads tagged VERB, mapping them to speech-act frames instead of matching surface strings.
- **I2** (frames): mine recurring UD sub-tree patterns, such as a modal plus a 2nd-person subject or a wh-word plus aux inversion, as explainable rules for Request, Recommendation and Question.
- **I3** (learn): when inducing repair or classification rules from silver data, filter out rules anchored on content entities, and use topic-shifted test sets as negative controls.
- **I4** (answer): evaluate readers separately per genre (fables, school tests, word problems) against a global model to see where domain-specific handling is actually worth it.
- **I5** (learn): run per-class ablations of lexical versus tree-based evidence in prag's speech-act decisions to confirm that both channels earn their place.

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

## Institutions

- [Massachusetts Institute of Technology](https://md.research.elamur.ai/free/en/universities/massachusetts-institute-of-technology/) — University, Cambridge, United States · 159 works · 65,157 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 9,085 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 8,888 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 9,296 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 9,206 works

🧭 Topics (1): [💬 Speech act theory](https://md.research.elamur.ai/free/en/topics/speech-act-theory/) · 160 works

## Cite

Cite as: Soroush Vosoughi and Deb Roy. 2016. Tweet Acts: A Speech Act Classifier for Twitter. arXiv:1605.05156.

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

```bibtex
@misc{vosoughi2016tweet,
  title = {{Tweet Acts: A Speech Act Classifier for Twitter}},
  author = {Soroush Vosoughi and Deb Roy},
  year = {2016},
  doi = {10.48550/arxiv.1605.05156},
  eprint = {1605.05156},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.1605.05156}
}
```

- [← previous Pragmatic Factors in Image Description: The Case of Negations](https://md.research.elamur.ai/free/en/papers/miltenburg-2016-pragmatic-factors-image-description-case/)
- [next → Phrase Detectives Corpus 1.0 Crowdsourced Anaphoric Coreference.](https://md.research.elamur.ai/free/en/papers/chamberlain-2016-phrase-detectives-corpus-1-0/)
- [↑ back to papers of 2016](https://md.research.elamur.ai/free/en/papers/2016/page/3/)

## References

15 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Austin, J. L. 1962. How to do things with words. Clarendon Press, Oxford. [find](https://scholar.google.com/scholar?q=Austin%2C+J%2E+L%2E+1962%2E+How+to+do+things+with+words%2E+Clarendon+Press%2C+Oxford%2E)
2. Crystal, D. 2006. Language and the internet. [↗](https://doi.org/10.1017/cbo9780511487002)
3. Kong, L.; Schneider, N.; Swayamdipta, S.; Bhatia, A.; Dyer, C.; and Smith, N. A. 2014. [A dependency parser for tweets](https://md.research.elamur.ai/free/en/papers/kong-2014-dependency-parser-tweets/). In Proceedings of the Conference on Empirical Methods in Natural Language Processing, Doha, Qatar, to appear.
4. Moore, R. J. 2009. Twitter data analysis: An investor’s perspective. In [http://techcrunch.com/2009/10/05/twitter-data-analysis-an-investors-perspective-2/](http://techcrunch.com/2009/10/05/twitter-data-analysis-an-investors-perspective-2/). techcrunch. [↗](http://techcrunch.com/2009/10/05/twitter-data-analysis-an-investors-perspective-2/)
5. Owoputi, O.; O’Connor, B.; Dyer, C.; Gimpel, K.; Schneider, N.; and Smith, N. A. 2013. [Improved part-of-speech tagging for online conversational text with word clusters](https://md.research.elamur.ai/free/en/papers/owoputi-2013-improved-part-speech-tagging-online/). In HLT-NAACL, 380–390.
6. Porter, M. F. 1980. An algorithm for suffix stripping. Program: electronic library and information systems 14(3):130– 137. [↗](https://doi.org/10.1108/eb046814)
7. Searle, J. R. 1969. Speech acts: An essay in the philosophy of language, volume 626. Cambridge university press. [find](https://scholar.google.com/scholar?q=Searle%2C+J%2E+R%2E+1969%2E+Speech+acts%3A+An+essay+in+the+philosophy+of+language%2C+volume+626%2E+Cambridge+university+press%2E)
8. Searle, J. R. 1976. A taxonomy of illocutionary acts. Linguistic Agency University of Trier. [find](https://scholar.google.com/scholar?q=Searle%2C+J%2E+R%2E+1976%2E+A+taxonomy+of+illocutionary+acts%2E+Linguistic+Agency+University+of+Trier%2E)
9. Stolcke, A.; Ries, K.; Coccaro, N.; Shriberg, E.; Bates, R.; Jurafsky, D.; Taylor, P.; Martin, R.; Van Ess-Dykema, C.; and Meteer, M. 2000. [Dialogue act modeling for automatic tagging and recognition of conversational speech](https://md.research.elamur.ai/free/en/papers/stolcke-2000-dialogue-act-modeling-automatic-tagging/). Computational linguistics 26(3):339–373. [↗](https://doi.org/10.1162/089120100561737)
10. Stone, P.; Dunphy, D. C.; Smith, M. S.; and Ogilvie, D. 1968. The general inquirer: A computer approach to content analysis. Journal of Regional Science 8(1):113–116. [find](https://scholar.google.com/scholar?q=Stone%2C+P%2E%3B+Dunphy%2C+D%2E+C%2E%3B+Smith%2C+M%2E+S%2E%3B+and+Ogilvie%2C+D%2E+1968%2E+The+general+inquirer%3A+A+computer+approach+to+content+analysis%2E+Journal+of+Regional+Science+8%281%29%3A113%E2%80%93116%2E)
11. Vosoughi, S., and Roy, D. 2015. A human-machine collaborative system for identifying rumors on twitter. In proceedings of ICDMW 2015, 47–50. [find](https://scholar.google.com/scholar?q=Vosoughi%2C+S%2E%2C+and+Roy%2C+D%2E+2015%2E+A+human%2Dmachine+collaborative+system+for+identifying+rumors+on+twitter%2E+In+proceedings+of+ICDMW+2015%2C+47%E2%80%9350%2E)
12. Vosoughi, S., and Roy, D. 2016. A semi-automatic method for efficient detection of stories on social media. In proceedings of the 10th ICWSM. [↗](https://doi.org/10.48550/arxiv.1605.05134)
13. Vosoughi, S. 2015. Automatic Detection and Verification of Rumors on Twitter. Ph.D. Dissertation, Massachusetts Institute of Technology. [find](https://scholar.google.com/scholar?q=Vosoughi%2C+S%2E+2015%2E+Automatic+Detection+and+Verification+of+Rumors+on+Twitter%2E+Ph%2ED%2E+Dissertation%2C+Massachusetts+Institute+of+Technology%2E)
14. Wierzbicka, A. 1987. English speech act verbs: A semantic dictionary. Academic Press Sydney. [find](https://scholar.google.com/scholar?q=Wierzbicka%2C+A%2E+1987%2E+English+speech+act+verbs%3A+A+semantic+dictionary%2E+Academic+Press+Sydney%2E)
15. Zhao, X., and Jiang, J. 2011. An empirical comparison of topics in twitter and traditional media. Singapore Management University School of Information Systems Technical paper series. Retrieved November 10:2011. [find](https://scholar.google.com/scholar?q=Zhao%2C+X%2E%2C+and+Jiang%2C+J%2E+2011%2E+An+empirical+comparison+of+topics+in+twitter+and+traditional+media%2E+Singapore+Management+University+School+of+Information+Systems+Technical+paper+series%2E+Retrieved+Novemb)

*Updated 24 October 2026*