---
title: "Dimensions of (dis)preference in designing polar answers in"
description: "They then code design features such as offset, fillers, oh versus other discourse markers, non-interjection answers, epistemic… 43 references."
authors: ["Ryan Ka Yau Lai", "Yan Lashchev"]
year: 2025
venue: "Proceedings of the Society for Computation in Linguistics 2025"
source: "https://aclanthology.org/2025.scil-1.15/"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/lai-2025-dimensions-dis-preference-designing-polar/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/lai-2025-dimensions-dis-preference-designing-polar/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/page/17/) / Dimensions of (dis)preference in designing polar answers in American English: A latent class analysis

# Dimensions of (dis)preference in designing polar answers in American English: A latent class analysis

**Authors:** Ryan Ka Yau Lai and Yan Lashchev · **Year:** 2025 · **Venue:** [Proceedings of the Society for Computation in Linguistics 2025](https://md.research.elamur.ai/free/en/venues/scil/) ([SCiL 2025](https://md.research.elamur.ai/free/en/venues/scil/2025/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2025.scil-1.15/) · [PDF](https://aclanthology.org/2025.scil-1.15.pdf) · [OpenAlex](https://openalex.org/W6921368231)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Questions often lean toward an expected reply. Conversation Analysis has long held that replies going against that lean are delayed, hedged or explained, but this rested on qualitative work and samples of about 200 pairs. Lai and Lashchev test the idea at scale on American English phone conversations in the Switchboard Corpus, drawing on SwDA dialogue-act tags and the NXT-format annotations. They extract polar question–answer pairs and divide each answer into a pre-core, a core (the first unit carrying polarity) and a post-core. They then code design features such as offset, fillers, oh versus other discourse markers, non-interjection answers, epistemic downgrade, expansions, contrastive conjunctions and self-repair. A latent class model groups the answers, and tilt-conformity is linked to class membership as an auxiliary variable. The features fall into three dimensions: challenging the question's assumptions, expanding the answer, and delaying it. Answers that contradict the tilt differ only modestly from conforming ones, while answers with no polarity differ sharply. The authors conclude that preference is gradient and multidimensional, which matters for dialogue systems that try to imitate human answering.

## Key points
- Data come from the Switchboard Corpus, using SwDA tags (in the CSVs of Potts 2011) and NXT-format XML.
  - Polar questions were found via the qy and ^g tags.
  - Pairs with a gap of 5 s or more were dropped as likely errors.
- Only features occurring in more than 5% of answers were modelled. Breath and laughter were dropped for this reason; post-core self-repair (SISR) passed and was kept.
- Epistemic downgrades were detected with the help of spaCy POS tags and dependency parses. Only 5% of interjection-type answers are downgraded, against 21% of non-interjection-type answers.
- Tilt-non-conforming answers make the class with no challenge, expansion or delay features (class D) less likely. Compared with D, classes A, B and C each show increased odds, with p = .003, .005 and \< .001.
  - Non-polarity answers lean far more strongly toward the assumption-challenging classes (p \< .001).
- Two results were unexpected:
  - Silent offset groups with assumption-challenging features rather than with filler-type delays.
  - The interjection vs. non-interjection choice patterns together with qualification.

## Interesting ideas
- Anchoring each answer on its first polarity-bearing unit, then describing material before and after it separately, turns a messy reply into a comparable three-slot structure.
- Lexicon building runs in three steps: harvest candidate adverbs and modals with a tagger, hand-pick the relevant ones, then re-scan by surface form. The final scan catches tokens the tagger mislabelled.
- Treating oh apart from other discourse markers keeps a signal of epistemic authority distinct from mere stalling, instead of pooling all markers into one bucket.
- Answers without any polarity serve as a contrast group, showing that the tilt effect is small next to them, so effect sizes are judged against a meaningful baseline.
- Unmodelled reply features are grouped into latent classes, and the predictor of interest is added only afterward as an auxiliary variable. This keeps the discovered typology from being shaped by the hypothesis.

## For Mova

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

- **I1** (frames): The speech-act layer could locate the "core" yes/no in a reply and tag pre-core hedges and post-core expansions as separate pragmatic signals for implicature.
- **I2** (learn): The same harvest–curate–rescan loop could build hedge or downgrade lists from silver-parsed text without inheriting tagger errors.
- **I3** (tokens): Discourse-marker tagging in the en crate could give oh its own label so that later stages can read its distinct function.
- **I4** (learn): When evaluating a pragmatic classifier, a clearly different control category would show whether a detected effect is large or trivial.
- **I5** (answer): Students answering yes/no questions could interpret replies by design class (challenge, expand, delay), e.g. treating a repetitional or downgraded reply as possibly non-committal rather than a plain yes.

*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

- [University of California, Santa Barbara](https://md.research.elamur.ai/free/en/universities/university-of-california-santa-barbara/) — University, Santa Barbara, United States · 67 works · 10,550 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works

🧭 Topics (1): [English](https://md.research.elamur.ai/free/en/topics/english/) · 2,379 works

## Cite

Cite as: Ryan Ka Yau Lai and Yan Lashchev. 2025. Dimensions of (dis)preference in designing polar answers in American English: A latent class analysis. Proceedings of the Society for Computation in Linguistics 2025.

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

```bibtex
@inproceedings{lai2025dimensions,
  title = {{Dimensions of (dis)preference in designing polar answers in American English: A latent class analysis}},
  author = {Ryan Ka Yau Lai and Yan Lashchev},
  booktitle = {Proceedings of the Society for Computation in Linguistics 2025},
  year = {2025},
  doi = {10.7275/scil.3123},
  url = {https://doi.org/10.7275/scil.3123}
}
```

- [← previous Dialect2SQL: A Novel Text-to-SQL Dataset for Arabic Dialects with a Focus on Moroccan Darija](https://md.research.elamur.ai/free/en/papers/chafik-2025-dialect2sql-novel-text-sql-dataset/)
- [next → Discourse structure and narration: A diachronic view from Germanic](https://md.research.elamur.ai/free/en/papers/demske-2025-discourse-structure-narration-diachronic/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/17/)

## References

43 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Jurafsky, Daniel, Elizabeth Shriberg & Debra Biasca. 1997. Switchboard SWBD-DAMSL Shallow-Discourse-Function Annotation Coders Manual. [find](https://scholar.google.com/scholar?q=Jurafsky%2C+Daniel%2C+Elizabeth+Shriberg+%26+Debra+Biasca%2E+1997%2E+Switchboard+SWBD%2DDAMSL+Shallow%2DDiscourse%2DFunction+Annotation+Coders+Manual%2E)
2. Alloatti, Francesca, Luigi Di Caro, Alessio Bosca, & others. 2021. Conversation analysis, repair sequences and human computer interaction–a theoretical framework and an empirical proposal of action. In Proceedings of the Fourth Workshop on Reasoning and Learning for Human-Machine Dialogues (DEEP-DIAL 2021) at the Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21). Association for the Advancement of Artificial Intelligence. [find](https://scholar.google.com/scholar?q=Alloatti%2C+Francesca%2C+Luigi+Di+Caro%2C+Alessio+Bosca%2C+%26+others%2E+2021%2E+Conversation+analysis%2C+repair+sequences+and+human+computer+interaction%E2%80%93a+theoretical+framework+and+an+empirical+proposal+of+action%2E+I)
3. Fischer, Kerstin. 2015. Conversation, Construction Grammar, and cognition. Language and Cognition 7(4). 563–588. https://doi.org/10.1017/langcog.2015.23. [↗](https://doi.org/10.1017/langcog.2015.23)
4. Ford, Cecilia E. 2001. At the intersection of turn and sequence. In Margaret Selting & Elzabeth Couper-Kuhlen (eds.), Studies in interactional linguistics (Studies in Discourse and Grammar 10). Amsterdam: John Benjamins Publishing. 51–80. [↗](https://doi.org/10.1075/sidag.10.05for)
5. Godfrey, John J, Edward C Holliman & Jane McDaniel. 1992. SWITCHBOARD: Telephone speech corpus for research and development. In IEEE International Vonference on Acoustics, Dpeech, and Signal Processing, vol. 1, 517–520. IEEE Computer Society. [find](https://scholar.google.com/scholar?q=Godfrey%2C+John+J%2C+Edward+C+Holliman+%26+Jane+McDaniel%2E+1992%2E+SWITCHBOARD%3A+Telephone+speech+corpus+for+research+and+development%2E+In+IEEE+International+Vonference+on+Acoustics%2C+Dpeech%2C+and+Signal+Processin)
6. Hallquist, Michael N. & Joshua F. Wiley. 2018. MplusAutomation : An R package for facilitating large-scale latent variable analyses in Mplus. Structural Equation Modeling: A Multidisciplinary Journal 25(4). 621–638. https://doi.org/10.1080/10705511.2017.1402334. [↗](https://doi.org/10.1080/10705511.2017.1402334)
7. Asparouhov, Tihomir & Bengt Muthén. 2014. Auxiliary variables in mixture modeling: Three-step approaches using Mplus. Structural Equation Modeling: A Multidisciplinary Journal 21(3). 329–341. [find](https://scholar.google.com/scholar?q=Asparouhov%2C+Tihomir+%26+Bengt+Muth%C3%A9n%2E+2014%2E+Auxiliary+variables+in+mixture+modeling%3A+Three%2Dstep+approaches+using+Mplus%2E+Structural+Equation+Modeling%3A+A+Multidisciplinary+Journal+21%283%29%2E+329%E2%80%93341%2E)
8. Heritage, John. 1998. Oh-prefaced responses to inquiry. Language in Society 27(3). 291–334. https://doi.org/10.1017/S0047404500019990. [↗](https://doi.org/10.1017/s0047404500019990)
9. Bolinger, Dwight. 1957. Interrogative structures of American English: the direct question (Publication of the American Dialect Society; 28; No. 28). Alabama: American Dialect Society. [find](https://scholar.google.com/scholar?q=Bolinger%2C+Dwight%2E+1957%2E+Interrogative+structures+of+American+English%3A+the+direct+question+%28Publication+of+the+American+Dialect+Society%3B+28%3B+No%2E+28%29%2E+Alabama%3A+American+Dialect+Society%2E)
10. Heritage, John. 2005. Cognition in discourse. In Hedwig Te Molder & Jonathan Potter (eds.), Conversation and Cognition, 184–202. 1st edn. Cambridge: Cambridge University Press. https://doi.org/10.1017/CBO9780511489990.009. [↗](https://doi.org/10.1017/cbo9780511489990.009)
11. Brennan, Susan E & Maurice Williams. 1995. The feeling of another′ s knowing: Prosody and filled pauses as cues to listeners about the metacognitive states of speakers. Journal of Memory and Language 34(3). 383–398. [↗](https://doi.org/10.1006/jmla.1995.1017)
12. Calhoun, Sasha, Jean Carletta, Jason M Brenier, Neil Mayo, Dan Jurafsky, Mark Steedman & David Beaver. 2010. The NXT-format Switchboard Corpus: a rich resource for investigating the syntax, semantics, pragmatics and prosody of dialogue. Language Resources and Evaluation 44. 387–419. [↗](https://doi.org/10.1007/s10579-010-9120-1)
13. Cappelli, Gloria. 2007. “I reckon I know how Leonardo da Vinci must have felt ...”: epistemicity, evidentiality and English verbs of cognitive attitude. Pari (Grosseto): Pari Publishing. [find](https://scholar.google.com/scholar?q=Cappelli%2C+Gloria%2E+2007%2E+%E2%80%9CI+reckon+I+know+how+Leonardo+da+Vinci+must+have+felt+%2E%2E%2E%E2%80%9D%3A+epistemicity%2C+evidentiality+and+English+verbs+of+cognitive+attitude%2E+Pari+%28Grosseto%29%3A+Pari+Publishing%2E)
14. Heritage, John. 2015. Well-prefaced turns in English conversation: A conversation analytic perspective. Journal of Pragmatics 88. 88–104. [↗](https://doi.org/10.1016/j.pragma.2015.08.008)
15. Heritage, John & Steven Clayman. 2010. Talk in action: interactions, identities, and institutions (Language in Society 38). Chichester Malden: Wiley-Blackwell. [find](https://scholar.google.com/scholar?q=Heritage%2C+John+%26+Steven+Clayman%2E+2010%2E+Talk+in+action%3A+interactions%2C+identities%2C+and+institutions+%28Language+in+Society+38%29%2E+Chichester+Malden%3A+Wiley%2DBlackwell%2E)
16. Heritage, John & Geoffrey Raymond. 2012. Navigating epistemic landscapes: Acquiescence, agency and resistance in responses to polar questions. In Jan P. De Ruiter (ed.), Questions, 179–192. 1st edn. Cambridge University Press. https://doi.org/10.1017/CBO9781139045414.013. [↗](https://doi.org/10.1017/cbo9781139045414.013)
17. Dingemanse, Mark & Andreas Liesenfeld. 2022. From text to talk: Harnessing conversational corpora for humane and diversity-aware language technology. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 5614–5633. Dublin, Ireland: Association for Computational Linguistics. https://doi.org/10.18653/v1/2022.acl-long.385. [↗](https://doi.org/10.18653/v1/2022.acl-long.385)
18. Heritage, John & Chase Wesley Raymond. 2021. Preference and polarity: epistemic stance in question design. Research on Language and Social Interaction 54(1). 39–59. https://doi.org/10.1080/08351813.2020.1864155.174 9 [↗](https://doi.org/10.1080/08351813.2020.1864155.174)
19. Honnibal, Matthew & Ines Montani. 2017. spaCy 2: Natural language understanding with Bloom embeddings, convolutional neural networks and incremental parsing. [find](https://scholar.google.com/scholar?q=Honnibal%2C+Matthew+%26+Ines+Montani%2E+2017%2E+spaCy+2%3A+Natural+language+understanding+with+Bloom+embeddings%2C+convolutional+neural+networks+and+incremental+parsing%2E)
20. Pomerantz, Anita & John Heritage. 2012. Preference. In Jack Sidnell & Tanya Stivers (eds.), The Handbook of Conversation Analysis, 210–228. 1st edn. Wiley. https://doi.org/10.1002/9781118325001.ch11. [↗](https://doi.org/10.1002/9781118325001.ch11)
21. Kendrick, Kobin H. & Francisco Torreira. 2015. The timing and construction of preference: a quantitative study. Discourse Processes 52(4). 255–289. https://doi.org/10.1080/0163853X.2014.955997. [↗](https://doi.org/10.1080/0163853x.2014.955997)
22. Potts, Christopher. 2011. The Switchboard Dialog Act Corpus. Computational Pragmatics. [http://compprag.christopherpotts.net/swda.html](http://compprag.christopherpotts.net/swda.html). [↗](http://compprag.christopherpotts.net/swda.html)
23. Quirk, Randolph, Sidney Greenbaum, Geoffrey Leech & Jan Svartvik. 1985. A Comprehensive Grammar of the English Language. London: Longman. [find](https://scholar.google.com/scholar?q=Quirk%2C+Randolph%2C+Sidney+Greenbaum%2C+Geoffrey+Leech+%26+Jan+Svartvik%2E+1985%2E+A+Comprehensive+Grammar+of+the+English+Language%2E+London%3A+Longman%2E)
24. Kendrick, Kobin H & Judith Holler. 2017. Gaze direction signals response preference in conversation. Research on Language and Social Interaction 50(1). 12–32. [↗](https://doi.org/10.1080/08351813.2017.1262120)
25. Raymond, Geoffrey. 2003. Grammar and social organization: yes/no interrogatives and the structure of responding. American Sociological Review 68(6). 939– 967. https://doi.org/10.1177/000312240306800607. [↗](https://doi.org/10.1177/000312240306800607)
26. Lah, Ji Young & Yo-An Lee. 2023. Managing turn-taking through beep sounds by Bixby: Applying conversation analysis to human-chatbot interaction constructions. Linguistic Research 40. 61–87. https://doi.org/10.17250/KHISLI.40..202309.003. [↗](https://doi.org/10.17250/khisli.40..202309.003)
27. Robinson, Jeffrey D. 2020a. Revisiting preference organization in context: a qualitative and quantitative examination of responses to information seeking. Research on Language and Social Interaction 53(2). 197–222. https://doi.org/10.1080/08351813.2020.1739398. [↗](https://doi.org/10.1080/08351813.2020.1739398)
28. Lee, Seung-Hee. 2015. Two forms of affirmative responses to polar questions. Discourse Processes 52(1). 21–46. https://doi.org/10.1080/0163853X.2014.899001. [↗](https://doi.org/10.1080/0163853x.2014.899001)
29. Masyn, Katherine E. 2013. Latent Class Analysis and Finite Mixture Modeling. In Todd D. Litte (ed.), The Oxford Handbook of Qauntitative Methods in Psychology: Vol 2: Statistical Analysis. Oxford University Press. https://doi.org/10.1093/oxfordhb/9780199934898.013. 0025. [↗](https://doi.org/10.1093/oxfordhb/9780199934898.013)
30. Robinson, Jeffrey D. 2020b. One Type of Polar, Information-Seeking Question and Its Stance of Probability: Implications for the Preference for Agreement. Research on Language and Social Interaction 53(4). 425–442. https://doi.org/10.1080/08351813.2020.1826759. [↗](https://doi.org/10.1080/08351813.2020.1826759)
31. Meteer, Marie & Ann Taylor. 1995. Dysfluency Annotation Stylebook for the Switchboard Corpus. [find](https://scholar.google.com/scholar?q=Meteer%2C+Marie+%26+Ann+Taylor%2E+1995%2E+Dysfluency+Annotation+Stylebook+for+the+Switchboard+Corpus%2E)
32. Roberts, Seán G, Francisco Torreira & Stephen C Levinson. 2015. The effects of processing and sequence organization on the timing of turn taking: a corpus study. Frontiers in psychology SA 2015(6). 509. [↗](https://doi.org/10.3389/fpsyg.2015.00509)
33. Muthén, Bengt & Linda Muthén. 2019. Mplus: A general latent variable modeling program. [find](https://scholar.google.com/scholar?q=Muth%C3%A9n%2C+Bengt+%26+Linda+Muth%C3%A9n%2E+2019%2E+Mplus%3A+A+general+latent+variable+modeling+program%2E)
34. Morgan, Grant B. 2015. Mixed mode latent class analysis: An examination of fit index performance for classification. Structural Equation Modeling: A Multidisciplinary Journal 22(1). 76–86. https://doi.org/10.1080/10705511.2014.935751. [↗](https://doi.org/10.1080/10705511.2014.935751)
35. Sacks, Harvey. 2010 [1987]. On the preferences for agreement and contiguity in sequences in conversation. In Patrick Griffiths, Andrew Merrison & Aileen Bloomer (eds.), Language in Use: A Reader, 8–22. Milton Park: Routledge. [find](https://scholar.google.com/scholar?q=Sacks%2C+Harvey%2E+2010+%5B1987%5D%2E+On+the+preferences+for+agreement+and+contiguity+in+sequences+in+conversation%2E+In+Patrick+Griffiths%2C+Andrew+Merrison+%26+Aileen+Bloomer+%28eds%2E%29%2C+Language+in+Use%3A+A+Reader%2C+8%E2%80%9322)
36. Nishizaka, Aug & Kaoru Hayano. 2015. Conversational Preference. In Karen Tracy, Todd Sandel & Cornelia Ilie (eds.), The International Encyclopedia of Language and Social Interaction, 1–7. 1st edn. Wiley. https://doi.org/10.1002/9781118611463.wbielsi071. [↗](https://doi.org/10.1002/9781118611463.wbielsi071)
37. Smith, Vicki L & Herbert H Clark. 1993. On the course of answering questions. Journal of Memory and Language 32(1). 25–38. [↗](https://doi.org/10.1006/jmla.1993.1002)
38. Stivers, Tanya, Nicholas J. Enfield, Penelope Brown, Christina Englert, Makoto Hayashi, Trine Heinemann, Gertie Hoymann, Federico Rossano, Jan Peter De Ruiter & Kyung-Eun Yoon. 2009. Universals and cultural variation in turn-taking in conversation. Proceedings of the National Academy of Sciences 106(26). 10587– 10592. [↗](https://doi.org/10.1073/pnas.0903616106)
39. Nylund-Gibson, Karen & Andrew Young Choi. 2018. Ten frequently asked questions about latent class analysis. Translational Issues in Psychological Science 4(4). 440. [↗](https://doi.org/10.1037/tps0000176)
40. Pillet-Shore, Danielle. 2017. Preference Organization. In Oxford Research Encyclopedia of Communication. Oxford: Oxford University Press. https://doi.org/10.1093/acrefore/9780190228613.013.1 32. [↗](https://doi.org/10.1093/acrefore/9780190228613.013.1)
41. Stivers, Tanya & Makoto Hayashi. 2010. Transformative answers: One way to resist a question’s constraints. Language in Society 39(1). 1–25. https://doi.org/10.1017/S0047404509990637. [↗](https://doi.org/10.1017/s0047404509990637)
42. Pomerantz, Anita. 1985. Agreeing and disagreeing with assessments: some features of preferred/dispreferred turn shapes. In J. Maxwell Atkinson (ed.), Structures of Social Action, 57–101. 1st edn. Cambridge: Cambridge University Press. https://doi.org/10.1017/CBO9780511665868.008. [↗](https://doi.org/10.1017/cbo9780511665868.008)
43. Stivers, Tanya. 2022. The book of answers: alignment, autonomy, and affiliation in social interaction (Foundations of Human Interaction). New York, NY: Oxford University Press. 175 10 [find](https://scholar.google.com/scholar?q=Stivers%2C+Tanya%2E+2022%2E+The+book+of+answers%3A+alignment%2C+autonomy%2C+and+affiliation+in+social+interaction+%28Foundations+of+Human+Interaction%29%2E+New+York%2C+NY%3A+Oxford+University+Press%2E+175+10)

*Updated 1 November 2026*