Elamur Research⌕
☰
home / papers / 2022 / ALEN App: Argumentative Writing Support To Foster English Language Learning

ALEN App: Argumentative Writing Support To Foster English Language Learning

Paper · 2022 · Thiemo Wambsganss, Andrew Caines and Paula Buttery

Summary

The paper asks whether feedback on argument structure, rather than on grammar or vocabulary, can support people learning English. It follows the "arguing to learn" tradition, where argumentation is a means to other learning goals. The authors built ALEN (Argumentation for Learning English), a web writing tool. ALEN runs an argumentation-mining model over a learner's essay and highlights claims and premises. It draws a graph of how they connect, flags claims that lack supporting premises, and shows three summary scores: readability, coherence and persuasiveness. The model is a sentence-level SVM trained on a corpus of 1000 student-written business-model peer-feedback essays. The authors tested the tool in two small field studies with 28 German 12th-graders, who wrote Cambridge B2-style persuasive essays. Questionnaire scores for technology acceptance and self-efficacy were clearly above the scale midpoint. Students praised the highlighting and the graph view, but disliked wrong highlights and asked for grammar feedback. The work is a proof of concept for discourse-level feedback in language learning. It does not measure actual learning gains.

Key points

  • The argument model comes from Wambsganss et al. (2020b) and is trained on 1000 annotated peer-feedback essays. An SVM classifies argument components with 65.4% test accuracy and binary claim-premise relations with 72.1%.
  • The interface marks claims in green and premises in yellow and adds a clickable argument graph. Its dashboard has adjustable feedback granularity and links to explanations and help pages.
  • Study 1 (n=10) used technology acceptance items on a 1–7 Likert scale:
    • ease-of-use 5.77
    • perceived usefulness 5.60
    • intention to use 5.7
  • Study 2 (n=18) measured self-efficacy with seven Bandura-style items, with a mean of 5.02.
  • The writing tasks were randomly assigned Cambridge English B2 prompts of about 200 words, embedded in the unipark survey platform after an intro video. Only post-task perceptions were collected, with no control group and no measure of learning outcomes.

Interesting ideas

  • I1. Instead of grading a text, the tool shows where an argument is structurally broken, for example a claim with no premise, and asks the writer to repair it. This turns analysis output into a concrete next action.
  • I2. Students often could not tell whether an argument was weak or the sentence was simply ungrammatical. This shows that feedback must say which layer an error comes from.
  • I3. Feedback is layered: summary scores and a graph come first, and the user clicks spans or nodes to reach detailed explanations. Users control how much detail they see.
  • I4. The training corpus was chosen using explicit criteria: student-written, large enough, and annotated under a rigorous guideline with reasonable agreement. Domain match was treated as essential, unlike general tools such as MARGOT or TARGER.
  • I5. The argument structure is shown both as in-text highlights and as a linked graph, so users can move between surface text and structure.

For Mova

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

  • I1 (frames): Mova could mark assertions in a text's frames that have no supporting or causal link and expose these gaps as explainable diagnostics.
  • I2 (tree): Mova could report parse confidence or anomalies separately, so that downstream frame or argument failures are not wrongly blamed on meaning when the syntax was the issue.
  • I3 (answer): Mova's answers could give a short verdict first, with the full derivation (tree → frames → world facts) available on request for each step.
  • I4 (learn): Mova could set similar written admission criteria for silver or gold data sources, matching the target genre (school texts, fables) and requiring agreement evidence.
  • I5 (world): Mova could display its world graph with every entity or event node linked back to the source span, which makes the text-to-world step inspectable.

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 CambridgeCambridge · United Kingdom243 works · 121,396 citations🎓École Polytechnique Fédérale de LausanneLausanne · Switzerland44 works · 7,050 citations

 Fields, topics and concepts

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksComputer Science Applications · 102 works

🧭 Topics 1Research subjects and languages the work is about.English · 2,263 works

Cite

Cite as Thiemo Wambsganss, Andrew Caines and Paula Buttery. 2022. ALEN App: Argumentative Writing Support To Foster English Language Learning. Proceedings of the 17th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2022).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2022.bea-1.18

@inproceedings{wambsganss2022alen,
  title = {{ALEN App: Argumentative Writing Support To Foster English Language Learning}},
  author = {Thiemo Wambsganss, Andrew Caines and Paula Buttery},
  booktitle = {Proceedings of the 17th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2022)},
  year = {2022},
  doi = {10.18653/v1/2022.bea-1.18},
  url = {https://doi.org/10.18653/v1/2022.bea-1.18}
}

References

37 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Tazin Afrin, Omid Kashefi, Christopher Olshefski, Diane Litman, Rebecca Hwa, and Amanda Godley. 2021. Effective Interfaces for Student-Driven Revision Sessions for Argumentative Writing. In Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems, pages 1–13, New York, NY, USA. Acm. find
  2. Christa S.C. Asterhan and Baruch B. Schwarz. 2016. Argumentation for Learning: Well-Trodden Paths and Unexplored Territories. Educational Psychologist, 51(2):164–187. ↗
  3. Albert Bandura. 1991. Social cognitive theory of self-regulation. Organizational Behavior and Human Decision Processes, 50(2):248–287. ↗
  4. Artem Chernodub, Oleksiy Oliynyk, Philipp Heidenreich, Alexander Bondarenko, Matthias Hagen, Chris Biemann, and Alexander Panchenko. 2019. TARGER: Neural Argument Mining at Your Fingertips. pages 195–200. find
  5. David H. Jonassen and Bosung Kim. 2010. Arguing to learn and learning to argue: Design justifications and guidelines. Educational Technology Research and Development, 58(4):439–457. ↗
  6. Anisia Katinskaia and Roman Yangarber. 2021. Assessing grammatical correctness in language learning. In Proceedings of the 16th Workshop on Innovative Use of NLP for Building Educational Applications, pages 135–146, Online. Association for Computational Linguistics. find
  7. Elma Kerz, Daniel Wiechmann, Yu Qiao, Emma Tseng, and Marcus Ströbel. 2021. Automated classification of written proficiency levels on the CEFR-scale through complexity contours and RNNs. In Proceedings of the 16th Workshop on Innovative Use of NLP for Building Educational Applications, pages 199–209, Online. Association for Computational Linguistics. find
  8. Deanna Kuhn. 1992. Thinking as Argument. Harvard Educational Review, 62(2):155–179. ↗
  9. John Lawrence and Chris Reed. 2019. Argument mining: A survey. Computational Linguistics, 45(4):765– 818. ↗
  10. Marco Lippi and Paolo Torroni. 2015. Argument mining: A machine learning perspective. In International Workshop on Theory and Applications of Formal Argumentation, pages 163–176. Springer. find
  11. Marco Lippi and Paolo Torroni. 2016. MARGOT: A web server for argumentation mining. Expert Systems with Applications, 65:292–303. ↗
  12. Maria Nadejde and Joel Tetreault. 2019. Personalizing grammatical error correction: Adaptation to proficiency level and L1. In Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019), Hong Kong, China. Association for Computational Linguistics. ↗
  13. Lily Ng, Anne Lauscher, Joel Tetreault, and Courtney Napoles. 2020. Creating a domain-diverse corpus for theory-based argument quality assessment. In Proceedings of the 7th Workshop on Argument Mining, Online. Association for Computational Linguistics. ↗
  14. Jonathan F. Osborne, J. Bryan Henderson, Anna MacPherson, Evan Szu, Andrew Wild, and Shi Ying Yao. 2016. The development and validation of a learning progression for argumentation in science. Journal of Research in Science Teaching, 53(6):821– 846. ↗
  15. Abelardo Pardo, Kathryn Bartimote, Simon Buckingham Shum, Shane Dawson, Jing Gao, Dragan Gašević, Steve Leichtweis, Danny Liu, Roberto Martínez-Maldonado, Negin Mirriahi, Adon Christian Michael Moskal, Jurgen Schulte, George Siemens, and Lorenzo Vigentini. 2018. OnTask: Delivering Data-Informed, Personalized Learning Support Actions. Journal of Learning Analytics, 5(3):235–249. ↗
  16. Niels Pinkwart, Kevin Ashley, Collin Lynch, and Vincent Aleven. 2009. Evaluating an Intelligent Tutoring System for Making Legal Arguments with Hypotheticals. International Journal of Artificial Intelligence in Education, 19:401–424. find
  17. Jan Wira Gotama Putra, Simone Teufel, and Takenobu Tokunaga. 2021. Parsing argumentative structure in English-as-foreign-language essays. In Proceedings of the 16th Workshop on Innovative Use of NLP for Building Educational Applications, pages 97–109, Online. Association for Computational Linguistics.
  18. Severin Landolt, Thiemo Wambsganß, and Matthias Söllner. 2021. A taxonomy for deep learning in natural language processing. In Proceedings of the Annual Hawaii International Conference on System Sciences, pages 1–10, Hawaii, USA. find
  19. Ivanič Roz. 2004. Discourses of writing and learning to write. Language and Education, 18(3):220–245. ↗
  20. Anne Lauscher, Goran Glavaš, and Simone Paolo Ponzetto. 2019. An Argument-Annotated Corpus of Scientific Publications. pages 40–46. find
  21. Anne Lauscher, Lily Ng, Courtney Napoles, and Joel Tetreault. 2020. Rhetoric, logic, and dialectic: Advancing theory-based argument quality assessment in natural language processing. In Proceedings of the 28th International Conference on Computational Linguistics, Barcelona, Spain (Online). International Committee on Computational Linguistics. find
  22. Katharina Scheiter and Peter Gerjets. 2007. Learner control in hypermedia environments. Educational Psychology Review, 19(3):285–307. ↗
  23. Oliver Scheuer, Frank Loll, Niels Pinkwart, and Bruce M. McLaren. 2010. Computer-supported argumentation: A review of the state of the art. International Journal of Computer-Supported Collaborative Learning, 5(1):43–102. find
  24. Burr Settles, Geoffrey T. LaFlair, and Masato Hagiwara. 2020. Machine learning–driven language assessment. Transactions of the Association for Computational Linguistics, 8. ↗
  25. Christian Stab and Iryna Gurevych. 2014. Annotating Argument Components and Relations in Persuasive Essays. In Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers, pages 1501–1510.
  26. Christian Stab and Iryna Gurevych. 2017. Parsing Argumentation Structures in Persuasive Essays. Computational Linguistics, 43(3):619–659. ↗
  27. Daniel D. Suthers. 2003. Representational Guidance for Collaborative Inquiry. In Arguing to Learn, pages 27–46. Springer. ↗
  28. Viswanath Venkatesh and Hillol Bala. 2008. Technology acceptance model 3 and a research agenda on interventions. Decision Sciences, 39(2):273–315. ↗
  29. Henning Wachsmuth, Nona Naderi, Ivan Habernal, Yufang Hou, Graeme Hirst, Iryna Gurevych, and Benno Stein. 2017. Argumentation Quality Assessment: Theory vs. Practice. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 250–255, Vancouver, Canada. Association for Computational Linguistics. Human Factors in Computing Systems, New York, NY, USA. Association for Computing Machinery. find
  30. Florian Weber, Thiemo Wambsganss, Dominic Rüttimann, and Matthias Söllner. 2021. Pedagogical Agents for Interactive Lernaing: A Taxonomy of Conversational Agents in Education. In Forty-Second International Conference on Information Systems, pages 1–17, Austin, Texas, USA. find
  31. Max White and Alla Rozovskaya. 2020. A comparative study of synthetic data generation methods for grammatical error correction. In Proceedings of the Fifteenth Workshop on Innovative Use of NLP for Building Educational Applications, pages 198–208, Seattle, WA, USA → Online. Association for Computational Linguistics. find
  32. Helen Yannakoudakis, Øistein E. Andersen, Ardeshir Geranpayeh, Ted Briscoe, and Diane Nicholls. 2018. Developing an automated writing placement system for esl learners. Applied Measurement in Education, 31:251–267. ↗
  33. Thiemo Wambsganss, Tobias Kueng, Matthias Söllner, and Jan Marco Leimeister. 2021. ArgueTutor: An Adaptive Dialog-Based Learning System for Argumentation Skills. In Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems, pages 1–14. Association for Computing Machinery, New York, NY, USA. find
  34. Thiemo Wambsganss and Christina Niklaus. 2022. Modeling persuasive discourse to adaptively support students’ argumentative writing. 60th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference. find
  35. Thiemo Wambsganss, Christina Niklaus, Matthias Cetto, Matthias Söllner, Jan Marco Leimeister, and Siegfried Handschuh. 2020a. AL: An Adaptive Learning Support System for Argumentation Skills. In Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems, pages 1–14, New York, NY, USA. Association for Computing Machinery. find
  36. Thiemo Wambsganss, Christina Niklaus, Matthias Söllner, Siegfried Handschuh, and Jan Marco Leimeister. 2020b. A Corpus for Argumentative Writing Support in German. In 28th International Conference on Computational Linguistics (Coling), pages 1–14, Barcelona, Spain. find
  37. Wenting Wang, Deeksha Arya, Nicole Novielli, Jinghui Cheng, and Jin L.C. Guo. 2020. ArguLens: Anatomy of Community Opinions on Usability Issues Using Argumentation Models. In ACM CHI Conference on find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/wambsganss-2022-alen-app-argumentative-writing-support/