Machine learning for spelling acquisition: How accurate is the prediction of specific spelling errors in German primary school students? ------------------------------------------------------------------------ ---------- Richard Böhme^1*, Stefan Coors^1,2*, Patrick Oster¹, Meike Munser-Kiefer¹ & Sven Hilbert¹ ¹Department of Human Sciences, University of Regensburg, Regensburg, Germany ²Department of Statistics, Ludwig-Maximilians-University, Munich, Germany ^*Contributed equally to this work <br> Preprint available at [https://doi.org/10.31234/osf.io/shguf][1] ---------- **Abstract** *Background.* In Germany, 30 % of students demonstrate insufficient spelling skills at the end of primary school – partly owing to the challenge for teachers to manage a variety of student learning needs. Digital tools using machine learning (ML) have already proven to be useful in enabling teachers to individualise students’ learning. However, there are still no suitable approaches for demographics not yet proficient in spelling. *Objectives.* With an aim to adapt ML for students of all proficiencies, we investigate how accurately spelling errors can be predicted across different literacy skill levels, which specific errors are predicted best (and worst), and the content-related reasons for these errors. *Methods.* We developed a web application for spelling that was used by N = 685 first and second graders in Bavaria, Germany. With the 18,133 different misspellings made, we trained six ML models and compared their performances. *Results and conclusions.* Comparing all ML models employed in this work, the random forest performed best on average as a predictor of spelling errors. Errors at the syllable and morpheme level were predicted best, and errors at the basic phoneme-grapheme level were predicted slightly less accurately. Confusions often concerned cases that are considered linguistically ambiguous or occurred in complex error entanglements. *Implications.* The results show that ML can be a useful tool to investigate specific spelling deficiencies in demographics not yet proficiently literate. ML could assist in individualising spelling acquisition, such as by automatically providing students individualised feedback or by providing teachers with diagnostic information about their students’ learning progress. ---------- **References** - Böhme, R., Munser-Kiefer, M., & Prestridge, S. (2020). Lernunterstützung mit digitalen Medien in der Grundschule. *Zeitschrift Für Grundschulforschung, 13*(1), 1–14. - Hebbecker, K., & Souvignier, E. (2018). Formatives Assessment im Leseunterricht der Grundschule – Implementation und Wirksamkeit eines modularen, materialgestützten Konzepts. *Zeitschrift Für Erziehungswissenschaft, 21*(4), 735–765. - Hilbert, S., Coors, S., Kraus, E., Bischl, B., Lindl, A., Frei, M., . . . Stachl, C. (2021). Machine learning for the educational sciences. *Review of Education, 9*(3). ISB (State Institute for School Quality and Educational Research) (2017). *LehrplanPLUS Grundschule in Bayern (4th ed.)*. Munich: J. Maiss. - Lang, M., Binder, M., Richter, J., Schratz, P., Pfisterer, F., Coors, S., . . . Bischl, B. (2019). mlr3: A modern object-oriented machine learning framework in R. *Journal of Open Source Software, 4*(44), 1903. - Meurers, D., Kuthy, K. de, Nuxoll, F., Rudzewitz, B., & Ziai, R. (2019). Scaling up intervention studies to investigate real-life foreign language learning in school. *Annual Review of Applied Linguistics, 39*, 161–188. - Sinclair, J. (2020). *Using Machine Learning to Predict Children’s Reading Comprehension from Lexical and Syntactic Features Extracted from Spoken and Written Language* (Doctoral dissertation). Toronto: University of Toronto. - Sparks, R. L., Patton, J., & Murdoch, A. (2014). Early reading success and its relationship to reading achievement and reading volume: Replication of ‘10 years later’. *Reading and Writing, 27*(1), 189–211. Stanat, P., Schipolowski, S., Rjosk, C., Weirich, S., & Haag, N. (Eds.) (2017). *IQB Trends in Student Achievement 2016: The Second National Assessment of German and Mathematics Proficiencies at the End of Fourth Grade*. Münster: Waxmann. - Stanat, P., Schipolowski, S., Schneider, R., Sachse, K. A., Weirich, S., & Henschel, S. (2022). *Kompetenzen in den Fächern Deutsch und Mathematik am Ende der 4. Jahrgangsstufe: Erste Ergebnisse nach über einem Jahr Schulbetrieb unter Pandemiebedingungen.* Berlin: Waxmann. - Vasalou, A., Benton, L., Ibrahim, S., Sumner, E., Joye, N., & Herbert, E. (2021). Do children with reading difficulties benefit from instructional game supports? Exploring children's attention and understanding of feedback. *British Journal of Educational Technology, 52*(6), 2359–2373. - Zeuch, N., Förster, N., & Souvignier, E. (2017). Assessing Teachers’ Competencies to Read and Interpret Graphs from Learning Progress Assessment: Results from Tests and Interviews. *Learning Disabilities Research & Practice, 32*(1), 61–70. ---------- [1]: https://doi.org/10.31234/osf.io/shguf