Using Machine Learning to Enhance Test Quality
Main Article Content
Abstract
This study focuses on the application of machine learning methods to improve the quality of test items. The research includes a review of the subject area and the implementation of two enhancement methods: similar question retrieval and distractor quality assessment. The first method involves testing five transformer-based models for generating text embeddings and six clustering algorithms. The second method uses the same transformer models in combination with three classification algorithms. Experimental results demonstrated the high effectiveness of the proposed approaches in solving both tasks.
Article Details
References
2. Hrich N., Azekri M., Khaldi M. An ai educational tool for detecting redundancy in distractors and items within multiple-choice tests // INTED2024 Proceedings. IATED, 2024. P. 6454–6458.
3. Аванесов В.С. Теория и практика педагогических измерений. ЦТ и МКО УГТУ-УПИ, 2005.
4. Brusilovsky P., Miller P. Web-based testing for distance education. In: P. DeBra and J. Leggett (Eds.) Proceedings of WebNet'99, World Conference of the WWW and Internet, Honolulu, HI, Oct. 24–30, 1999. AACE, P. 149–154.
5. Толстобров А.П., Коржик И.А. Возможности анализа и повышения качества тестовых заданий при использовании сетевой системы управления обучением Moodle // Вестник ВГУ. 2008. Т. 2. С. 100–106.
6. Алпацкая Е.В., Бубнов Н.В., Минченков А.В. Дифференцирующая способность тестовых материалов для оценки качества обучения // Ученые записки университета им. П.Ф. Лесгафта. 2015. № 11 (129). С. 9–14.
7. Анастази А. Психологическое тестирование. Питер, 2009.
8. Lord F.M. Applications of item response theory to practical testing problems. Routledge, 2012.
9. AlMahmoud R.H., Alian M. The effect of clustering algorithms on question answering // Expert Systems with Applications. 2024. Vol. 243. Article number 122959.
10. Zhang W.N. et al. A topic clustering approach to finding similar questions from large question and answer archives // PloS one. 2014. Vol. 9, No. 3. Article number e71511.
11. Alian M., Al-Naymat G. Questions clustering using canopy-K-means and hierarchical-K-means clustering // International Journal of Information Technology, 2022. Vol. 14, No. 7. P. 3793–3802.
12. Tarrant M., Ware J., Mohammed A. M. An assessment of functioning and non-functioning distractors in multiple-choice questions: a descriptive analysis // BMC medical education. 2009. Vol. 9. P. 1–8.
13. Moore S. et al. An automatic question usability evaluation toolkit // International Conference on Artificial Intelligence in Education. Cham: Springer Nature Switzerland, 2024. P. 31–46.
14. First Quora Dataset Release: Question Pairs // Quora, 2017. URL: https://www.quora.com/q/quoradata/First-Quora-Dataset-Release-Question-Pairs (дата обращения: 30.04.2025).
15. Quora Question Pairs Russian // Платформа Kaggle, 2022. URL: https://www.kaggle.com/datasets/loopdigga/quora-question-pairs-russian (дата обращения: 30.04.2025).
16. Hugging Face – The AI Community [Электронный ресурс]. URL: https://huggingface.co/ (дата обращения: 30.04.2025).
17. All-MiniLM-L6-v2 // Платформа Hugging Face. URL: https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2 (дата обращения: 30.04.2025).
18. Sentence-transformers/all-mpnet-base-v2 // Платформа Hugging Face. URL: https://huggingface.co/sentence-transformers/all-mpnet-base-v2 (дата обращения: 30.04.2025).
19. Paraphrase-multilingual-MiniLM-L12-v2 // Платформа Hugging Face. URL: https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 (дата обращения: 30.04.2025).
20. Gte-multilingual-base // Платформа Hugging Face. URL: https://huggingface.co/Alibaba-NLP/gte-multilingual-base (дата обращения: 30.04.2025).
21. Rubert-tiny2 // Платформа Hugging Face. URL: https://huggingface.co/cointegrated/rubert-tiny2 (дата обращения: 30.04.2025).
22. Набор данных MMLU // Платформа Hugging Face. URL: https://huggingface.co/datasets/alexandrainst/m_mmlu (дата обращения: 30.04.2025).
23. Wiki-ru-wordnet документация // URL: https://wiki-ru-wordnet.readthedocs.io/en/latest/ (дата обращения: 30.04.2025).
24. Библиотека для обработки естественного языка NLTK // URL: https://www.nltk.org/ (дата обращения: 30.04.2025).
25. Liang C. et al. Distractor generation for multiple choice questions using learning to rank // Proceedings of the thirteenth workshop on innovative use of NLP for building educational applications. 2018. Article number 28490.
This work is licensed under a Creative Commons Attribution 4.0 International License.
Presenting an article for publication in the Russian Digital Libraries Journal (RDLJ), the authors automatically give consent to grant a limited license to use the materials of the Kazan (Volga) Federal University (KFU) (of course, only if the article is accepted for publication). This means that KFU has the right to publish an article in the next issue of the journal (on the website or in printed form), as well as to reprint this article in the archives of RDLJ CDs or to include in a particular information system or database, produced by KFU.
All copyrighted materials are placed in RDLJ with the consent of the authors. In the event that any of the authors have objected to its publication of materials on this site, the material can be removed, subject to notification to the Editor in writing.
Documents published in RDLJ are protected by copyright and all rights are reserved by the authors. Authors independently monitor compliance with their rights to reproduce or translate their papers published in the journal. If the material is published in RDLJ, reprinted with permission by another publisher or translated into another language, a reference to the original publication.
By submitting an article for publication in RDLJ, authors should take into account that the publication on the Internet, on the one hand, provide unique opportunities for access to their content, but on the other hand, are a new form of information exchange in the global information society where authors and publishers is not always provided with protection against unauthorized copying or other use of materials protected by copyright.
RDLJ is copyrighted. When using materials from the log must indicate the URL: index.phtml page = elbib / rus / journal?. Any change, addition or editing of the author's text are not allowed. Copying individual fragments of articles from the journal is allowed for distribute, remix, adapt, and build upon article, even commercially, as long as they credit that article for the original creation.
Request for the right to reproduce or use any of the materials published in RDLJ should be addressed to the Editor-in-Chief A.M. Elizarov at the following address: amelizarov@gmail.com.
The publishers of RDLJ is not responsible for the view, set out in the published opinion articles.
We suggest the authors of articles downloaded from this page, sign it and send it to the journal publisher's address by e-mail scan copyright agreements on the transfer of non-exclusive rights to use the work.