University of Twente Student Theses
High school students interaction with a chemical learning app
Rijswick, D.G.B. van (2024) High school students interaction with a chemical learning app.
|
PDF
15MB |
| Abstract: | This research aimed to develop an application to help high school students learn to write chemical formulas by hand. The study had three stages: input methods, OCR processing, and feedback mechanisms. Three input methods were tested: writing on plain paper, grid boxes, and directly on a tablet. Results showed significant differences between schools in preferred methods, suggesting the need for tailored educational practices. The OCR stage evaluated various models, with the MNIST and A-Z dataset model achieving 97% accuracy but requiring improvements for chemical formulas. Challenges included insufficient data for specific models, highlighting the need for larger datasets. The feedback stage assessed providing the correct answer, marking mistakes, and offering detailed explanations. Students preferred structured, incremental feedback. Limitations included app malfunctions and insufficient OCR training data, as well as incomplete ethics consent form collection. Future research should focus on expanding datasets, exploring advanced machine learning techniques, and streamlining the consent process. The study underscores the importance of user-friendly input methods, specialized OCR datasets, and detailed feedback in enhancing learning experiences, guiding future research and educational tool development. |
| Item Type: | Essay (Master) |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Subject: | 54 computer science, 81 education, teaching |
| Programme: | Interaction Technology MSc (60030) |
| Link to this item: | https://purl.utwente.nl/essays/101715 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page