ABSTRACT
This paper describes the development process of learning outcomes and prerequisite knowledge recommendation system based on the information about an academic course. The recommendation system is designed to be implemented in the service Educational Program Maker for working with education process elements. The recommendation system aims to help university staff members during academic course creation and, as a result, make the paperwork digitizing in universities easier and faster. Learning outcomes recommendations are computed with the Universal Sentence Encoder and learning content data. Prerequisite knowledge recommendations are calculated with information regarding curricula and concept domains. Developed algorithms were modified for implementation in the service, and interface prototypes for forms with displayed recommendations were created. Models were evaluated with the hit rate metric; the results showed that final models outperform baselines.
- Educational Program maker. Accessed August 23, 2021. https://op.itmo.ruGoogle Scholar
- Anastasiia Chernysheva, Maksim Khlopotov, Svetlana Derkunskaia, Carina Babayants, Anton Govorov, Valeria Artamonova, and Sergey Koriakov (in press). 2021. Разработка алгоритма экспертизы и верификации рабочих программ дисциплин для использования в информационных системах [Developing the algorithm for examination and verification of academic courses for future use in information systems]. Vestnik of Astrakhan State Technical University. Series: Management, Computer Science And Informatics. 2021, no. 1.Google Scholar
- Anton Govorov, Anastasiia Chernysheva, Maksim Khlopotov, Svetlana Derkunskaia, and Anna Arzumanian. 2020. Individual Learning Pathway Validation Based on the Syllabus. In Proceeding of the 26th Conference of Fruct Association. 108-114. https://doi.org/10.23919/FRUCT48808.2020.9087453Google ScholarCross Ref
- Anastasiia Chernysheva, Maksim Khlopotov, Anton Govorov, Svetlana Derkunskaia, Valeria Artamonova, Carina Babayants, Sergey Koriakov, and Anna Arzumanian (in press). 2021. Target Professions Based Approach for Individual Learning Pathway Creation. International Journal of Information and Education TechnologyGoogle Scholar
- Joaquim Moré, Jordi Conesa, David Baneres, and Montserrat Junyent. 2015. A Semi-Automated System for Recognizing Prior Knowledge. International Journal of Emerging Technologies in Learning, 10(7): 23-30. https://doi.org/10.3991/ijet.v10i7.4610Google ScholarCross Ref
- Isabel Guitart, Jordi Conesa, David Baneres, Joaquim Moré, Jordi Duran, and David Gañan. 2016. Extraction of Relevant Terms and Learning Outcomes from Online Courses. International Journal of Emerging Technologies in Learning, 11(10): 22-30. https://doi.org/10.3991/ijet.v11i10.5928Google ScholarCross Ref
- Atish Pawar, Sahib Budhiraja, Daniel Kivi, and Vijay Mago. 2018. Are we on the same learning curve: Visualization of Semantic Similarity of Course Objectives. arXiv:1804.06339Google Scholar
- Igor Labutov, Yun Huang, Peter Brusilovsky, and Daqing He. 2017. Semi-Supervised Techniques for Mining Learning Outcomes and Prerequisites. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. (August 2017), 907-915. https://doi.org/10.1145/3097983.3098187Google ScholarDigital Library
- Jason Angel, Segun Taofeek Aroyehun, and Alexander Gelbukh. 2020. NLP-CIC @ PRELEARN: Mastering prerequisites relations, from hand-crafted features tembeddings. In Proceedings of Seventh Evaluation Campaign of Natural Language Processing and Speech Tools for Italian. Final Workshop (EVALITA 2020), Online. CEUR.org.Google Scholar
- Giovanni Puccetti, Luis Bolanos, Filippo Chiarello, and Gualtiero Fantoni. 2020. B4DS @ PRELEARN: Ensemble Method for Prerequisite Learning. In Proceedings of Seventh Evaluation Campaign of Natural Language Processing and Speech Tools for Italian. Final Workshop (EVALITA 2020), Online. CEUR.org.Google ScholarCross Ref
- Alessio Moggio and Andrea Parizz. 2020. UNIGE SE @ PRELEARN: Utility for Automatic Prerequisite Learning from Italian Wikipedia. In Proceedings of Seventh Evaluation Campaign of Natural Language Processing and Speech Tools for Italian. Final Workshop (EVALITA 2020), Online. CEUR.org.Google Scholar
- Matthew E. Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, and Luke Zettlemoyer. 2018. Deep contextualized word representations. arXiv:1802.05365Google Scholar
- Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv:1810.04805Google Scholar
- Nils Reimers and Iryna Gurevych. 2019. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. arXiv:1908.10084Google Scholar
- Yinfei Yang, Daniel Cer, Amin Ahmad, Mandy Guo, Jax Law, Noah Constant, Gustavo Hernandez Abrego, Steve Yuan, Chris Tar, Yun-Hsuan Sung, Brian Strope, and Ray Kurzweil. 2020. Multilingual Universal Sentence Encoder for Semantic Retrieval. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations. (July 2020), 87-94.Google ScholarCross Ref
- Christopher Olston, Fangwei Li, Jeremiah Harmsen, Jordan Soyke, Kiril Gorovoy, Li Lao, Noah Fiedel, Sukriti Ramesh, and Vinu Rajashekhar. 2017. TensorFlow-Serving: Flexible, High-Performance ML Serving. arXiv:1712.06139Google Scholar
Index Terms
- The Development of Learning Outcomes and Prerequisite Knowledge Recommendation System
Recommendations
A General Rating Recommended Weight-Aware Model for Recommendation System
HCC 2016: Revised Selected Papers of the Second International Conference on Human Centered Computing - Volume 9567In recommendation system, the ratings represent the users' preference and play an important role in recommending items to users. However, the ratings of items may be influenced by many factors, such as time the latest ratings are more able to reflect ...
Parallel Ratio Based CF for Recommendation System
ICCCNT '16: Proceedings of the 7th International Conference on Computing Communication and Networking TechnologiesWith the increase in E-commerce, Recommendation Systems are getting popular to provide recommendations of various items (movies, books, music) to users. To build the Recommendation System (RS), Collaborative Filtering (CF) techniques are proven ...
Comments