Semantic Tag Clustering to Alleviate the Cold Start Problem in Learning Resource Recommendation: A Case Study on Delicious Dataset
Abstract
This study explores a methodology for recommending learning resources, demonstrated through a case study on the Delicious dataset. Tags, representing keywords assigned to describe content, are semantically clustered using K-Means. Sentence Transformers are employed to generate dense vector representation of these tags, enabling more effective clustering. The system identifies meaningful tag groups to deliver relevant recommendations, even in the absence of user interaction history, effectively addressing the cold-start problem through predefined tag profiles. The proposed methodology personalizes resource recommendations for Deaf and Hard of Hearing (DHH) learners by leveraging their profile and resource Meta data. It enhances resource search during the cold start phase by identifying the most relevant tag cluster that matches with the learner’s search query and retrieving preferred content based on the learner profile. Future extensions could incorporate dynamic preferences that evolve over time, enabling more adaptable and personalized recommendations. This work provides a robust foundation for clustering the resources based on their semantic meaning, thereby improving content-based search and retrieval of relevant learning resources.
Metrics
References
Lalitha, T.B., Sreeja, P.S. (2024) .Keyword Extraction and Pattern Model Identification on Online Learning Contents for Classification to Enhance Microlearning Concepts and Obtain Personalized eLearning Contents, International Journal of Engineering Trends and Technology, 72(3), 230–248. https://doi.org/10.14445/22315381/IJETT-V72I3P121
Government of India, Department of Empowerment of Persons with Disabilities, (2016). The Rights of Persons with Disabilities Act.
Singh, S. (2019). Revisiting Inclusion of Children with Hearing Impairment: Issues and Possibilities, in Disability, Inclusion and Inclusive Education, Springer, 157–174. https://doi.org/10.1007/978-981-15-0524-9_8
Poly, A., Banu, P.K.N. (2024). Discovering the Micro-Clusters from a group of DHH learners. In Advances in educational technologies and instructional design book series, 159–175. https://doi.org/10.4018/979-8-3693-0868-4.ch010
Joy, J., Renumol, V. (2021). Mapping of learning style with learning object metadata for addressing cold-start problem in e-learning recommender systems. International Journal of Learning Technology, 16(4), 267. https://doi.org/10.1504/ijlt.2021.121364
Mendez, N.D.D., Morales, V.T., Vicari, R.M. (2016). Learning object metadata mapping with learning styles as a strategy for improving usability of educational resource repositories. IEEE Revista Iberoamericana De Tecnologias Del Aprendizaje, IEEE, 11(2), 101–106. https://doi.org/10.1109/rita.2016.2554038
Klašnja-Milićević, A., Ivanović, M., Vesin, B., Budimac, Z. (2017). Enhancing e-learning systems with personalized recommendation based on collaborative tagging techniques. Applied Intelligence, 48(6), 1519–1535. https://doi.org/10.1007/s10489-017-1051-8
Vairavasundaram, S., Varadharajan, V., Vairavasundaram, I., & Ravi, L. (2015). Data mining‐based tag recommendation system: an overview. Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery, 5(3), 87–112. https://doi.org/10.1002/widm.1149
Selvakumar, S., Inbarani, H., Shakkeel, P.M. (2016). A Hybrid Personalized Tag Recommendations for Social E-Learning System, International Journal of Control theory and applications, 9(2) , 1187–1199.
Pan, X., Zeng, X., Ding, L. (2022). Topic optimization–incorporated collaborative recommendation for social tagging. Data Technologies and Applications, 58(3), 407–426. https://doi.org/10.1108/dta-11-2021-0332
Jo, H., Hong, J., Choeh, J.Y. (2023). Improving Collaborative Filtering Recommendations with Tag and Time Integration in Virtual Online Communities. Applied Sciences, 13(18), 10528. https://doi.org/10.3390/app131810528
Bogers, T. (2018). Tag-Based recommendation. In Lecture notes in computer science, 441–479. https://doi.org/10.1007/978-3-319-90092-6_12
X. Pan and Y. Shi, Automatic Generation of Multidimensional Labels of Educational Resources Based on Grey Clustering In International Conference on E-Learning, E-Education, and Online Training, Springer Nature Switzerland, 160-174. https://doi.org/10.1007/978-3-031-51471-5_11
ACM Recommender Systems. (2020). RecSys . https://recsys.acm.org/recsys20
GroupLens. (2013). HetRec2011 dataset. https://grouplens.org/datasets/hetrec-2011
Waskow.Canada.Ca, Slot Online 24 Jam Deposit Pulsa & Judi Terpercaya, Delicious.com, 2021. http://www.delicious.com
Devika, R., Vairavasundaram, S., Mahenthar, C.S.J., Varadarajan, V., Kotecha, K. (2021). A deep learning model based on BERT and sentence transformer for semantic keyphrase extraction on big social data. IEEE Access, 9, 165252–165261. https://doi.org/10.1109/access.2021.3133651
Khosa, S., Mehmood, A., Rizwan, M. (2023). Unifying sentence transformer embedding and Softmax voting ensemble for accurate news category prediction. Computers, 12(7), 137. https://doi.org/10.3390/computers12070137
Merlini, D., Rossini, M. (2021). Text categorization with WEKA: A survey. Machine Learning With Applications, 4, 100033. https://doi.org/10.1016/j.mlwa.2021.100033
Jelodar, H., Wang, Y., Yuan, C., Feng, X., Jiang, X., Li, Y., Zhao, L. (2018). Latent Dirichlet allocation (LDA) and topic modeling: models, applications, a survey. Multimedia Tools and Applications, 78(11), 15169–15211. https://doi.org/10.1007/s11042-018-6894-4
Patwardhan, N., Marrone, S., Sansone, C. (2023). Transformers in the real world: A survey on nlp applications. Information, 14(4), 242. https://doi.org/10.3390/info14040242
Copyright (c) 2025 Anisha Poly, Nizar Banu P.K

This work is licensed under a Creative Commons Attribution 4.0 International License.
Views: Abstract : 67 | PDF : 34
Plum Analytics