Skip to main content

Research Repository

Advanced Search

Outputs (119)

Partially-Supervised Metric Learning via Dimensionality Reduction of Text Embeddings using Transformer Encoders and Attention Mechanisms (2024)
Journal Article
Hodgson, R., Wang, J., Cristea, A. I., & Graham, J. (2024). Partially-Supervised Metric Learning via Dimensionality Reduction of Text Embeddings using Transformer Encoders and Attention Mechanisms. IEEE Access, https://doi.org/10.1109/access.2024.3403991

Real-world applications of word embeddings to downstream clustering tasks may experience limitations to performance, due to the high degree of dimensionality of the embeddings. In particular, clustering algorithms do not scale well when applied to hi... Read More about Partially-Supervised Metric Learning via Dimensionality Reduction of Text Embeddings using Transformer Encoders and Attention Mechanisms.

Recommender systems for teachers: The relation between social ties and the effectiveness of socially-based features (2023)
Journal Article
Yacobson, E., Toda, A. M., Cristea, A. I., & Alexandron, G. (2024). Recommender systems for teachers: The relation between social ties and the effectiveness of socially-based features. Computers & Education, 210, Article 104960. https://doi.org/10.1016/j.compedu.2023.104960

Open Educational Resources (OER) repositories provide teachers with a wide range of learning resources (LRs), enabling them to design various learning sequences. However, search & select in large OER repositories can be a daunting task for teachers.... Read More about Recommender systems for teachers: The relation between social ties and the effectiveness of socially-based features.

Solving the imbalanced data issue: automatic urgency detection for instructor assistance in MOOC discussion forums (2023)
Journal Article
Alrajhi, L., Alamri, A., Pereira, F. D., Cristea, A. I., & Oliveira, E. H. T. (2023). Solving the imbalanced data issue: automatic urgency detection for instructor assistance in MOOC discussion forums. User Modeling and User-Adapted Interaction, https://doi.org/10.1007/s11257-023-09381-y

In MOOCs, identifying urgent comments on discussion forums is an ongoing challenge. Whilst urgent comments require immediate reactions from instructors, to improve interaction with their learners, and potentially reducing drop-out rates—the task is d... Read More about Solving the imbalanced data issue: automatic urgency detection for instructor assistance in MOOC discussion forums.

Sim-GAIL: A generative adversarial imitation learning approach of student modelling for intelligent tutoring systems (2023)
Journal Article
Li, Z., Shi, L., Wang, J., Cristea, A. I., & Zhou, Y. (2023). Sim-GAIL: A generative adversarial imitation learning approach of student modelling for intelligent tutoring systems. Neural Computing and Applications, 35(34), 24369-24388. https://doi.org/10.1007/s00521-023-08989-w

The continuous application of artificial intelligence (AI) technologies in online education has led to significant progress, especially in the field of Intelligent Tutoring Systems (ITS), online courses and learning management systems (LMS). An impor... Read More about Sim-GAIL: A generative adversarial imitation learning approach of student modelling for intelligent tutoring systems.

Serendipitous Gains of Explaining a Classifier - Artificial versus Human Performance and Annotator Support in an Urgent Instructor-Intervention Model for MOOCs (2023)
Presentation / Conference
Alrajhi, L., Pereira, F. D., Cristea, A. I., & Alamri, A. (2023, September). Serendipitous Gains of Explaining a Classifier - Artificial versus Human Performance and Annotator Support in an Urgent Instructor-Intervention Model for MOOCs. Paper presented at HT '23: 34th ACM Conference on Hypertext and Social Media, Rome Italy

Determining when instructor intervention is needed, based on learners’ comments and their urgency in massive open online course (MOOC) environments, is a known challenge. To solve this challenge, prior art used autonomous machine learning (ML) models... Read More about Serendipitous Gains of Explaining a Classifier - Artificial versus Human Performance and Annotator Support in an Urgent Instructor-Intervention Model for MOOCs.

Evaluation of a hybrid AI-human recommender for CS1 instructors in a real educational scenario (2023)
Conference Proceeding
Dwan Pereira, F., Oliveira, E., Rodrigues, L., Cabral, L., Oliveira, D., Carvalho, L., …Ferreira Mello, R. (2023). Evaluation of a hybrid AI-human recommender for CS1 instructors in a real educational scenario. In Responsive and Sustainable Educational Futures: 18th European Conference on Technology Enhanced Learning, EC-TEL 2023, Aveiro, Portugal, September 4–8, 2023, Proceedings (308-323). https://doi.org/10.1007/978-3-031-42682-7_21

Automatic code graders, also called Programming Online Judges (OJ), can support students and instructors in introduction to programming courses (CS1). Using OJs in CS1, instructors select problems to compose assignment lists, whereas students submit... Read More about Evaluation of a hybrid AI-human recommender for CS1 instructors in a real educational scenario.

Using deep learning to analyze the psychological effects of COVID-19 (2023)
Journal Article
Almeqren, M. A., Almegren, M., Alhayan, F., Cristea, A. I., & Pennington, D. R. (2023). Using deep learning to analyze the psychological effects of COVID-19. Frontiers in Psychology, 14, Article 962854. https://doi.org/10.3389/fpsyg.2023.962854

Problem: Sentiment Analysis (SA) automates the classification of the sentiment of people’s attitudes, feelings or reviews employing natural language processing (NLP) and computational approaches. Deep learning has recently demonstrated remarkable suc... Read More about Using deep learning to analyze the psychological effects of COVID-19.

The engage taxonomy: SDT-based measurable engagement indicators for MOOCs and their evaluation (2023)
Journal Article
Cristea, A. I., Alamri, A., Alshehri, M., Dwan Pereira, F., Toda, A. M., Harada T. de Oliveira, E., & Stewart, C. (2024). The engage taxonomy: SDT-based measurable engagement indicators for MOOCs and their evaluation. User Modeling and User-Adapted Interaction, 34(2), 323-374. https://doi.org/10.1007/s11257-023-09374-x

Massive Online Open Course (MOOC) platforms are considered a distinctive way to deliver a modern educational experience, open to a worldwide public. However, student engagement in MOOCs is a less explored area, although it is known that MOOCs suffer... Read More about The engage taxonomy: SDT-based measurable engagement indicators for MOOCs and their evaluation.

Language as a latent sequence: Deep latent variable models for semi-supervised paraphrase generation (2023)
Journal Article
Yu, J., Cristea, A. I., Harit, A., Sun, Z., Aduragba, O. T., Shi, L., & Al Moubayed, N. (2023). Language as a latent sequence: Deep latent variable models for semi-supervised paraphrase generation. AI open, 4, 19-32. https://doi.org/10.1016/j.aiopen.2023.05.001

This paper explores deep latent variable models for semi-supervised paraphrase generation, where the missing target pair for unlabelled data is modelled as a latent paraphrase sequence. We present a novel unsupervised model named variational sequence... Read More about Language as a latent sequence: Deep latent variable models for semi-supervised paraphrase generation.