Framework for the adaptation of an autonomous academic recommendation system as a service-oriented architecture

Monsalve-Pulido, Julián Alberto; Aguilar, José; Montoya, Edwin

doi:10.1007/s10639-022-11172-8

Cited by 4 publications

(1 citation statement)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, [1] provides a way to evaluate program and student data using machine learning and graph analysis to provide guidance and advice to students on their educational paths. Another researcher [2] proposed a system with a learning cognitive map to improve students' learning achievement, while [3] focused on providing a framework for an academic recommendation system. However, previous research largely overlooked the issue of imbalanced data.…”

Section: Introductionmentioning

confidence: 99%

Unraveling the Effectiveness of the K-Nn Algorithm for Imbalanced Data in Research Topic Recommendations

2024

Journal of Southwest Jiaotong University

View full text Add to dashboard Cite

This study addresses the challenge of selecting research topics for undergraduate students, focusing on computer science, by evaluating a recommendation model based on the k-Nearest Neighbor algorithm (kNN). The objective is to enhance the accuracy of research topic recommendations in the presence of imbalanced data. The methodology involves data cleaning, transformation, and correlation-based feature selection, with a particular focus on addressing missing values and optimizing the feature set. The Synthetic Minority Over-Sampling Technique (SMOTE) is employed to balance the dataset. The model development includes a comprehensive analysis of various k values, leading to the identification of k=3 with Manhattan distance as the optimal configuration, achieving an accuracy of 82%. The experiment explores different training data proportions, revealing that a 90:10 ratio yields the highest accuracy. This study incorporates a Grid Search technique for hyperparameter tuning, highlighting the importance of selecting appropriate distance metrics and nearest neighbor values. The system implementation is presented with user and administrator interfaces. Findings indicate varying model performance across research categories, emphasizing the need for category-specific evaluation metrics. The study concludes with a discussion on the significance of the results, which contribute to the improvement of research topic recommendation systems for students through the integration of advanced machine learning techniques.

show abstract

Section: Introductionmentioning

confidence: 99%

Unraveling the Effectiveness of the K-Nn Algorithm for Imbalanced Data in Research Topic Recommendations

2024

Journal of Southwest Jiaotong University

View full text Add to dashboard Cite

show abstract

Hybrid optimization-enabled deep Q network for fault prediction in service-oriented architecture

Singh,

Kumar

2023

J Supercomput

View full text Add to dashboard Cite

Analysis of Meta-Features in the Context of Adaptive Hybrid Recommendation Systems

Varela

Aguilar

Monsalve-Pulido

et al. 2022

2022 XVLIII Latin American Computer Conference (CLEI)

View full text Add to dashboard Cite

Framework for the adaptation of an autonomous academic recommendation system as a service-oriented architecture

Cited by 4 publications

References 25 publications

Unraveling the Effectiveness of the K-Nn Algorithm for Imbalanced Data in Research Topic Recommendations

Unraveling the Effectiveness of the K-Nn Algorithm for Imbalanced Data in Research Topic Recommendations

Hybrid optimization-enabled deep Q network for fault prediction in service-oriented architecture

Analysis of Meta-Features in the Context of Adaptive Hybrid Recommendation Systems

Contact Info

Product

Resources

About