Associating students and teachers for tutoring in higher education using clustering and data mining

Group work is a prevalent activity in educational settings, where students are often divided into topic-specific groups based on their preferences. The grouping should reflect students’ aspirations as much as possible. Usually, the resulting groups should also be balanced in terms of protected attributes like gender, as studies suggest that students may learn better in mixed-gender groups. Moreover, to allow a fair workload across the groups, the cardinalities of the different groups should be balanced. In this paper, we introduce a multi-fair capacitated (MFC) grouping problem that fairly partitions students into non-overlapping groups while ensuring balanced group cardinalities (with a lower and an upper bound), and maximizing the diversity of members regarding the protected attribute. To obtain the MFC grouping, we propose three approaches: a greedy heuristic approach, a knapsack-based approach using vanilla maximal knapsack formulation, and an MFC knapsack approach based on group fairness knapsack formulation. Experimental results on a real dataset and a semi-synthetic dataset show that our proposed methods can satisfy students’ preferences and deliver balanced and diverse groups regarding cardinality and the protected attribute, respectively.

show abstract

“…. , 18), as the average number of students per group should not exceed 20 [21]. The upper bound C u is set as C u = C l + 1 for all datasets.…”

Section: Methodsmentioning

confidence: 99%

Multi-fair Capacitated Students-Topics Grouping Problem

Quy

Friege

Ntoutsi

2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…The problem around which the data preprocessing revolves is the different search strategies such as sequential, random, and complete that are proposed for this task. The evaluation criterion is set with filtering (distance, information, dependency, and consistency), hybrid and wrapper methods [50][51][52][53][54]. Undirected graph calculated from the correlation matrix (Pearson's method).…”

Section: Data Preprocessingmentioning

confidence: 99%

Predicting Academic Success of College Students Using Machine Learning Techniques

Guanin-Fajardo,

Guaña-Moya,

Casillas

2024

Data

View full text Add to dashboard Cite

College context and academic performance are important determinants of academic success; using students’ prior experience with machine learning techniques to predict academic success before the end of the first year reinforces college self-efficacy. Dropout prediction is related to student retention and has been studied extensively in recent work; however, there is little literature on predicting academic success using educational machine learning. For this reason, CRISP-DM methodology was applied to extract relevant knowledge and features from the data. The dataset examined consists of 6690 records and 21 variables with academic and socioeconomic information. Preprocessing techniques and classification algorithms were analyzed. The area under the curve was used to measure the effectiveness of the algorithm; XGBoost had an AUC = 87.75% and correctly classified eight out of ten cases, while the decision tree improved interpretation with ten rules in seven out of ten cases. Recognizing the gaps in the study and that on-time completion of college consolidates college self-efficacy, creating intervention and support strategies to retain students is a priority for decision makers. Assessing the fairness and discrimination of the algorithms was the main limitation of this work. In the future, we intend to apply the extracted knowledge and learn about its influence of on university management.

show abstract

“…However, this study does not guarantee a unique result because it is dependent on the variables used and the characteristics of the subjects. Clustering is a statistical procedure that classifies various objects into clusters or groups that exhibit similarities within a group and differences from different groups [9]. The K-Means algorithm groups several items into user-defined clusters [10].…”

Section: Introductionmentioning

confidence: 99%

Cluster Analysis of Learning Management System (LMS) Performance : A Diagnostic Assessment

Manaligod¹,

Cano²,

Enriquez³

2022

Ijasc

View full text Add to dashboard Cite

Background/Objective. The COVID-19 has accelerated the conduct of online classes around the world. To administer distant learning, schools are now relying on learning management systems. With the problems of the abrupt shift to an online modality, there must be measures in place to cluster students' characteristics in order to assist their learning requirements, struggles, and academic performances. Methods/Statistical Analysis. Based on Delone and McLean's IS Success model, this study used quantitative approaches and exploratory techniques to explain the higher education learners' clusters. From March to April 2021, 303 samples were randomly selected from students participating in online programs at a higher education school on Taft Avenue in Manila. Sex, school, frequency of use, time duration, and experience with the LMS were all factors in the study. Both Hierarchical Cluster Analysis and K-Means Cluster Analysis were used to classify the samples. Findings. The results revealed that there are four clusters formed which are labeled as: service-oriented, system quality-oriented, holistic-oriented, and LMS-averse. Based on the results, information quality has the greatest influence. Since the clustering analysis is non-inferential and it is used as an exploratory technique, the researchers do not guarantee a unique solution as this depends on the elements of the subjects and the variables used. Improvements/Applications. The academic stakeholders can use the cluster analysis to make the appropriate interventions to improve the online course content and enhance the students' academic performance. Some of these appropriate interventions include creating course policies, planning the necessary training of teachers and students, and developing the online delivery of the lessons.

show abstract

Associating students and teachers for tutoring in higher education using clustering and data mining

Cited by 15 publications

References 16 publications

Multi-fair Capacitated Students-Topics Grouping Problem

Multi-fair Capacitated Students-Topics Grouping Problem

Predicting Academic Success of College Students Using Machine Learning Techniques

Cluster Analysis of Learning Management System (LMS) Performance : A Diagnostic Assessment

Contact Info

Product

Resources

About