Improving the expressiveness of black-box models for predicting student performance

Villagr-Arnedo, Carlos J.; Gallego-Durn, Francisco J.; Largo, Faraón Llorens; Compa-Rosique, Patricia; Cuerda, Rosana Satorre; Molina-Carmona, Rafael

doi:10.1016/j.chb.2016.09.001

Cited by 43 publications

(18 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Для разрешения многогранной проблемы выполнения ОУ ВО заданий по подготовке специалистов используются различные приемы и методы: построение статистической модели выбытия студентов [27] и модели с использованием уровней отсева [7], многомерная шкала успеваемости учащихся [28], прогнозирование успеваемости учащихся [29], анализ события отчисления студента [6].…”

Section: обзор литературыunclassified

Methods for Optimization of Student’s Number in Higher Educational Institutions

Bokarev¹,

Denisova²,

Dobrenko³

et al. 2018

IntegrEdu

View full text Add to dashboard Cite

Introduction. The article deals with implementation of tasks of specialists’ training by universities. The relevance is determined by a dropout trends in training years. The authors analyze the results of the specialists’ training and graduation; also they determine the goal and objectives of the research. The study purpose is to identify specialists’ training patterns and to develop methods to optimize the students’ number in training years according to the final results. Materials and Methods. Results of training and graduates’ number for 2012-2017 comprised material for the study. An approach to provide management of assignment for higher education professionals training has been developed, and it is the students’ number optimization methodology in years of study according to the final results. It links initial and final results into one line and predicts intermediate results that ensure fulfillment of graduates’ training orders not lower than the established final results. The following general scientific methods are used in the article: compilation, benchmarking, synthesis and normative forecasting. Results. Optimization methodologies in years of education concerning the final results were tested. The findings showed that the final result directly depends on the intermediate results; the students’ number decline can be brought to optimal values if initial and final results are determined and linked with each other. Discussion and Conclusion. The possibility to bring students’ number reduction into line with optimal values is proved theoretically and practically if the forecast of graduation is provided. Thus the forecast of optimal intermediate results is the main link for educational management methods development for specialists’ training tasks. It is an area for further research. The contribution to science consists in the development of methods for predicting the optimal number of students in the year regarding to the final result. The article’s materials will be useful to the permanent composition of professional educational institutions for the development of measures tar geted control in the educational process. Keywords: assignment on specialists’ training, students’ drop out, trends in specialists’ training, specialists’ graduation, optimization of students’ number Acknowledgments: The work was carried out within the research project “Quality management of professional education based on new information technologies”. The authors are grateful to the anonymous reviewer.

show abstract

Section: обзор литературыunclassified

Methods for Optimization of Student’s Number in Higher Educational Institutions

Bokarev¹,

Denisova²,

Dobrenko³

et al. 2018

IntegrEdu

View full text Add to dashboard Cite

show abstract

“…Unlike classroom teaching, e-Learning courses have specific characteristics such as the transactional distance between actors (educators and students) and the use of learning platforms, called as Learning Management System (LMS) or Massive Open Online Courses (MOOC). This transactional distance presents challenges in the teaching process such as: i) the lack of information about the students' real academic progress, ii) the attempt to predict the result of the students' academic performance, iii) the difficulty in making pedagogical decisions due to the low support of Information Systems, iv) the difficulty in keeping the student engaged, and v) high dropout rates (Yago et al, 2018;Villagra-Arnedo et al, 2017;Iglesias-Prada et al, 2015). Thus, researchers are making an effort to minimize such challenges using computational resources applied to the educational context.…”

Section: Introductionmentioning

confidence: 99%

Monitoring Academic Performance Based on Learning Analytics and Ontology: A Systematic Review

Costa¹,

Sanches²,

Amorim³

et al. 2020

Informatics in Education

View full text Add to dashboard Cite

This paper presents a systematic literature review of the coordinated use of Learning Analytics and Computational Ontologies to support educators in the process of academic performance evaluation of students. The aim is to provide a general overview for researchers about the current state of this relationship between Learning Analytics and Ontologies, and how they have been applied in a coordinated way. We selected 31 of a total of 1230 studies related to the research questions. The retrieved studies were analyzed from two perspectives: first, we analyzed the approaches where researchers used Learning Analytics and Ontologies in a coordinated way to describe some Taxonomy of Educational Objectives; In the second perspective, we seek to identify which models or methods have been used as an analytical tool for educational data. The results of this review suggest that: 1) few studies consider that student interactions in the Learning Management System can represent students' learning experiences; 2) most studies use ontologies in the context of learning object assessment to enable learning sequencing; 3) we did not identify methods of evaluation of academic performance guided by Taxonomies of Educational Objectives; and 4) no studies were identified that report the coordinated use of Learning Analytics and Computational Ontologies, in the context of academic performance monitoring. Thus, we identify future directions of research such as the proposal of a new model of evaluation of academic performance.

show abstract

“…Predicting student performance at an early stage is very beneficial in figuring out weak students (Pandey & Taruna, 2016) and permits academic establishments to provide suitable support for students who face difficulties (Altujjar et al, 2016). Prediction models are used to detect trends and Detecting trends and patterns of behavior in learning problems can be identified using prediction methods (Villagrá-Arnedo et al, 2017). Many factors other than academic factors are taken into consideration in constructing student performance prediction models, such as psychological, social, and demographic factors (Altujjar et al, 2016).…”

Section: Introductionmentioning

confidence: 99%

Implementation of Gain Ratio and K-Nearest Neighbor for Classification of Student Performance

Setiyorini

Asmono²

2020

pilar

View full text Add to dashboard Cite

Predicting student performance is very useful in analyzing weak students and providing support to students who face difficulties. However, the work done by educators has not been effective enough in identifying factors that affect student performance. The main predictor factor is an informative student academic score, but that alone is not good enough in predicting student performance. Educators utilize Educational Data Mining (EDM) to predict student performance. KK-Nearest Neighbor is often used in classifying student performance because of its simplicity, but the K-Nearest Neighbor has a weakness in terms of the high dimensional features. To overcome these weaknesses, a Gain Ratio is used to reduce the high dimension of features. The experiment has been carried out 10 times with the value of k is 1 to 10 using the student performance dataset. The results of these experiments are obtained an average accuracy of 74.068 with the K-Nearest Neighbor and obtained an average accuracy of 75.105 with the Gain Ratio and K-Nearest Neighbor. The experimental results show that Gain Ratio is able to reduce the high dimensions of features that are a weakness of K-Nearest Neighbor, so the implementation of Gain Ratio and K-Nearest Neighbor can increase the accuracy of the classification of student performance compared to using the K-Nearest Neighbor alone.

show abstract

Improving the expressiveness of black-box models for predicting student performance

Cited by 43 publications

References 22 publications

Methods for Optimization of Student’s Number in Higher Educational Institutions

Methods for Optimization of Student’s Number in Higher Educational Institutions

Monitoring Academic Performance Based on Learning Analytics and Ontology: A Systematic Review

Implementation of Gain Ratio and K-Nearest Neighbor for Classification of Student Performance

Contact Info

Product

Resources

About