The Estimation of Students' Academic Success by Data Mining Methods

Göker, Hanife; Bülbül, Halil İbrahim; Irmak, Erdal

doi:10.1109/icmla.2013.173

Cited by 14 publications

(4 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the dynamic expert system developed, the results of the most commonly used classification algorithms according to the model performance criteria (K-The Nearest Neighbor (k-NN), Decision Trees (J48), Sequential Minimal Optimization Algorithm (SMO) and RBF Network) [57] are given in Table 1: The values of TP rate, recall, precision and f-measure, among the model performance criteria, are desired to be close to 1, such as the ROC area value [29][30]58]. When the comparison table is examined, it is observed that the ROC area, TP rate, recall, precision and f-measure values of all algorithms are greater than 0.80.…”

Section: Resultsmentioning

confidence: 99%

Dynamic Expert System Design for the Prediction of Attention Deficit and Hyperactivity Disorder in Childhood

Göker¹,

Tekedere

2019

Bilişim Teknolojileri Dergisi

View full text Add to dashboard Cite

In this study, for the first time, a Dynamic Expert System was developed to predict attention deficit and hyperactivity impairment in childhood. In this context, the decision-making process, which requires complex and experienced field experts to diagnose the disease, has been transferred to the developed expert system. The subject of the study was determined as prediction of attention deficit and hyperactivity disorder, which is one of the most common psychiatric disorders of childhood. The developed Dynamic Expert System consists of three basic parts, which are the knowledge base, the inference mechanism and the description unit. Data clusters are recorded as attributes and records in the knowledge base. While attributes are determined by field experts, records are composed of clinical patient data received from the Gazi Hospital, Department of Pediatric Mental Health and Diseases. Ensuring the dynamic renewal of the rule base is the most important characteristic of the study using the Naive Bayes Algorithm in the inference mechanism of the developed system. In this way, when the system encounters a new situation that is not previously encountered, it can take advantage of the existing rules and guess which class the rule belongs to. With real data, the system has been trained; and its performance was tested. As a result of this study, accuracy was determined to be 88.62%; precision was determined to be 89.2%, recall was determined to be 88.6%, f-measure was determined to be 88.6% and ROC area value was determined to be 89.8%. It was observed that the performance of the system was quite high compared to the model performance criteria.

show abstract

Section: Resultsmentioning

confidence: 99%

Dynamic Expert System Design for the Prediction of Attention Deficit and Hyperactivity Disorder in Childhood

Göker¹,

Tekedere

2019

Bilişim Teknolojileri Dergisi

View full text Add to dashboard Cite

show abstract

“…EDM research studies have explored the performance of different statistical and machine learning models for prediction tasks, such as artificial neural networks, decision trees, logistic regression, Naïve Bayes, Bayesian networks, vector support machines, extreme learning machines, k-nearest neighbor, k-means clumping algorithm, J48, zeroR, random trees [22][23][24][25][26][27][28][29][30][31]. The most accurate predictions have been achieved with vector support machine models, k-nearest neighbor, artificial neural networks, Naïve Bayes and random forest.…”

Section: Educational Data Mining (Edm)mentioning

confidence: 99%

Predicting students’ academic progress and related attributes in first-year medical students: an analysis with artificial neural networks and Naïve Bayes

Monteverde-Suárez,

González-Flores,

Santos-Solórzano

et al. 2024

BMC Med Educ

View full text Add to dashboard Cite

Background Dropout and poor academic performance are persistent problems in medical schools in emerging economies. Identifying at-risk students early and knowing the factors that contribute to their success would be useful for designing educational interventions. Educational Data Mining (EDM) methods can identify students at risk of poor academic progress and dropping out. The main goal of this study was to use machine learning models, Artificial Neural Networks (ANN) and Naïve Bayes (NB), to identify first year medical students that succeed academically, using sociodemographic data and academic history. Methods Data from seven cohorts (2011 to 2017) of admitted medical students to the National Autonomous University of Mexico (UNAM) Faculty of Medicine in Mexico City were analysed. Data from 7,976 students (2011 to 2017 cohorts) of the program were included. Information from admission diagnostic exam results, academic history, sociodemographic characteristics and family environment was used. The main dataset included 48 variables. The study followed the general knowledge discovery process: pre-processing, data analysis, and validation. Artificial Neural Networks (ANN) and Naïve Bayes (NB) models were used for data mining analysis. Results ANNs models had slightly better performance in accuracy, sensitivity, and specificity. Both models had better sensitivity when classifying regular students and better specificity when classifying irregular students. Of the 25 variables with highest predictive value in the Naïve Bayes model, percentage of correct answers in the diagnostic exam was the best variable. Conclusions Both ANN and Naïve Bayes methods can be useful for predicting medical students’ academic achievement in an undergraduate program, based on information of their prior knowledge and socio-demographic factors. Although ANN offered slightly superior results, Naïve Bayes made it possible to obtain an in-depth analysis of how the different variables influenced the model. The use of educational data mining techniques and machine learning classification techniques have potential in medical education.

show abstract

“…However, the success of this project is unknown. As Göker, Bülbül [36] mentioned that a database, which contains students' demographic, personal, and academic score information, is a warning system to predict students' academic success and any barriers to the same. Capturing valuable information in a structured, normalized method is important to maximize the benefits of the student database.…”

Section: Related Studymentioning

confidence: 99%

The Role of Global Educational Database in Educational Data Mining

Banerjee

2018

EJENG

View full text Add to dashboard Cite

Educational Data Mining is one of the major on-going research platforms now. Students’ records need to be maintained and analyzed in a manner so that they can be utilized to predict students’ behavior and learning methods. Although students’ academic records need to be processed and analyzed through data mining tools, the primary challenge is to gather individual academic student details. This paper proposes a global database of students irrespective of geographical boundaries. Academic performance of every student from every country will be updated in this platform. Students’ performance on major examinations will be available in the database. Supporting documents and performance details will be readily available and accessible to the evaluators from any geographic location. This will be helpful to standardize the evaluation process and analyze the performance of a student, irrespective of geographic boundaries. The following paper will discuss the available EDM tools and how data can be analyzed to extract information.

show abstract

The Estimation of Students' Academic Success by Data Mining Methods

Cited by 14 publications

References 1 publication

Dynamic Expert System Design for the Prediction of Attention Deficit and Hyperactivity Disorder in Childhood

Dynamic Expert System Design for the Prediction of Attention Deficit and Hyperactivity Disorder in Childhood

Predicting students’ academic progress and related attributes in first-year medical students: an analysis with artificial neural networks and Naïve Bayes

The Role of Global Educational Database in Educational Data Mining

Contact Info

Product

Resources

About