Abstract:In recent years, artificial intelligence has played an important role in education, wherein one of the most commonly used applications is forecasting students’ academic performance based on personal information such as social status, income, address, etc. This study proposes and develops an artificial neural network model capable of determining whether a student will pass a certain class without using personal or sensitive information that may compromise student privacy. For model training, we used information… Show more
“…In Addition, ref. [29] developed an artificial neural network designed to predict a student's likelihood of passing a specific course, importantly, without relying on personal or sensitive information that could infringe on student privacy. The model was trained using data from 32,000 students at The Open University in the United Kingdom, incorporating details such as the number of attempts at the course, the average number of assessments, the course pass rate, the average engagement with online materials, and the total number of clicks within the virtual learning environment.…”
Educational institutions are increasingly focused on supporting students who may be facing academic challenges, aiming to enhance their educational outcomes through targeted interventions. Within this framework, leveraging advanced deep learning techniques to develop recommendation systems becomes essential. These systems are designed to identify students at risk of underperforming by analyzing patterns in their historical academic data, thereby facilitating personalized support strategies. This research introduces an innovative deep learning model tailored for pinpointing students in need of academic assistance. Utilizing a Gated Recurrent Neural Network (GRU) architecture, the model is rich with features such as a dense layer, max-pooling layer, and the ADAM optimization method used to optimize performance. The effectiveness of this model was tested using a comprehensive dataset containing 15,165 records of student assessments collected across several academic institutions. A comparative analysis with existing educational recommendation models, like Recurrent Neural Network (RNN), AdaBoost, and Artificial Immune Recognition System v2, highlights the superior accuracy of the proposed GRU model, which achieved an impressive overall accuracy of 99.70%. This breakthrough underscores the model’s potential in aiding educational institutions to proactively support students, thereby mitigating the risks of underachievement and dropout.
“…In Addition, ref. [29] developed an artificial neural network designed to predict a student's likelihood of passing a specific course, importantly, without relying on personal or sensitive information that could infringe on student privacy. The model was trained using data from 32,000 students at The Open University in the United Kingdom, incorporating details such as the number of attempts at the course, the average number of assessments, the course pass rate, the average engagement with online materials, and the total number of clicks within the virtual learning environment.…”
Educational institutions are increasingly focused on supporting students who may be facing academic challenges, aiming to enhance their educational outcomes through targeted interventions. Within this framework, leveraging advanced deep learning techniques to develop recommendation systems becomes essential. These systems are designed to identify students at risk of underperforming by analyzing patterns in their historical academic data, thereby facilitating personalized support strategies. This research introduces an innovative deep learning model tailored for pinpointing students in need of academic assistance. Utilizing a Gated Recurrent Neural Network (GRU) architecture, the model is rich with features such as a dense layer, max-pooling layer, and the ADAM optimization method used to optimize performance. The effectiveness of this model was tested using a comprehensive dataset containing 15,165 records of student assessments collected across several academic institutions. A comparative analysis with existing educational recommendation models, like Recurrent Neural Network (RNN), AdaBoost, and Artificial Immune Recognition System v2, highlights the superior accuracy of the proposed GRU model, which achieved an impressive overall accuracy of 99.70%. This breakthrough underscores the model’s potential in aiding educational institutions to proactively support students, thereby mitigating the risks of underachievement and dropout.
“…Heyul Chavez et al [3] predicted students' academic performance using ANN. The system used the Open University of the United Kingdom dataset, which contains 32,000 student's data.…”
Section: Literature Reviewmentioning
confidence: 99%
“…Many ML methods are used to forecast student performance in online courses, including Random Forest (RF), Support Vector Machine (SVM), Naive Bayes (NB), and Logistic Regression (LR). It generates two sorts of output: pass, the learner will complete the course successfully, and fail, the learner might not [3]. Teachers can gain a better grasp of their data by utilizing ML techniques.…”
The virtual learning environment (VLE) is essential today and widely used globally for information exchange. Compared to in-person lectures, a VLE aids distant learning, although it might be challenging to maintain constant student interest. Academic activities are not actively pursued by students, which has an impact on their learning curves. The primary goal of this review is to impart a thorough knowledge and comprehension of various techniques, including machine learning (ML) and deep learning (DL), which are utilized for predicting student progress and performance and, consequently, how these prediction techniques help to find the most crucial student attribute for prediction. Additionally, this analysis reveals a rising trend in the volume and diversity of this field’s research. At the same time, the assessment revealed several problems with research quality that highlight the need for the community to strengthen efforts to validate and replicate work and to describe methods and outcomes in greater detail. It can help teachers, parents, students, and tutors decide on the appropriate learning support for their charges when taking online courses.
“…Another encouraging work on the development of a suitable neural network model to accurately predict the probability that a student will pass an examination can be seen to have used ten characteristic attributes as the input variables for a three-layer ANN (11) . The said model has no need to infringe students' personal information, but has successfully demonstrated that the ANN model is superior to Naïve Bayes algorithm, Decision trees/random forests or Support vector machine (SVM)/support vector regression (SVR) in terms of ability to predict the academic performance of students at 83% accuracy level.…”
Objective: To evaluate the capacity of artificial neural network modeling in quantification of relative contribution of various factors towards happiness index of university faculty members and to adjudge the degree of agreement with the results of descriptive statistical analysis under hard societal situation. Methods: A relational-research is conducted by descriptive statistics and ANN modeling with 93 variables, grouped into 24 major variables. The primary data are obtained through surveying after random convenient sampling with self-administered questionnaire based on five-point Likert scale. The study is conducted on 350 faculty members; 273 duly filled in questionnaires are received. The data stemming from varying perceptions of teachers is highly nonlinear. ANN is chosen for its capability to capture high nonlinearity; a gold standard method of comparison with learning tools like multiple regression or logistic regression reveals it superiority; sample size driven predictive uncertainty makes machine learning unsuitable. Findings: ANN modeling shows that the independent variable 'salary' has 46% negative weightage on attainment of happiness whereas, the given working condition related factors record a 45-48% weightage. Descriptive statistics corroborate ANN result, showing that salary, job satisfaction and work environment cause dissatisfaction by recording poor happiness index ~65%. Novelty: The novelty lies in implementation of ANN modeling on community survey generated data for identification of significant affecting happiness of faculty members. Consideration of 93 influencing factors grouped into 24 input variable and to examine if ANN prediction corroborates statistical test of significance adds credence to the novelty of the present approach hitherto unreported.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.