Predicting Students Grades Using Artificial Neural Networks and Support Vector Machine

Umair, Sajid; Sharif, Muhammad Majid

doi:10.4018/978-1-5225-2255-3.ch449

Cited by 16 publications

(4 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Al-Barak et al applied decision trees for grade prediction by using students' transcript data [2]. Umair et al used Support Vector Machines (SVMs) to select key training instances for grade prediction [35].…”

Section: Student Performance Predictionmentioning

confidence: 99%

Reliable Deep Grade Prediction with Uncertainty Estimation

Rangwala

2019

Proceedings of the 9th International Conference on Learning Analytics &Amp; Knowledge

View full text Add to dashboard Cite

Currently, college-going students are taking longer to graduate than their parental generations. Further, in the United States, the six-year graduation rate has been 59% for decades. Improving the educational quality by training better-prepared students who can successfully graduate in a timely manner is critical. Accurately predicting students' grades in future courses has attracted much attention as it can help identify at-risk students early so that personalized feedback can be provided to them on time by advisors. Prior research on students' grade prediction include shallow linear models; however, students' learning is a highly complex process that involves the accumulation of knowledge across a sequence of courses that can not be sufficiently modeled by these linear models. In addition to that, prior approaches focus on prediction accuracy without considering prediction uncertainty, which is essential for advising and decision making. In this work, we present two types of Bayesian deep learning models for grade prediction under a course-specific framework: i)Multilayer Perceptron (MLP) and ii) Recurrent Neural Network (RNN). These course-specific models are based on the assumption that prior courses can provide students with knowledge for future courses so that grades of prior courses can be used to predict grades in a future course. The MLP ignores the temporal dynamics of students' knowledge evolution. Hence, we propose RNN for students' performance prediction. To evaluate the performance of the proposed models, we performed extensive experiments on data collected from a large public university. The experimental results show that the proposed models achieve better performance than prior state-of-the-art approaches. Besides more accurate results, Bayesian deep learning models estimate uncertainty associated with the predictions. We explore how uncertainty estimation can be applied towards developing a reliable educational early warning system. In addition to uncertainty, we also develop an approach to explain the prediction results, which is useful for advisors to provide personalized feedback to students.

show abstract

Section: Student Performance Predictionmentioning

confidence: 99%

Reliable Deep Grade Prediction with Uncertainty Estimation

Rangwala

2019

Proceedings of the 9th International Conference on Learning Analytics &Amp; Knowledge

View full text Add to dashboard Cite

show abstract

“…From Literature, classifications and predictive techniques are the most appropriate method to gather the aforementioned information. Some of the classification techniques used for prediction are: i. the use of SVM for prediction in medical sciences and education [19] [18] [17].…”

Section: Literature Reviewmentioning

confidence: 99%

Predicting Media Literacy Level of Secondary School Students in Fiji

Reddy

Chaudhary

Sharma

2019

2019 IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE)

View full text Add to dashboard Cite

The digital revolution has set a platform for all the information and means of communication to be digitised, thus creating a digital media society. This explosion of digital media requires individuals to have a set of skills and knowledge to survive in this lifelong digital media society. In such a context, many countries around the world are now leveraging on Media Literacy to enhance the necessary skills of individuals and improve upon responsible media engagement. Therefore, predicting media literacy of students is essential so that suitable interventions can be put in place. This paper presents an analysis of Media Literacy status of Year 12 and Year 13 students at randomly selected secondary schools in Fiji, and it presents a set of predictive models using classification techniques. A quantitative study using a reliable survey was conducted to determine the Media Literacy of students using a Likert scale of 1-5. The analysis for this study was using the R software whereby classification algorithms such as Random Forest Classifiers, Decision Trees and Support Vector Machine Algorithm (SVM) were used to build the predictive models. These models will be used to derive appropriate interventions to improve Media Literacy of students. The baseline data from the study provide information on media literacy of Fijian students. The paper concludes with the important attributes that contribute towards an individual's competency on media literacy.

show abstract

“…There have been many studies on text processing in the World using the SVM achieving many positive results, such as: In the education data mining technique, (Umair & Sharif, 2018) predicted students' performance on the basis of their habits and comments; Stock price prediction (Madge & Bhatt, 2015) used daily closing prices for 34 technology stocks to calculate price volatility and strong momentum for individual stocks and for the overall sector. Ehrentraut, Ekholm, and Tan (2018) built a surveillance system that reliably detects all patient records of who have potentially hospital-acquired infections to reduce the burden of having the hospital staff manually check patient records.…”

Section: Related Workmentioning

confidence: 99%

Text Classification Based on Support Vector Machine

Nguyện¹

2019

DLU JOS

View full text Add to dashboard Cite

Sự phát triển của Internet làm cho thông tin lưu trữ trực tuyến hàng ngày gia tăng nhanh chóng. Do vậy, để tìm đúng thông tin mà chúng ta cần quan tâm thì mất khá nhiều thời gian nên cần phải dùng những kỹ thuật tổ chức và xử lý dữ liệu về văn bản. Kỹ thuật này được gọi là phân lớp văn bản hay nói cách khác là phân loại văn bản. Đã có rất nhiều phương pháp nghiên cứu về phân loại văn bản nhưng trong bài viết này chúng tôi tìm hiểu và áp dụng phương pháp Support Vector Machine và so sánh hiệu quả của nó với phương pháp phân loại theo xác suất Naïve Bayes. Ngoài ra, trước khi thực hiện phân lớp chúng tôi thực hiện các bước tiền xử lý bằng cách trích xuất các từ khóa đặc trưng với kỹ thuật giảm chiều tập huấn luyện nhằm làm giảm thời gian trong quá trình phân lớp.

show abstract

Predicting Students Grades Using Artificial Neural Networks and Support Vector Machine

Cited by 16 publications

References 21 publications

Reliable Deep Grade Prediction with Uncertainty Estimation

Reliable Deep Grade Prediction with Uncertainty Estimation

Predicting Media Literacy Level of Secondary School Students in Fiji

Text Classification Based on Support Vector Machine

Contact Info

Product

Resources

About