A semi-supervised learning approach for predicting student's performance: First-year students case study

Yekti Widyaningsih, Nur Fitriani, Devvi Sarwinda

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Students performance is an essential part of a higher learning institution because one of the criteria for a high -quality university is based on its excellent record of academic achievements. The first-year of the lecture is the student period of laying the foundation that will affect academic success because first-year plays an important role in shaping the attitudes and performance of students in the following years. In this study, a semi-supervised learning approach is used to classify the performance of first-year students in the Department of Mathematics, Universitas Indonesia. Student performance will be divided into two categories, namely medium and high. The sample in this study consist of 140 first-year students with 27 features. There are two processes used i.e. clustering and the classification process. In the clustering process, the data is divided into three clusters using K-Means Clustering and the Naïve Bayes Classifier is chosen to classify it. The performance of the proposed algorithms is stated by accuracy, sensitivity, and specificity value i.e. 96%, 92.86%, and 100% respectively.

Original languageEnglish
Title of host publicationProceedings of 2019 International Conference on Information and Communication Technology and Systems, ICTS 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages291-295
Number of pages5
ISBN (Electronic)9781728121338
DOIs
Publication statusPublished - 1 Jul 2019
Event12th International Conference on Information and Communication Technology and Systems, ICTS 2019 - Surabaya, Indonesia
Duration: 18 Jul 2019 → …

Publication series

NameProceedings of 2019 International Conference on Information and Communication Technology and Systems, ICTS 2019

Conference

Conference12th International Conference on Information and Communication Technology and Systems, ICTS 2019
CountryIndonesia
CitySurabaya
Period18/07/19 → …

Keywords

  • K-Means Clustering
  • Naïve Bayes Classifier
  • Semi-supervised Learning
  • Student Performance

Fingerprint Dive into the research topics of 'A semi-supervised learning approach for predicting student's performance: First-year students case study'. Together they form a unique fingerprint.

Cite this