Identifying Technical and Vocational Education and Training (TVET) Sentiment from Social Media Using a Machine Learning Approach

Authors

DOI:

https://doi.org/10.31436/iiumej.v26i3.3739

Keywords:

TVET, Sentiment Analysis, Machine learning

Abstract

Technical and Vocational Education and Training (TVET) has become a key priority for the Malaysian government to enhance the system, better aligning it with industrial demands and workforce needs. The primary priority is to ensure that students and graduates acquire in-demand skills, thereby increasing their employability and creating more attractive job opportunities. Due to rapid technological advancements, social media has emerged as a powerful platform for public discourse where discussions on TVET programs, policies, and perceptions occur extensively. Among these platforms, Facebook is a widely used space for public interactions through posts and comments. This study employs sentiment analysis to analyse TVET-related discussions on Facebook, categorising sentiment into positive, neutral, and negative polarities. The Term Frequency-Inverse Document Frequency (TF-IDF) method is utilised to extract meaningful insights, and six classifiers, comprised of Support Vector Machine (SVM), Naïve Bayes (NB), Decision Tree (DT), Random Forest (RF), K-Nearest Neighbour (KNN), and Logistic Regression (LR), are applied. Using an 80%-20% training and testing split, results indicate that SVM achieves the highest accuracy performance, with a score of 0.62, outperforming other classifiers. Hence, this study provides valuable insights for policymakers and relevant stakeholders in the TVET ecosystem. By leveraging sentiment analysis and machine learning, decision-makers can better understand public perceptions and develop well-informed strategies to realign and enhance the TVET system.

ABSTRAK: Pendidikan dan Latihan Teknikal dan Vokasional (TVET) menjadi keutamaan kerajaan Malaysia bagi meningkatkan sistem agar lebih selaras dengan permintaan industri dan keperluan tenaga kerja.  Keutamaan ini adalah bagi memastikan pelajar dan graduan memperoleh kemahiran yang diperlukan, meningkatkan kebolehpekerjaan serta mewujudkan lebih banyak peluang pekerjaan. Kepesatan kemajuan teknologi menyebabkan media sosial muncul sebagai platfom berpengaruh bagi wacana awam di mana perbincangan mengenai program, dasar, dan persepsi TVET berlangsung secara meluas. Antara platfom tersebut, Facebook menjadi medium terbanyak digunakan bagi interaksi awam melalui hantaran dan komen.  Kajian ini menggunakan analisis sentimen bagi menganalisis perbincangan berkaitan TVET di Facebook dengan mengkategorikan sentimen kepada positif, neutral, dan negatif. Kaedah Frekuensi Dokumen Terma Frequency-Inverse (TF-IDF) digunakan bagi mengekstrak pandangan bermakna dan seterusnya menerapkan enam pengklasifikasi yang terdiri daripada Mesin Sokongan Vaktor (SVM), Naïve Bayes (NB), Pokok Keputusan (DT), Rawak Forest (RF), K-Nearest Neighbour (KNN), dan Regriasi Logistik (LR). Menggunakan peratusan data pembahagian latihan dan ujian sebanyak 80%-20%, dapatan kajian menunjukkan bahawa SVM mencapai prestasi ketepatan tertinggi dengan skor 0.62,  mengatasi pengklasifikasi lain. Oleh itu, kajian ini memberi pandangan berharga kepada penggubal dasar dan pihak berkepentingan dalam ekosistem TVET. Dengan memanfaatkan analisis sentimen dan pembelajaran mesin, penggubal dasar dapat memperoleh pemahaman mendalam tentang persepsi awam dan membangunkan strategi berinformasi bagi menyelaras dan meningkatkan sistem TVET.

Downloads

Download data is not yet available.

Metrics

Metrics Loading ...

Author Biography

Mira Kartiwi, International Islamic University Malaysia

Mira Kartiwi completed her studies at the University of Wollongong, Australia, resulting in the following degrees being conferred: Bachelor of Commerce ub Business Information Systems, Master of Information Systems and her PhD with a thesis "Electronic commerce adoption in urban and rural Indonesian SMEs". Currently, she is a full Professor in the Department of Information Systems, Kulliyyah of Information and Communication Technology, International Islamic University Malaysia (IIUM). She is also the Director for Centre for Professional Development in the IIUM.


Mira Kartiwi was one of the recipients of Australia Postgraduate Award (APA) in 2004. For her achievement in research, she was awarded the Higher Degree Research Award for Excellence in 2007. In 2011, Mira Kartiwi has been appointed as the Honorary Fellow at University of Wollongong, Australia. In this role, she has completed a number of research collaborations with researchers in the Business Faculty and SMART Infrastructure Facility.  and As acknowledgement for her expertise, she also has been appointed as Editorial Board member in local and international journals. She is also an experienced consultant specializing in financial and manufacturing sectors. Her areas of expertise include: health informatics, e-commerce, data mining, information systems strategy, business process improvement, product development, marketing, delivery strategy, workshop facilitation, training, and communications. Through her consultancy work, she has access to an extensive network of associate consultants and businesses.    Having completed several certifications in e-learning and data analytics, she is a certified Moodle Educator and a fellow and instructor for the Collaborative Online International Learning (COIL) program at Shenandoah University (Barzinji Project, USA). Through her COIL projects with various partner institutions, she promotes diverse viewpoints on course topics and global issues through data analytics, encouraging students to consider alternative perspectives and challenge their own assumptions.   In addition to her academic and industrial work, Mira Kartiwi is renowned as a passionate Cyberparenting activist. She works closely with schools and Muslim societies in Indonesia, Malaysia and Australia to provide awareness for parents and children on the risk of going online (Internet).

References

UNESCO-UNEVOC, “What is TVET??” Accessed: Apr. 04, 2022. [Online]. Available: https://unevoc.unesco.org/home/TVET&context=#ref1

Department of Polytechnic and Community College Education, Hala Tuju Transformasi Politeknik, First edition. Department of Polytechnic and Community College Education, 2024.

D. A. Dutta, “Impact of Digital Social Media on Indian Higher Education: Alternative Approaches of Online Learning during COVID-19 Pandemic Crisis,” International Journal of Scientific and Research Publications (IJSRP), vol. 10, no. 05, pp. 604–611, May 2020, doi: 10.29322/ijsrp.10.05.2020.p10169.

F. O. Nwokike, I. C. Ezeabii, and S. N. Oluka, “Social Media: A Platform for Effective Instructional Delivery of Technical and Vocational Education and Training (TVET) Programmes,” International Journal of Education, Learning and Development, vol. 9, no. 5, pp. 37–47, 2021, [Online]. Available: https://ssrn.com/abstract=3895718

S. Hashim, A. Masek, N. S. Abdullah, A. N. Paimin, and W. H. N. W. Muda, “Students’ intention to share information via social media: A case study of COVID-19 pandemic,” Indonesian Journal of Science and Technology, vol. 5, no. 2, pp. 236–245, 2020, doi: 10.17509/ijost.v5i2.24586.

M. Mujahid et al., “Sentiment analysis and topic modeling on tweets about online education during covid-19,” Applied Sciences (Switzerland), vol. 11, no. 18, Sep. 2021, doi: 10.3390/app11188438.

F. S. Dolianiti, D. Iakovakis, S. B. Dias, S. Hadjileontiadou, J. A. Diniz, and L. Hadjileontiadis, “Sentiment analysis techniques and applications in education: A survey,” Communications in Computer and Information Science, vol. 993, pp. 412–427, 2019, doi: 10.1007/978-3-030-20954-4_31.

R. Hermansyah and R. Sarno, “Sentiment Analysis about Product and Service Evaluation of PT Telekomunikasi Indonesia Tbk from Tweets Using TextBlob, Naive Bayes & K-NN Method,” in International Seminar on Application for Technology of Information and Communication (iSemantic), 2020, pp. 511–516.

N. A. Rahman, S. D. Idrus, and N. L. Adam, “Classification of customer feedbacks using sentiment analysis towards mobile banking applications,” IAES International Journal of Artificial Intelligence, vol. 11, no. 4, pp. 1579–1587, Dec. 2022, doi: 10.11591/ijai.v11.i4.pp1579-1587.

A. Padwal and R. Koshy, “A Hybrid Approach to Predict Election Candidate Success Using Candidate Speech and Voter Opinion,” in Proceedings - International Conference on Communication, Information and Computing Technology, ICCICT 2021, Institute of Electrical and Electronics Engineers Inc., 2021. doi: 10.1109/ICCICT50803.2021.9510167.

M. S. Shallan, I. F. Moawad, R. El Naggar, and H. Montasser, “Using Machine Learning Techniques to Maximize Profitability in the Hospitality Industry,” in 6th International Conference on Computing and Informatics, ICCI 2024, Institute of Electrical and Electronics Engineers Inc., 2024, pp. 182–188. doi: 10.1109/ICCI61671.2024.10485148.

Q. A. B. K. Zaman, W. N. S. B. W. Yusoff, and Q. B. B. A. Shah, “Sentiment Analysis on The Place of Interest in Malaysia,” Journal of Advanced Research in Applied Sciences and Engineering Technology, vol. 43, no. 1, pp. 54–65, Jan. 2025, doi: 10.37934/araset.43.1.5465.

S. Madarbakus, A. Gobin, and R. K. Sungkur, “Using Sentiment Analysis and Machine Learning to Collect the Perception of Online Learning,” in 2023 Advances in Science and Engineering Technology International Conferences, ASET 2023, Institute of Electrical and Electronics Engineers Inc., 2023. doi: 10.1109/ASET56582.2023.10180757.

J. Jünger and T. Keyling, “Facepager. An application for automated data retrieval on the web. Source code and releases available at https://github.com/strohne/Facepager/.”

M. Stanley, K. R. Aiswarya, and G. Deepa, “Sentiment Analysis of Covid Vaccine Tweet with Vader, and Implementation of Different Machine Learning Models,” in 2023 14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023, Institute of Electrical and Electronics Engineers Inc., 2023. doi: 10.1109/ICCCNT56998.2023.10308224.

M. Edalati, A. Shariq Imran, Z. Kastrati, and S. M. Daudpota, “The Potential of Machine Learning Algorithms for Sentiment Classification of Students’ Feedback on MOOC,” 2022.

A. A. Reshi et al., “COVID-19 Vaccination-Related Sentiments Analysis: A Case Study Using Worldwide Twitter Dataset,” Healthcare, vol. 10, no. 3, Mar. 2022, doi: 10.3390/healthcare10030411.

Downloads

Published

2025-09-09

How to Cite

Sharin, N. H., & Kartiwi, M. (2025). Identifying Technical and Vocational Education and Training (TVET) Sentiment from Social Media Using a Machine Learning Approach. IIUM Engineering Journal, 26(3), 295–303. https://doi.org/10.31436/iiumej.v26i3.3739

Issue

Section

Electrical, Computer and Communications Engineering

Similar Articles

You may also start an advanced similarity search for this article.