Sentiment Prediction Based on Deep Learning for Intelligent E-Learning Systems
Corressponding author's email:
dunghv@hcmute.edu.vnDOI:
https://doi.org/10.54644/jte.2025.1661Keywords:
BERT model, Feedback information, Intelligent e-learning systems, Machine learning, RoBERTa, Sentiment analysisAbstract
Sentiment analysis on feedback information plays a crucial role in intelligent e-learning systems (IES). To enhance customer service quality through reviews, predicting sentiment polarity is crucial. This paper focuses on integrating sentiment analysis into an online programming course in intelligent e-learning systems to better understand the challenges faced by students. E-learning platforms, typically web-based, are vital for reflecting users’ experiences, emotions, and purchase intentions. Recently, sentiment analysis systems have frequently been used on popular platforms like Facebook and Twitter, helping companies identify potential customers across different segments. Utilizing sentiment analysis assists in making informed product adjustments to meet user satisfaction. Our approach employs modern frameworks to build deep learning models, specifically leveraging the pre-trained RoBERTa model. We integrate this into a website application with a Django back-end, facilitating an easy implementation of RoBERTa into an API that communicates with Next.js, a cutting-edge framework for full-stack developers. This combination ensures optimal performance for the user experience and scalability of the project. Experimental results demonstrate that incorporating sentiment analysis into websites significantly enhances trust among users in e-learning systems.
Downloads: 0
References
P. K. Sari, A. Alamsyah, and S. Wibowo, “Measuring e-commerce service quality from online customer review using sentiment analysis,” J. Phys.: Conf. Ser., vol. 971, p. 012053, 2018, doi: 10.1088/1742-6596/971/1/012053. DOI: https://doi.org/10.1088/1742-6596/971/1/012053
L. Yang, Y. Li, J. Wang, and R. S. Sherratt, “Sentiment analysis for e-commerce product reviews in Chinese based on sentiment lexicon and deep learning,” IEEE Access, vol. 8, pp. 23522–30, 2022, doi: 10.1109/ACCESS.2020.2969854. DOI: https://doi.org/10.1109/ACCESS.2020.2969854
M. Demircan, A. Seller, F. Abut, and M. F. Akay, “Developing Turkish sentiment analysis models using machine learning and e-commerce data,” Int. J. Cogn. Comput. Eng., vol. 2, pp. 202–207, 2021. DOI: https://doi.org/10.1016/j.ijcce.2021.11.003
L. de Bruin, “Exploring the sentiment analysis performance of BERT models on domain-specific Twitter data when combined with an intelligent pre-processor,” Bachelor thesis, Radboud University, Netherlands, 2022.
E. Alzahrani and L. Jololian, “How different text-preprocessing techniques using the BERT model affect the gender profiling of authors,” arXiv, vol. 10, p. 48550, 2021, doi: arXiv:2109.13890. DOI: https://doi.org/10.5121/csit.2021.111501
M. Bilal and A. A. Almazroi, “Effectiveness of fine-tuned BERT model in the classification of helpful and unhelpful online customer reviews,” Electron. Commer. Res., vol. 23, pp. 2737–57, 2023, doi: 10.1007/s10660-022-09560-w. DOI: https://doi.org/10.1007/s10660-022-09560-w
A. Vaswani, N. Shazeer, N. Parmar, et al., “Attention is all you need,” in Adv. Neural Inf. Process. Syst. 30 (NIPS 2017), U. von Luxburg et al., Eds. Long Beach, CA, USA: NIPS Foundation, 2017, pp. 5998–6008.
H. N. Tran and U. Kruschwitz, “UR-IW-HNT at GermEval 2021: an ensembling strategy with multiple BERT models,” arXiv, vol. 10, p. 48550, 2021, doi: 2110.02042.
E. Hassan, T. Abd El-Hafeez, and M. Y. Shams, “Optimizing classification of diseases through language model analysis of symptoms,” Sci. Rep., vol. 14, p. 1507, 2024, doi: 10.1038/s41598-024-51615-5. DOI: https://doi.org/10.1038/s41598-024-51615-5
W. Yu, B. T. Boenninghoff, and D. Kolossa, “BERT-based ironic authors profiling,” CEUR Workshop Proc., vol. 3180, pp. 2720–2733, 2022.
R. Qasim, W. H. Bangyal, M. A. Alqarni, and A. A. Almazroi, “A fine-tuned BERT-based transfer learning approach for text classification,” J. Healthc. Eng., Jan. 7, 2022, doi: 10.1155/2022/3498123. DOI: https://doi.org/10.1155/2022/3498123
D. T. Bui, B. Pradhan, O. Lofman, I. Revhaug, and O. B. Dick, “Landslide susceptibility mapping at Hoa Binh province (Vietnam) using an adaptive neuro-fuzzy inference system and GIS,” Comput. Geosci., vol. 45, pp. 199–211, 2012, doi: 10.1016/j.cageo.2011.10.031. DOI: https://doi.org/10.1016/j.cageo.2011.10.031
K. Taalab, T. Cheng, and Y. Zhang, “Mapping landslide susceptibility and types using Random Forest,” Big Earth Data, vol. 2, pp. 159–178, 2018, doi: 10.1080/20964471.2018.1472392. DOI: https://doi.org/10.1080/20964471.2018.1472392
A. Hasan, S. Moin, A. Karim, and S. Shamshirband, “Machine learning-based sentiment analysis for Twitter accounts,” Math. Comput. Appl., vol. 23, p. 11, 2018, doi: 10.3390/mca23010011. DOI: https://doi.org/10.3390/mca23010011
S. Vijayaraghavan and D. Basu, “Sentiment analysis in drug reviews using supervised machine learning algorithms,” arXiv, 2020, doi: arXiv:2003.11643.
C. Qi, A. Fourie, Q. Chen, and Q. Zhang, “A strength prediction model using artificial intelligence for recycling waste tailings as cemented paste backfill,” J. Clean. Prod., vol. 183, pp. 566–578, 2018, doi: 10.1016/j.jclepro.2018.02.154. DOI: https://doi.org/10.1016/j.jclepro.2018.02.154
A. T. P. Nguyen, V. D. Hoang, et al., “Development of Code Evaluation System based on Abstract Syntax Tree,” J. Tech. Educ. Sci., vol. 19, pp. 15–24, 2024, doi: 10.54644/jte.2024.1514. DOI: https://doi.org/10.54644/jte.2024.1514
Downloads
Published
How to Cite
Issue
Section
Categories
License
Copyright (c) 2025 Journal of Technical Education Science
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Copyright © JTE.
