Sentiment Analysis and Topic Mining Using a Novel Deep Attention-Based Parallel Dual-Channel Model for Online Course Reviews | Cognitive Computation Skip to main content

Advertisement

Springer Nature Link
Log in

Sentiment Analysis and Topic Mining Using a Novel Deep Attention-Based Parallel Dual-Channel Model for Online Course Reviews

  • Published:
Cognitive Computation Aims and scope Submit manuscript

Abstract

The sentiment analysis and topic mining of course reviews are helpful for course improvement and development. In order to improve the quality of online teaching and effectively mine the information such as sentiments contained in course reviews, a novel Deep Attention-based Parallel Dual-Channel Model (DAPDM) is proposed by combining deep learning neural network algorithms. Bidirectional Encoder Representation from Transformers (BERT) is used to train word vectors. Convolutional neural network (CNN) and bi-directional long short-term memory (BiLSTM) with attention mechanism are used to form a dual-channel model to extract sentiment features and enrich semantics. Firstly, a total of 48,501 online course reviews are selected for experiment and analysis. BERT is also used for data enhancement to obtain balanced data. And the data are substituted into DAPDM and 8 other comparative models to verify the model performance. Secondly, the student-course-institution tripartite graph relationship network and the different sentiment feature words co-occurrence network are constructed and visualized to further study the internal relationship among students, courses, and institutions. Finally, the latent dirichlet allocation (LDA) model is used to extract concerns of different sentiments. The classification accuracy, the macro-average of F1 and the weighted average of F1 on DAPDM are respectively improved to 89.44%, 0.8195, and 0.8939 compared with the comparison model. And its receiver operating characteristic (ROC) curve results are optimal. The relationship network can uncover the most popular courses and institutions, and discover that courses serve as a bridge between students and institutions. It is also found that learners’ reviews mainly focus on the course content, technical content, difficulty degree, teachers’ teaching level, etc., which are also the main factors affecting the course learners’ satisfaction with the course. The study can provide theoretical and technical support for the specification and development of online courses.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
¥17,985 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (Japan)

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Data Availability

The datasets generated during and/or analyzed during the current study are available from the corresponding author on reasonable request.

References

  1. Bousbia N, Belamri I. Which contribution does EDM provide to computer-based learning environments? In: Educational Data Mining. Springer; 2014. pp. 3–28. https://doi.org/10.1007/978-3-319-02738-8_1.

  2. Movassagh AA, Alzubi JA, Gheisari M, Rahimi M, Mohan S, Abbasi AA, Nabipour N. Artificial neural networks training algorithm integrating invasive weed optimization with differential evolutionary model. J Ambient Intell Humaniz Comput. 2021;1–9. https://doi.org/10.1007/s12652-020-02623-6.

  3. Cheng Y, Zhang X, Wang X, Zhao H, Yu Y, Wang X, de Pablos PO. Rethinking the development of technology-enhanced learning and the role of cognitive computing. Int J Semant Web Inf Syst (IJSWIS). 2021;17(1):67–96. https://doi.org/10.4018/IJSWIS.2021010104.

    Article  Google Scholar 

  4. Tretyakov E, Savić D, Korpusenko A, Ionkina K. Sentiment analysis of social networks messages. In: Biologically Inspired Cognitive Architectures 2021. Springer International Publishing; 2022. pp. 552–560. https://doi.org/10.1007/978-3-030-96993-6_61.

  5. Liao J, Tang J, Zhao X. Course drop-out prediction on MOOC platform via clustering and tensor completion. Tsinghua Sci Technol. 2019;24(4):412–422. https://doi.org/10.26599/TST.2018.9010110.

  6. Zhai G, Yang Y, Wang H, Du S. Multi-attention fusion modeling for sentiment analysis of educational big data. Big Data Mining and Analytics. 2020;3(4):311–319. https://doi.org/10.26599/BDMA.2020.9020024.

  7. Olivera G, Zita B, Aleksandar K. Opinion mining in higher education: a corpus-based approach. Enterp Inf Syst. 2020;1–26. https://doi.org/10.1080/17517575.2020.1773542.

  8. Beasley ZJ, Piegl LA, Rosen P. Polarity in the classroom: A case study leveraging peer sentiment toward scalable assessment. IEEE Trans Learn Technol. 2021;14(4):515–25. https://doi.org/10.1109/TLT.2021.3102184.

    Article  Google Scholar 

  9. Tzeng J-W, Lee C-A, Huang N-F, Huang H-H, Lai C-F. Mooc evaluation system based on deep learning. Int Rev Res Open Dist Learn. 2022;23(1):21–40. https://doi.org/10.19173/irrodl.v22i4.5417.

  10. Wang Z, Yu Z, Guo B, Lu X. Sentiment analysis of Chinese micro blog based on lexicon and ruleset. Comput Eng Appl. 2015;51(8):218–25. https://doi.org/10.3778/j.issn.1002-8331.1308-0187.

    Article  Google Scholar 

  11. Chang C-H, Hwang S-Y, Wu M-L. Learning bilingual sentiment lexicon for online reviews. Electron Commer Res Appl. 2021;47. https://doi.org/10.1016/j.elerap.2021.101037.

  12. Liu Z, Liu L. Empirical study of sentiment classification for Chinese microblog based on machine learning. Comput Eng Appl. 2012;48(1):1–4. https://doi.org/10.3778/j.issn.1002-8331.2012.01.001.

    Article  Google Scholar 

  13. Isidoros P, Ioannis H. Recognizing emotions in text using ensemble of classifiers. Eng Appl Artif Intell. 2016;51:191–201. https://doi.org/10.1016/j.engappai.2016.01.012.

    Article  Google Scholar 

  14. Ghosh S, Vinyals O, Strope B, Roy S, Dean T, Heck L. Contextual LSTM (CLSTM) models for large scale NLP tasks. Neural Netw. 2016;2(12):1127–36. https://doi.org/10.1145/1235.

    Article  Google Scholar 

  15. Zhou Y, Liu Y, Cai J. Sentiment analysis of micro-blogs based on attention mechanism. Information studies: Theory & Application. 2018;41(03):89–94. https://doi.org/10.16353/j.cnki.1000-7490.2018.03.018.

  16. Dashtipour K, Gogate M, Adeel A, Larijani H, Hussain A. Sentiment analysis of persian movie reviews using deep learning. Entropy. 2021;23(5):596. https://doi.org/10.3390/e23050596.

    Article  Google Scholar 

  17. Abdu SA, Yousef AH, Salem A. Multimodal video sentiment analysis using deep learning approaches, a survey. Inf Fusion. 2021;76:204–26. https://doi.org/10.1016/j.inffus.2021.06.003.

    Article  Google Scholar 

  18. Alzubi JA, Jain R, Nagrath P, Satapathy S, Taneja S, Gupta P. Deep image captioning using an ensemble of CNN and LSTM based deep neural networks. J Intell Fuzzy Syst. 2021;40(4):5761–9. https://doi.org/10.3233/JIFS-189415.

    Article  Google Scholar 

  19. Alzubi JA, Jain R, Kathuria A, Khandelwal A, Saxena A, Singh A. Paraphrase identification using collaborative adversarial networks. J Intell Fuzzy Syst. 2020;39(1):1021–32. https://doi.org/10.3233/JIFS-191933.

    Article  Google Scholar 

  20. Chen X, Xie H. A structural topic modeling-based bibliometric study of sentiment analysis literature. Cogn Comput. 2020;12(6):1097–129. https://doi.org/10.1007/s12559-020-09745-1.

    Article  MathSciNet  Google Scholar 

  21. Kumar A, Srinivasan K, Cheng W-H, Zomaya AY. Hybrid context enriched deep learning model for fine-grained sentiment analysis in textual and visual semiotic modality social data. Inf Process Manag. 2020;57(1):102141. https://doi.org/10.1016/j.ipm.2019.102141.

  22. Alzubi OA, Alzubi JA, Alweshah M, Qiqieh I, Al-Shami S, Ramachandran M. An optimal pruning algorithm of classifier ensembles: dynamic programming approach. Neural Comput & Applic. 2020;32(20):16091–107. https://doi.org/10.1007/s00521-020-04761-6.

    Article  Google Scholar 

  23. Zhai G, Yang Y, Wang H, Du S. Multi-aspect sentiment attention modeling for sentiment classification of educational big data. Pattern Recognition and Artificial Intelligence. 2019;32(9):828–834. https://doi.org/10.16451/j.cnki.issn1003-6059.201909007.

  24. Liu Y, Zhao Y. Sentiment analysis of Chinese short text based on teaching evaluation. Mod Electron Technol. 2019;42(06):30–33+37.

  25. Spatiotis N, Perikos I, Mporas I, Paraskevas M. Sentiment analysis of teachers using social information in educational platform environments. Int J Artif Intell Tools. 2020;29(02):2040004. https://doi.org/10.1142/S0218213020400047.

    Article  Google Scholar 

  26. Basiri ME, Nemati S, Abdar M, Cambria E, Acharya UR. ABCDM: an attention-based bidirectional CNN-RNN deep model for sentiment analysis. Future Gener Comput Syst. 2021;115:279–94. https://doi.org/10.1016/j.future.2020.08.005.

    Article  Google Scholar 

  27. Wang B, Xiong Y, Yao Y, Chu W, Lv Y. Sentiment analysis of student teaching evaluation based on deep learning. E-education Research. 2021;42(04):101–107. https://doi.org/10.13811/j.cnki.eer.2021.04.014.

  28. Zhao S, Xiao Y, Guo J, Yue X, Yang J, Krishna R, Xu P, Keutzer K. Curriculum Cyclegan for textual sentiment domain adaptation with multiple sources. In: Proceedings of the Web Conference 2021. 2021. pp. 541–552. https://doi.org/10.1145/3442381.3449981.

  29. Zhou J, Ye J, Wang Z, Cai X, Li C. Progress and enlightenment of the education application of sentiment analysis abroad. Mod Educ Technol. 2020;30(12):34–40. https://doi.org/10.3969/j.issn.1009-8097.2020.12.005.

    Article  Google Scholar 

  30. Liu S, Peng X, Cheng HNH, Liu Z, Sun J, Yang C. Unfolding sentimental and behavioral tendencies of learners’ concerned topics from course reviews in a MOOC. J Educ Comput Res. 2019;57(3):670–696. https://doi.org/10.1177/0735633118757181.

  31. Jena RK. Sentiment mining in a collaborative learning environment: capitalising on big data. Behav Inform Technol. 2019;38(9):986–1001. https://doi.org/10.1080/0144929X.2019.1625440.

    Article  Google Scholar 

  32. Hew KF, Hu X, Qiao C, Tang Y. What predicts student satisfaction with MOOCS: a gradient boosting trees supervised machine learning and sentiment analysis approach. Comput Educ. 2020;145:103724. https://doi.org/10.1016/j.compedu.2019.103724.

  33. Osmanoglu UÖ, Atak ON, Çağlar K, Kayhan H, Can TC. Sentiment analysis for distance education course materials: a machine learning approach. Journal of Educational Technology and Online Learning. 2020;3(1):31–48. https://doi.org/10.31681/jetol.663733.

  34. Qi C, Liu S. Evaluating on-line courses via reviews mining. IEEE Access. 2021;9:35439–51. https://doi.org/10.1109/ACCESS.2021.3062052.

    Article  Google Scholar 

  35. Grönberg N, Knutas A, Hynninen T, Hujala M. Palaute: An online text mining tool for analyzing written student course feedback. IEEE Access. 2021;9:134518–13429. https://doi.org/10.1109/ACCESS.2021.3116425.

  36. Li L, Johnson J, Aarhus W, Shah D. Key factors in MOOC pedagogy based on NLP sentiment analysis of learner reviews: What makes a hit. Comput Educ. 2022;176:104354. https://doi.org/10.1016/j.compedu.2021.104354.

  37. Zhou J, Ye JM. Sentiment analysis in education research: a review of journal publications. Interact Learn Environ. 2020;1–13. https://doi.org/10.1080/10494820.2020.1826985.

  38. Devlin J, Chang M-W, Lee K, Toutanova K. Bert: Pre-training of deep bidirectional transformers for language understanding. 2018. Available from: http://arxiv.org/abs/1810.04805.

  39. Huang X, Liu G, Liu X, Yang A. Sentiment classification depth model based on word2vec and bi-directional LSTM. Application Research of Computers. 2019;36(12):3583–3587+3596. https://doi.org/10.19734/j.issn.1001-3695.2018.08.0599.

  40. Zhang C, Zhao M, Wu X. Financial fraud identification method for listed companies based on news sentiment. Journal of Shandong University of Science and Technology (Natural Science). 2021;40(01):91–99. https://doi.org/10.16452/j.cnki.sdkjzk.2021.01.011.

  41. Su J. Conditional text generation based on conditional layer normalization. Website. 2019. https://kexue.fm/archives/7124.

  42. Kim Y. Convolutional neural networks for sentence classification. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). ACL, Stroudsburg; 2014. pp. 1746–1751. https://doi.org/10.3115/v1/D14-1181.

  43. Johnson R, Zhang T. Deep pyramid convolutional neural networks for text categorization. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Vancouver, Canada; 2017. pp. 562–570. https://doi.org/10.18653/v1/P17-1052.

  44. Lai S, Xu L, Liu K, Zhao J. Recurrent convolutional neural networks for text classification. In: Twenty-ninth AAAI Conference on Artificial Intelligence. AAAI; 2015. pp. 2267–2273.

  45. Shen Z, Ju T. Research on tendency analysis of microblog comments based on BERT and BLSTM. Information studies: Theory & Application. 2020;43(08):173–177. https://doi.org/10.16353/j.cnki.1000-7490.2020.08.026.

  46. Shi Z, Dong Z, Pang C, Zhang B, Sun L. Sentiment analysis of e-commerce reviews based on BERT-CNN. Int J Comput Intell Appl. 2020;10(02):7–11. https://doi.org/10.3969/j.issn.2095-2163.2020.02.002.

    Article  Google Scholar 

  47. Song Y. MIHNet: Combining n-gram, sequential and global information for text classification. J Phys Conf Ser. 2020;1453(1):012156. https://doi.org/10.1088/1742-6596/1453/1/012156.

  48. Li S, Liu Z, Li Y. Temporal and spatial evolution of online public sentiment on emergencies. Inf Process Manag. 2020;57(2):102177. https://doi.org/10.1016/j.ipm.2019.102177.

  49. Li J, Cao N, Zhang Q, Zhang W, Ji S. Online social network groups discovery algorithm considering themes and time. Journal of Shandong University of Science and Technology (Natural Science). 2021;40(04):94–102. https://doi.org/10.16452/j.cnki.sdkjzk.2021.04.011.

  50. Ding S, Liu X, Zhen L. Research on the evolution of hot topics of online public opinion with the influence of comments. Journal of Modern Information. 2021;41(08):87–97. https://doi.org/10.3969/j.issn.1008-0821.2021.08.009.

    Article  Google Scholar 

Download references

Funding

This study was supported in part by the Natural Science Foundation of Shandong province under Grant ZR2022MG059 and ZR2020MF033, the National Bureau of Statistics of China under Grant 2022LZ31, the National Natural Science Foundation of China under Grant 61502280, the General project of science and technology plan of Beijing Municipal Commission of Education under Grant KM202010017001.

Author information

Authors and Affiliations

  1. College of Mathematics and Systems Science, Shandong University of Science and Technology, Qingdao, 266590, China

    Chun Yan & Jiahui Liu

  2. College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao, 266590, China

    Wei Liu

  3. ZHIYUAN (Liberal Study) College, Beijing Institute of Petro-chemical Technology, Beijing, 102617, China

    Xinhong Liu

Authors
  1. Chun Yan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jiahui Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Wei Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Xinhong Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Jiahui Liu, Wei Liu or Xinhong Liu.

Ethics declarations

Ethical Approval

This article does not contain any studies with human participants or animals performed by any of the authors.

Conflict of Interest

The authors declare no competing interests.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yan, C., Liu, J., Liu, W. et al. Sentiment Analysis and Topic Mining Using a Novel Deep Attention-Based Parallel Dual-Channel Model for Online Course Reviews. Cogn Comput 15, 304–322 (2023). https://doi.org/10.1007/s12559-022-10083-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12559-022-10083-7

Keywords

Search

Navigation