An empirical comparison of supervised learning algorithms and hybrid WDBN algorithm for MOOC courses

  • Jayakumar SadhasivamEmail author
  • Ramesh Babu Kalivaradhan
Original Research


In today’s scenario, sentiment classification has been acknowledged as a significant aspect, as it delivers the techniques for automatically analyzing people’s reviews to extract useful information on a product or service. Polarity classification is one among those techniques which determine the text polarity in the opinion. In this regard, the given paper explains a method for sentiment classification of online course reviews using a novel classifier, whale-based deep belief network (WDBN). The input course review data is pre-processed in the given technique, and the key features are extracted from the data using emotion-SentiWordNet based feature extraction process. To classify sentiments in the feature extracted data, WDBN is brought in by combining deep belief networks and whale optimization algorithm such that the weights of the network layers are selected optimally. The given technique, with the application of WDBN, classifies the course reviews into two classes, such as positive and negative class reviews. The given WDBN classifier is tested with the help of a publicly accessible online course review dataset, and the performance of the classifier is assessed using three metrics, such as sensitivity, specificity, and accuracy, where it could attain maximum performance of 86.3% sensitivity, 81.1% specificity and 86% accuracy.



  1. Abbasi A, France S, Zhang Z, Chen H (2011) Selecting attributes for sentiment classification using feature relation networks. IEEE Trans Knowl Data Eng 23(3):447–462. CrossRefGoogle Scholar
  2. Catal C, Nangir M (2017) A sentiment classification model based on multiple classifiers. Appl Soft Comput 50:135–141. CrossRefGoogle Scholar
  3. Che W, Zhao Y, Guo H, Su Z, Liu T (2015) Sentence compression for aspect-based sentiment analysis. IEEE/ACM Trans Speech Lang Process 23(12):2111–2124. CrossRefGoogle Scholar
  4. Chen L-S, Lin J-Y (2013) A study on review manipulation classification using decision tree. In: 2013 10th international conference on service systems and service management, pp 680–685.
  5. Chen T, Xu R, He Y, Wang X (2017) Improving sentiment analysis via sentence type classification using BiLSTM-CRF and CNN. Expert Syst Appl 72:221–230. CrossRefGoogle Scholar
  6. Dang Y, Zhang Y, Chen H (2010) A lexicon-enhanced method for sentiment classification: an experiment on online product reviews. IEEE Intell Syst 25(4):46–53. CrossRefGoogle Scholar
  7. Gui L, Zhou Y, Xu R, He Y, Lu Q (2017) Learning representations from heterogeneous network for sentiment classification of product reviews. Knowl Based Syst 124:34–45. CrossRefGoogle Scholar
  8. Hinton GE, Osindero S, Teh Y-W (2006) A fast learning algorithm for deep belief nets. Neural Comput 18(7):1527–1554. MathSciNetCrossRefzbMATHGoogle Scholar
  9. Kalaivani P, Shunmuganathan K (2013) Sentiment classification of movie reviews by supervised machine learning approaches. Indian J Comput Sci 4(4):285–292. Google Scholar
  10. Kennedy A, Diana I, Inkpen D (2006) Sentiment classification of movie and product reviews using contextual valance shifters. Comput Intell 22(2):110–125. CrossRefGoogle Scholar
  11. Lin Z, Jin X, Xu X, Wang Y, Cheng X, Wang W, Meng D (2016) An unsupervised cross-lingual topic model framework for sentiment classification. IEEE/ACM Trans Audio Speech Lang Process 24(3):432–444. CrossRefGoogle Scholar
  12. Liu S, Cheng X, Li F, Li F (2015) TASC: topic-adaptive sentiment classification on dynamic tweets. IEEE Trans Knowl Data Eng 27(6):1696–1709. CrossRefGoogle Scholar
  13. Liu Z, Liu S, Liu L, Sun J, Peng X, Wang T (2016) Sentiment recognition of online course reviews using multi-swarm optimization-based selected features. Neurocomputing 185:11–20. CrossRefGoogle Scholar
  14. Ren Y, Wang R, Ji D (2016) A topic-enhanced word embedding for Twitter sentiment classification. Inf Sci 369:188–198. CrossRefGoogle Scholar
  15. Sadhasivam J, Kalivaradhan RB (2018) A hybrid approach for deep belief networks and whale optimization algorithm to perform sentiment analysis for MOOC courses. Int J Adv Intell ParadigGoogle Scholar
  16. Tang D, Wei F, Qin B, Dong L, Liu T, Zhou M (2014) A joint segmentation and classification framework for sentiment analysis. In: Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), 23(2002), pp 477–487.
  17. Timmaraju A, Khanna V (2015) Sentiment analysis on movie reviews using recursive and recurrent neural network architectures. In: CS224N Projects, pp 2–7Google Scholar
  18. Tripathy A, Agrawal A, Rath SK (2016) Classification of sentiment reviews using n-gram machine learning approach. Expert Syst Appl 57:117–126. CrossRefGoogle Scholar
  19. Vojt J (2016) Deep neural networks and their implementation.
  20. Walsh RJ (2018) Sentiment analysis of Stanford course reviewsGoogle Scholar
  21. Wen M, Yang D, Rosé CP (2014) Sentiment analysis in MOOC discussion forums: what does it tell us? In: Proceedings of educational data mining, (Edm), pp 1–8. Accessed 25 Feb 2017
  22. Wu F, Huang Y, Yuan Z (2017) Domain-specific sentiment classification via fusing sentiment knowledge from multiple sources. Inf Fusion 35:26–37. CrossRefGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  • Jayakumar Sadhasivam
    • 1
    Email author
  • Ramesh Babu Kalivaradhan
    • 2
  1. 1.School of Information Technology and EngineeringVellore Institute of TechnologyVelloreIndia
  2. 2.School of Computer Science and EngineeringVellore Institute of TechnologyVelloreIndia

Personalised recommendations