Deep Learning Adaptation with Word Embeddings for Sentiment Analysis on Online Course Reviews

  • Danilo DessíEmail author
  • Mauro Dragoni
  • Gianni Fenu
  • Mirko Marras
  • Diego Reforgiato Recupero
Part of the Algorithms for Intelligent Systems book series (AIS)


Online educational platforms are enabling learners to consume a great variety of content and share opinions on their learning experience. The analysis of the sentiment behind such a collective intelligence represents a key element for supporting both instructors and learning institutions on shaping the offered educational experience. Combining Word Embedding representations and deep learning architectures has made possible to design sentiment analysis systems able to accurately measure the text polarity on several contexts. However, the application of such representations and architectures on educational data still appears limited. Therefore, considering the over-sensitiveness of the emerging models to the context where the training data is collected, conducting adaptation processes that target the e-learning context becomes crucial to unlock the full potential of a model. In this chapter, we describe a deep learning approach that, starting from Word Embedding representations, measures the sentiment polarity of textual reviews posted by learners after attending online courses. Then, we demonstrate how Word Embeddings trained on smaller e-learning-specific resources are more effective with respect to those trained on bigger general-purpose resources. Moreover, we show the benefits achieved by combining Word Embeddings representations with deep learning architectures instead of common machine learning models. We expect that this chapter will help stakeholders to get a clear view and shape the future research on this field.


Big data E-learning Deep learning Online education Sentiment analysis Word Embeddings Domain adaptation 



Danilo Dessì and Mirko Marras acknowledge Sardinia Regional Government for the financial support of their Ph.D. scholarship (P.O.R. Sardegna F.S.E. Operational Programme of the Autonomous Region of Sardinia, European Social Fund 2014–2020, Axis III “Education and Training,” Specific Goal 10.5).

The research leading to these results has received funding from the EU’s Marie Curie training network PhilHumans—Personal Health Interfaces Leveraging HUman-MAchine Natural interactionS under grant agreement 812882.

Furthermore, we gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan X GPU used for this research.


  1. 1.
    Araque, O., I. Corcuera-Platas, J.F. Sanchez-Rada, and C.A. Iglesias. 2017. Enhancing deep learning sentiment analysis with ensemble techniques in social applications. Expert Systems with Applications 77: 236–246.CrossRefGoogle Scholar
  2. 2.
    Atzeni, M., and Reforgiato, D. 2018. Deep learning and sentiment analysis for human-robot interaction. In European Semantic Web Conference, 14–18. SpringerGoogle Scholar
  3. 3.
    Bojanowski, P., E. Grave, A. Joulin, and T. Mikolov. 2017. Enriching word vectors with subword information. Transactions of the Association for Computational Linguistics 5, 135–146. URL Scholar
  4. 4.
    Boratto, L., S. Carta, G. Fenu, and R. Saia. 2016. Using neural word embeddings to model user behavior and detect user segments. Knowledge-Based Systems 108: 5–14. Scholar
  5. 5.
    Breiman, L. 2001. Random forests. Machine Learning 45 (1): 5–32. Scholar
  6. 6.
    Buscaldi, D., A. Gangemi, and D. Reforgiato Recupero. 2018. Semantic web challenges. In Fifth SemWebEval Challenge at ESWC 2018, Heraklion, Crete, Greece, June 3–June 7, 2018, Revised Selected Papers, 3rd ed. Springer Publishing Company, IncorporatedCrossRefGoogle Scholar
  7. 7.
    Cela, K.L., M.Á. Sicilia, and S. Sánchez. 2015. Social network analysis in e-learning environments. Educational Psychology Review 27 (1): 219–246.CrossRefGoogle Scholar
  8. 8.
    Chauhan, G.S., P. Agrawal, and Y.K. Meena. 2019. Aspect-based sentiment analysis of students feedback to improve teaching-learning process. In Information and Communication Technology for Intelligent Systems, 259–266. Berlin: Springer.Google Scholar
  9. 9.
    Clarizia, F., F. Colace, M. De Santo, M. Lombardi, F. Pascale, and A. Pietrosanto. 2018. E-learning and sentiment analysis: a case study. In Proceedings of the 6th International Conference on Information and Education Technology, 111–118. ACMGoogle Scholar
  10. 10.
    Deng, L. 2014. A tutorial survey of architectures, algorithms, and applications for deep learning. APSIPA Transactions on Signal and Information Processing, 3Google Scholar
  11. 11.
    Dessi, D., M. Dragoni, G. Fenu, M. Marras, and D. Reforgiato Recupero. 2019. Evaluating neural word embeddings created from online course reviews for sentiment analysis. In The 34th ACM/SIGAPP Symposium on Applied Computing, 2124–2127. SACGoogle Scholar
  12. 12.
    Dessì, D., G. Fenu, M. Marras, and D.R. Recupero. 2017. Leveraging cognitive computing for multi-class classification of e-learning videos. In European Semantic Web Conference, 21–25. SpringerGoogle Scholar
  13. 13.
    Dessì, D., G. Fenu, M. Marras, and D.R. Recupero. 2019. Bridging learning analytics and cognitive computing for big data classification in micro-learning video collections. Computers in Human Behavior 92: 468–477.CrossRefGoogle Scholar
  14. 14.
    Dessì, D., G. Fenu, M. Marras, and D. Reforgiato Recupero. 2018. Coco: Semantic-enriched collection of online courses at scale with experimental use cases. In Trends and Advances in Information Systems and Technologies, 1386–1396. Berlin: Springer.Google Scholar
  15. 15.
    Dos Santos, C., and M. Gatti. 2014. Deep convolutional neural networks for sentiment analysis of short texts. In Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers, 69–78Google Scholar
  16. 16.
    Dragoni, M., and D. Reforgiato Recupero. 2016. Challenge on fine-grained sentiment analysis within eswc2016. In Semantic Web Challenges, ed. H. Sack, S. Dietze, A. Tordai, and C. Lange, 79–94. Cham: Springer International Publishing.CrossRefGoogle Scholar
  17. 17.
    Dragoni, G., and M. Petrucci. 2017. A neural word embeddings approach for multi-domain sentiment analysis. IEEE Transactions on Affective Computing 8 (4): 457–470.CrossRefGoogle Scholar
  18. 18.
    Dridi, A., and D. Reforgiato. 2017. Leveraging semantics for sentiment polarity detection in social media. International Journal of Machine Learning and Cybernetics 10 (8): 2045–2055.CrossRefGoogle Scholar
  19. 19.
    Esparza, G., A. de Luna, A.O. Zezzatti, A. Hernandez, J. Ponce, M. Álvarez, E. Cossio, and J. de Jesus Nava. 2017. A sentiment analysis model to analyze students reviews of teacher performance using support vector machines. In International Symposium on Distributed Computing and Artificial Intelligence, 157–164. SpringerGoogle Scholar
  20. 20.
    Giatsoglou, M., M.G. Vozalis, K. Diamantaras, A. Vakali, G. Sarigiannidis, and K. Chatzisavvas. 2017. Sentiment analysis leveraging emotions and word embeddings. Expert Systems with Applications 69: 214–224.CrossRefGoogle Scholar
  21. 21.
    Ji, S., N. Satish, S. Li, and P. Dubey. 2016. Parallelizing word2vec in multi-core and many-core architectures. arXiv preprint arXiv:1611.06172
  22. 22.
    Joulin, A., E. Grave, P. Bojanowski, M. Douze, H. Jégou, and T. Mikolov. 2016. Fasttext. zip: Compressing text classification models. arXiv:1612.03651
  23. 23.
    Le, Q., and T. Mikolov. 2014. Distributed representations of sentences and documents. In International Conference on Machine Learning, 1188–1196Google Scholar
  24. 24.
    Li, Y., Q. Pan, T. Yang, S. Wang, J. Tang, and E. Cambria. 2017. Learning word representations for sentiment analysis. Cognitive Computation 9 (6): 843–851.CrossRefGoogle Scholar
  25. 25.
    Lin, C.C., W. Ammar, C. Dyer, and L. Levin. 2015. Unsupervised pos induction with word embeddings. arXiv preprint arXiv:1503.06760
  26. 26.
    Maas, A.L., R.E. Daly, P.T. Pham, D. Huang, A.Y. Ng, and C. Potts. 2011. Learning word vectors for sentiment analysis. In Proceedings of the Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, vol. 1, 142–150Google Scholar
  27. 27.
    Mikolov, T., K. Chen, G. Corrado, and J. Dean. 2013. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781
  28. 28.
    Mikolov, T., I. Sutskever, K. Chen, G.S. Corrado, and J. Dean. 2013. Distributed representations of words and phrases and their compositionality. In Advances in Neural Information Processing Systems, 3111–3119Google Scholar
  29. 29.
    Pang, B., and L. Lee. 2005. Seeing stars: Exploiting class relationships for sentiment categorization with respect to rating scales. CoRR abs/cs/0506075. URL
  30. 30.
    Pennington, J., R. Socher, and C. Manning. 2014. Glove: Global vectors for word representation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), 1532–1543Google Scholar
  31. 31.
    Poria, S., E. Cambria, and A. Gelbukh. 2015. Deep convolutional neural network textual features and multiple kernel learning for utterance-level multimodal sentiment analysis. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, 2539–2544Google Scholar
  32. 32.
    Reforgiato Recupero, D., Cambria, E.: Eswc’14 challenge on concept-level sentiment analysis. In: Presutti, V., Stankovic, M., Cambria, E., Cantador, I., Di Iorio, A., Di Noia, T., Lange, C., Reforgiato Recupero, D., Tordai, A. (eds.) Semantic Web Evaluation Challenge, pp. 3–20. Springer International Publishing, Cham (2014)CrossRefGoogle Scholar
  33. 33.
    Reforgiato Recupero, D., E. Cambria, and E. Di Rosa. 2017. Semantic sentiment analysis challenge eswc2017. Semantic Web Challenges, 109–123. Berlin: Springer.Google Scholar
  34. 34.
    Reforgiato Recupero, D., M. Dragoni, and V. Presutti. 2015. Eswc 15 challenge on concept-level sentiment analysis. In Semantic Web Evaluation Challenges, ed. F. Gandon, E. Cabrio, M. Stankovic, and A. Zimmermann, 211–222. Cham: Springer International Publishing.CrossRefGoogle Scholar
  35. 35.
    Rodrigues, M.W., L.E. Zárate, and S. Isotani. 2018. Educational data mining: A review of evaluation process in the e-learning. Telematics and Informatics 35 (6): 1701–1717.CrossRefGoogle Scholar
  36. 36.
    Rodriguez, P., A. Ortigosa, and R.M. Carro. 2012. Extracting emotions from texts in e-learning environments. In: 2012 Sixth International Conference on Complex, Intelligent, and Software Intensive Systems, 887–892. IEEEGoogle Scholar
  37. 37.
    Ruder, S. 2016. An overview of gradient descent optimization algorithms. arXiv preprint arXiv:1609.04747
  38. 38.
    Rudkowsky, E., M. Haselmayer, M. Wastian, M. Jenny, S. Emrich, and M. Sedlmair. 2018. More than bags of words: Sentiment analysis with word embeddings. Communication Methods and Measures 12 (2–3): 140–157.CrossRefGoogle Scholar
  39. 39.
    Saif, H., Y. He, A. Fernandez, and H. Alani. 2014. Semantic patterns for sentiment analysis of twitter. In: International Semantic Web Conference, 324–340. SpringerGoogle Scholar
  40. 40.
    Socher, R., J. Pennington, E.H. Huang, A.Y. Ng, and C.D. Manning. 2011. Semi-supervised recursive autoencoders for predicting sentiment distributions. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, 151–161. Association for Computational LinguisticsGoogle Scholar
  41. 41.
    Sokolova, M., and G. Lapalme. 2009. A systematic analysis of performance measures for classification tasks. Information Processing & Management 45 (4): 427–437.CrossRefGoogle Scholar
  42. 42.
    Tang, D., B. Qin, and T. Liu. 2015. Document modeling with gated recurrent neural network for sentiment classification. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, 1422–1432Google Scholar
  43. 43.
    Tang, D., F. Wei, B. Qin, N. Yang, T. Liu, and M. Zhou. 2016. Sentiment embeddings with applications to sentiment analysis. IEEE Transactions on Knowledge and Data Engineering 28 (2): 496–509.CrossRefGoogle Scholar
  44. 44.
    Tang, D., F. Wei, N. Yang, M. Zhou, T. Liu, and B. Qin. 2014. Learning sentiment-specific word embedding for twitter sentiment classification. In: Proceeding of the Annual Meeting of the Association for Computational Linguistics, 1555–1565Google Scholar
  45. 45.
    Tripathy, A., A. Agrawal, and S.K. Rath. 2016. Classification of sentiment reviews using n-gram machine learning approach. Expert Systems with Applications 57: 117–126.CrossRefGoogle Scholar
  46. 46.
    Turney, P.D., and P. Pantel. 2010. From frequency to meaning: Vector space models of semantics. Journal of artificial intelligence research 37: 141–188.MathSciNetCrossRefGoogle Scholar
  47. 47.
    Vu, T., D.Q. Nguyen, X. Vu, D.Q. Nguyen, M. Catt, and M. Trenell. 2018. NIHRIO at semeval-2018 task 3: A simple and accurate neural network model for irony detection in twitter. CoRR abs/1804.00520. URL
  48. 48.
    Zhang, L., S. Wang, and B. Liu. 2018. Deep learning for sentiment analysis: A survey. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery 8 (4): e1253.Google Scholar
  49. 49.
    Zhang, Z., and M. Lan. 2015. Learning sentiment-inherent word embedding for word-level and sentence-level sentiment analysis. In: 2015 International Conference on Asian Language Processing (IALP), 94–97Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • Danilo Dessí
    • 1
    Email author
  • Mauro Dragoni
    • 2
  • Gianni Fenu
    • 1
  • Mirko Marras
    • 1
  • Diego Reforgiato Recupero
    • 1
  1. 1.Department of Mathematics and Computer ScienceUniversity of CagliariCagliariItaly
  2. 2.Fondazione Bruno KesslerTrentoItaly

Personalised recommendations