A Deep Learning Semantic Approach to Emotion Recognition Using the IBM Watson Bluemix Alchemy Language

  • Giulio Biondi
  • Valentina FranzoniEmail author
  • Valentina Poggioni
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10406)


Sentiment analysis and emotion recognition are emerging research fields of research that aim to build intelligent systems able to recognize and interpret human emotions. Due to the applicability of these systems to almost all kinds of markets, also the interest of companies and industries is grown in an exponential way in the last years and a lot of frameworks for programming these systems are introduced. IBM Watson is one of the most famous and used: it offers, among others, a lot of services for Natural Language Processing. In spite of broad-scale multi-language services, most of functions are not available in a lot of “secondary” languages (like Italian). The main objective of this work is to demonstrate the feasibility of a translation-based approach to emotion recognition in texts written in “secondary” languages. We present a prototypical system using IBM Watson to extract emotions from Italian text by means of Bluemix Alchemy Language. Some preliminary results are shown and discussed in order to stress pro and cons of the approach.


Affective computing Emotion recognition Sentiment analysis SEMO Semantics Deep learning Machine learning Artificial intelligence Computer science IBM Watson Alchemy language Language translation 


  1. 1.
    Anusha, V., Sandhya, B.: A learning based emotion classifier with semantic text processing. In: El-Alfy, E.-S.M., Thampi, S.M., Takagi, H., Piramuthu, S., Hanne, T. (eds.) Advances in Intelligent Informatics. AISC, vol. 320, pp. 371–382. Springer, Cham (2015). doi: 10.1007/978-3-319-11218-3_34 Google Scholar
  2. 2.
    Baioletti, M., Milani, A., Poggioni, V., Rossi, F.: An ACO approach to planning. In: Cotta, C., Cowling, P. (eds.) EvoCOP 2009. LNCS, vol. 5482, pp. 73–84. Springer, Heidelberg (2009). doi: 10.1007/978-3-642-01009-5_7 CrossRefGoogle Scholar
  3. 3.
    Baioletti, M., Milani, A., Poggioni, V., Rossi, F.: Ant search strategies for planning optimization. In: ICAPS 2009 Proceedings of the 19th International Conference on Automated Planning and Scheduling, pp. 334–337 (2009)Google Scholar
  4. 4.
    Baioletti, M., Milani, A., Poggioni, V., Rossi, F.: Optimal planning with ACO. In: Serra, R., Cucchiara, R. (eds.) AI*IA 2009. LNCS, vol. 5883, pp. 212–221. Springer, Heidelberg (2009). doi: 10.1007/978-3-642-10291-2_22 CrossRefGoogle Scholar
  5. 5.
    Bhaskar, J., Sruthi, K., Nedungadi, P.: Hybrid approach for emotion classification of audio conversation based on text and speech mining. Procedia Comput. Sci. 46, 635–643 (2015)CrossRefGoogle Scholar
  6. 6.
    Chiancone, A., Franzoni, V., Milani, A.: A multistrain bacterial diffusion model for link prediction. Int. J. Pattern Recogn. Artif. Intell. 31(11), 157–172 (2017). World ScientificGoogle Scholar
  7. 7.
    Chiancone, A., Milani, A., Poggioni, V., Pallottelli, S., Madotto, A., Franzoni, V.: A multistrain bacterial model for link prediction. In: Proceedings of the International Conference on Natural Computation, pp. 1075–1079. IEEE Press (2016). doi: 10.1109/ICNC.2015.7378141
  8. 8.
    Ferrucci, D.A.: Introduction to this is watson. IBM J. Res. Dev. 56(34), 1 (2012)Google Scholar
  9. 9.
    Franzoni, V., Mencacci, M., Mengoni, P., Milani, A.: Semantic heuristic search in collaborative networks: measures and contexts. In: Proceedings 2014 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology, WI/IAT 2014, vol. 1, pp. 187–217. IEEE Press (2014). doi: 10.1109/WI-IAT.2014.27
  10. 10.
    Franzoni, V., Milani, A.: Pming distance: a collaborative semantic proximity measure. In: Proceedings of the IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2012, vol. 2, pp. 442–449. IEEE Press (2012). doi: 10.1109/WI-IAT.2012.226
  11. 11.
    Franzoni, V., Milani, A.: A pheromone-like model for semantic context extraction from collaborative networks. In: Proceedings IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology, WI-IAT 2015, 2016-January, pp. 540–547, IEEE Press (2016)Google Scholar
  12. 12.
    Franzoni, V., Poggioni, V., Zollo, F.: Can we infer book classification by blurbs. CEUR Workshop Proceedings, vol. 1127, pp. 16–19. CEUR WS (2014)Google Scholar
  13. 13.
    Franzoni, V., Biondi, G., Milani, A., Li, Y.: Web-based semantic similarity for emotion recognition in web objects. CoRR abs/1612.05734 (2016)Google Scholar
  14. 14.
    Franzoni, V., Poggioni, V., Zollo, F.: Automated classification of book blurbs according to the emotional tags of the social network zazie. In: 1st International Workshop on Emotion and Sentiment in Social and Expressive Media, ESSEM 2013, CEUR Workshop Proceedings, pp. 83–94. CEUR WS (2013)Google Scholar
  15. 15.
    Gentili, E., Milani, A., Poggioni, V.: Data summarization model for user action log files. In: Murgante, B., Gervasi, O., Misra, S., Nedjah, N., Rocha, A.M.A.C., Taniar, D., Apduhan, B.O. (eds.) ICCSA 2012. LNCS, vol. 7335, pp. 539–549. Springer, Heidelberg (2012). doi: 10.1007/978-3-642-31137-6_41 CrossRefGoogle Scholar
  16. 16.
    Gupta, R.K., Yang, Y.: Crystalnest at semeval-2017 task 4: Using sarcasm detection for enhancing sentiment classification and quantification. In: SemEval: 11th International Workshop on Semantic Evaluation, Aug 3–4, 2017, Vancouver, Canada (to appear)Google Scholar
  17. 17.
    High, R.: The Era of Cognitive Systems: An Inside Look at IBM Watson and How it Works. IBM Corporation, Redbooks, Armonk (2012)Google Scholar
  18. 18.
    Houjeij, A., Hamieh, L., Mehdi, N., Hajj, H.: A novel approach for emotion classification based on fusion of text and speech. In: 2012 19th International Conference on Telecommunications (ICT), pp. 1–6, April 2012Google Scholar
  19. 19.
    Huang, S.l., Chen, Y.S.: Developing document classifiers for recognizing article readers’ affects. In: Proceedings of the 2012 International Conference on Information Management (2012)Google Scholar
  20. 20.
    Liberati, C., Camillo, F.: Subjective business polarization: Sentiment analysis meets predictive modeling. In: Catania, B., et al. (eds.) New Trends in Databases and Information Systems. AISC, vol. 241. Springer, Cham (2014)CrossRefGoogle Scholar
  21. 21.
    Lupan, D., Bobocescu-Kesikis, S., Dascalu, M., Trausan-Matu, S., Dessus, P.: Predicting readers’ emotional states induced by news articles through latent semantic analysis. In: SMART 2013 International Conference on Social Media in Academia: Research and Teaching, pp. 79–84. Citeseer (2013)Google Scholar
  22. 22.
    Mancini, L., Milani, A., Poggioni, V., Chiancone, A.: Self regulating mechanisms for network immunization. AI Commun. 29(2), 301–317 (2016)MathSciNetCrossRefGoogle Scholar
  23. 23.
    Markines, B., Cattuto, C., Menczer, F.: Social spam detection. In: Proceedings of the 5th International Workshop on Adversarial Information Retrieval on the Web AIRWeb 2009, p. 41 (2009)Google Scholar
  24. 24.
    Milani, A., Poggioni, V.: Planning in reactive environments. Comput. Intell. 23(4), 439–463 (2007)MathSciNetCrossRefGoogle Scholar
  25. 25.
    Pallottelli, S., Franzoni, V., Milani, A.: Multi-path traces in semantic graphs for latent knowledge elicitation. In: Proceedings of International Conference on Natural Computation 2016-January, pp. 281–288. IEEE Press (2016). doi: 10.1109/ICNC.2015.7378004
  26. 26.
    Ren, F., Quan, C.: Linguistic-based emotion analysis and recognition for measuring consumer satisfaction: an application of affective computing. Inf. Technol. Manage. 13(4), 321–332 (2012)CrossRefGoogle Scholar
  27. 27.
    Shelke, N.: Approaches of emotion detection from text. Int. J. Comput. Sci. Inf. Technol. Res. 2(2), 123–128 (2014)Google Scholar
  28. 28.
    Shivhare, S.N., Garg, S., Mishra, A.: Emotionfinder: detecting emotion from blogs and textual documents. In: 2015 International Conference on Computing, Communication & Automation (ICCCA), pp. 52–57. IEEE (2015)Google Scholar
  29. 29.
    Shivhare, S.N., Saritha, S.K.: Emotion detection from text documents. Int. J. Data Min. Knowl. Manage. Process 4(6), 51 (2014)CrossRefGoogle Scholar
  30. 30.
    Taboada, M., Brooke, J., Tofiloski, M., Voll, K., Stede, M.: Lexicon-based methods for sentiment analysis. Comput. Linguist. 37(2), 267–307 (2011)CrossRefGoogle Scholar
  31. 31.
    Vallverdú, J., Trovato, G.: Emotional affordances for humanrobot interaction. Adapt. Behav. 24(5), 320–334 (2016)CrossRefGoogle Scholar
  32. 32.
    Vanzo, A., Croce, D., Castellucci, G., Basili, R., Nardi, D.: Spoken language understanding for service robotics in Italian. In: Adorni, G., Cagnoni, S., Gori, M., Maratea, M. (eds.) AI*IA 2016. LNCS, vol. 10037, pp. 477–489. Springer, Cham (2016). doi: 10.1007/978-3-319-49130-1_35 CrossRefGoogle Scholar
  33. 33.
    Wang, H., Xu, H., Liu, L., Song, W., Du, C.: An unsupervised microblog emotion dictionary construction method and its application on sentiment analysis. J. Inf. Comput. Sci. 12, 2729–2739 (2015)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Giulio Biondi
    • 1
  • Valentina Franzoni
    • 2
    Email author
  • Valentina Poggioni
    • 1
  1. 1.Department of Mathematics and Computer ScienceUniversity of PerugiaPerugiaItaly
  2. 2.Department of Computer, Control and Management EngineeringSapienza University of RomeRomeItaly

Personalised recommendations