Application of soft computing techniques for estimating emotional states expressed in Twitter® time series data

  • Erman ÇakıtEmail author
  • Waldemar Karwowski
  • Les Servi
Original Article


Because the emotional states of selected social groups may constitute a complex phenomenon, a suitable methodology is needed to analyze Twitter® text data that can reflect social emotions. Understanding the nature of social barometer data in terms of its underlying dynamics is critical for predicting the future states or behaviors of large social groups. This study investigated the use of the supervised soft computing techniques (1) fuzzy time series (FTS), (2) artificial neural network (ANN)-based FTS, and (3) adaptive neuro-fuzzy inference systems (ANFIS) for predicting the emotional states expressed in Twitter® data. The examined dataset contained 25,952 data points reflecting more than 380,000 Twitter® messages recorded hourly. The model prediction accuracy was performed using the root-mean-square error. The ANFIS approach resulted in the most accurate prediction among the three examined soft computing approaches. The findings of the study showed that the FTS, ANN-based FTS, and ANFIS models could be used to predict the emotional states of a large social group based on historical data. Such a modeling approach can support the development of real-time social and emotional awareness for practical decision-making, as well as rapid socio-cultural assessment and training.


Human emotional states Adaptive neuro-fuzzy inference systems Artificial neural networks Fuzzy time series Twitter® 



This study was supported in part by Grant No. N00014-11-1-0934 from the Office of Naval Research (ONR), Human, Social, Cultural, and Behavioral (HSCB) modeling program awarded to Waldemar Karwowski at the University of Central Florida, Orlando, Florida. Approved for Public Release; Distribution Unlimited. Case Number 17-3282 ©2017, The MITRE Corporation. All Rights Reserved.

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflicts of interest.


  1. 1.
    Prata DN, Soares KP, Silva MA, Trevisan DQ, Letouze P (2016) Social data analysis of Brazilian’s mood from Twitter. Int J Soc Sci Humanit 6(3):179CrossRefGoogle Scholar
  2. 2.
    Servi LD (2013) Analyzing social media data having discontinuous underlying dynamics. Oper Res Lett 41:581–585. MathSciNetCrossRefzbMATHGoogle Scholar
  3. 3.
    Karwowski W (2012) A review of human factors challenges of complex adaptive systems: discovering and understanding chaos in human performance. Hum Factors 54(6):983–995CrossRefGoogle Scholar
  4. 4.
    Twitter (2017) Twitter analytics. Accessed 13 Dec 2017
  5. 5.
    Pennebaker JW, Boyd RL, Jordan K, Blackburn K (2015) The development and psychometric properties of LIWC2015. University of Texas at Austin, AustinGoogle Scholar
  6. 6.
    Pennebaker JW, Booth RE, Francis ME (2007) Linguistic inquiry and word count: LIWC2007—operator’s manual., AustinGoogle Scholar
  7. 7.
    Pennebaker JW, Chung CK, Ireland M, Gonzales A, Booth RJ (2007) The development and psychometric properties of LIWC2007., AustinGoogle Scholar
  8. 8.
    Kumar M, Dredze M, Coppersmith G, De Choudhury M (2015) Detecting changes in suicide content manifested in social media following celebrity suicides. In: 26th ACM conference on hypertext & social media; September 01–04, 2015; Guzelyurt, Northern Cyprus. ACM Press, New York, pp 85–94Google Scholar
  9. 9.
    Kramer AD, Guillory JE, Hancock JT (2014) Experimental evidence of massive-scale emotional contagion through social networks. Proc Natl Acad Sci USA 111(24):8788–8790. CrossRefGoogle Scholar
  10. 10.
    De Choudhury M, Gamon M, Counts S, Horvitz E (2013) Predicting depression via social media. In: 7th international AAAI conference on weblogs and social media (ICWSM); July 8–11, 2013, Boston, USAGoogle Scholar
  11. 11.
    Wang Y, Kraut R, Levine J (2012) To stay or leave? The relationship of emotional and informational support to commitment in online health support groups. In: ACM 2012 conference on computer supported cooperative work; February 11–15, 2012. ACM Press, Seattle, pp 833–842Google Scholar
  12. 12.
    Hancock J, Gee K, Ciaccio K, Lin J (2008) I’m sad you’re sad: emotional contagion in CMC. 2008 In: ACM conference on computer supported cooperative work; November 08–12, 2008. ACM Press, San Diego, pp 295–298Google Scholar
  13. 13.
    Hancock J, Landrigan C, Silver C (2007) Expressing emotion in text-based communication. In: SIGCHI conference on human factors in computing systems; April 28–May 03, 2007. ACM Press, San Jose, CA, pp 929–932Google Scholar
  14. 14.
    Mogadala A, Varma V (2012) Twitter user behavior understanding with mood transition prediction. In: Proceedings of the 2012 workshop on data-driven user behavioral modelling and mining from social media ACM, pp 31–34Google Scholar
  15. 15.
    Bing L, Chan KC (2014) A fuzzy logic approach for opinion mining on large scale twitter data. In: Proceedings of the 2014 IEEE/ACM 7th international conference on utility and cloud computing. IEEE Computer Society, pp 652–657Google Scholar
  16. 16.
    Dash AK, Rout JK, Jena SK (2016) Harnessing twitter for automatic sentiment identification using machine learning techniques. In: Proceedings of 3rd international conference on advanced computing, networking and informatics. Springer, New Delhi, pp 507–514Google Scholar
  17. 17.
    Wang N, Varghese B, Donnelly PD (2016) A machine learning analysis of Twitter sentiment to the Sandy Hook shootings. arXiv preprint arXiv:1609.00536
  18. 18.
    Huq MR, Ali A, Rahman A (2017) Sentiment analysis on Twitter data using KNN and SVM. Int J Adv Comput Sci Appl 8(6):19–25Google Scholar
  19. 19.
    Mac Kim S (2011). Recognising emotions and sentiments in text. Ph.D. thesis, University of SydneyGoogle Scholar
  20. 20.
    Asur S, Huberman BA (2010). Predicting the future with social media. In: 2010 IEEE/WIC/ACM international conference on, web intelligence and intelligent agent technology (WI-IAT), vol 1. IEEE, pp 492–499Google Scholar
  21. 21.
    Gilbert E, Karahalios K (2010) Widespread worry and the stock market. In: ICWSM, pp 59–65Google Scholar
  22. 22.
    Bollen J, Mao H, Zeng X (2011) Twitter mood predicts the stock market. J Comput Sci 2(1):1–8CrossRefGoogle Scholar
  23. 23.
    Chen GH, Nikolov S, Shah D (2013) A latent source model for nonparametric time series classification. In: Advances in neural information processing systems, vol. 26. pp 1088–1096Google Scholar
  24. 24.
    Ma Z, Sun A, Cong G (2013) On predicting the popularity of newly emerging hashtags in twitter. J Assoc Inf Sci Technol 64(7):1399–1410CrossRefGoogle Scholar
  25. 25.
    Kong S, Mei Q, Feng L, Ye F, Zhao Z (2014) Predicting bursts and popularity of hashtags in real-time. In: Proceedings of the 37th international ACM SIGIR conference on research & development in information retrieval. ACM, pp 927–930Google Scholar
  26. 26.
    Servi LD, Elson SE (2014) A mathematical approach to identifying and forecasting shifts in the mood of social media users. IEEE Trans Comput Soc Syst 1(4):180–190CrossRefGoogle Scholar
  27. 27.
    Song Q, Chissom BS (1993) Fuzzy time series and its models. Fuzzy Sets Syst 54:269–277MathSciNetCrossRefzbMATHGoogle Scholar
  28. 28.
    Song Q, Chissom BS (1993) Forecasting enrollments with fuzzy time series—part I. Fuzzy Sets Syst 54:1–10CrossRefGoogle Scholar
  29. 29.
    Chen SM (1996) Forecasting enrollments based on fuzzy time series. Fuzzy Sets Syst 81(3):311–319CrossRefGoogle Scholar
  30. 30.
    Egrioglu E, Aladag CH, Yolcu U, Uslu VR, Basaran MA (2009) A new approach based on artificial neural networks for high order multivariate fuzzy time series. Expert Syst Appl 36(7):10589–10594CrossRefGoogle Scholar
  31. 31.
    Jang JSR (1993) ANFIS: adaptive-network-based fuzzy inference system. IEEE Trans Syst Man Cybern 23(5):665–685CrossRefGoogle Scholar
  32. 32.
    Çakıt E, Karwowski W, Bozkurt H, Ahram T, Thompson W, Mikusinski P, Lee G (2014) Investigating the relationship between adverse events and infrastructure development in an active war theater using soft computing techniques. Appl Soft Comput 25:204–214CrossRefGoogle Scholar
  33. 33.
    Zaheeruddin G (2006) A neuro-fuzzy approach for prediction of human work efficiency in noisy environment. Appl Soft Comput 6:283–294CrossRefGoogle Scholar
  34. 34.
    Çakıt E, Karwowski W (2017) Predicting the occurrence of adverse events using an adaptive neuro-fuzzy inference system (ANFIS) approach with the help of ANFIS input selection. Artif Intell Rev 48(2):139–155CrossRefGoogle Scholar
  35. 35.
    Nauck D, Klawonn F, Kruse R (1997) Foundations of neuro-fuzzy systems. Wiley, New YorkzbMATHGoogle Scholar
  36. 36.
    Chai T, Draxler RR (2014) Root mean square error (RMSE) or mean absolute error (MAE)? Arguments against avoiding RMSE in the literature. Geosci Model Dev 7(3):1247–1250CrossRefGoogle Scholar
  37. 37.
    Rantala J, Koivisto H (2002) Optimised subtractive clustering for neuro-fuzzy models. In: 3rd WSEAS international conference on fuzzy sets and fuzzy systemsGoogle Scholar
  38. 38.
    Stavroulakis P (ed) (2004) Neuro-fuzzy and fuzzy-neural applications in telecommunications. Springer, BerlinGoogle Scholar
  39. 39.
    Rezaei H, Rahmati M, Modarress H (2017) Application of ANFIS and MLR models for prediction of methane adsorption on X and Y faujasite zeolites: effect of cations substitution. Neural Comput Appl 28(2):301–312CrossRefGoogle Scholar
  40. 40.
    Lampos V, Lansdall-Welfare T, Araya R, Cristianini N (2013) Analysing mood patterns in the united kingdom through twitter content. arXiv preprint arXiv:1304.5507

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2019

Authors and Affiliations

  1. 1.Department of Industrial EngineeringAksaray UniversityAksarayTurkey
  2. 2.Department of Industrial Engineering and Management SystemsUniversity of Central FloridaOrlandoUSA
  3. 3.The MITRE CorporationBedfordUSA
  4. 4.Department of Industrial EngineeringGazi UniversityAnkaraTurkey

Personalised recommendations