Advertisement

Trends on Sentiment Analysis over Social Networks: Pre-processing Ramifications, Stand-Alone Classifiers and Ensemble Averaging

  • Christos Troussas
  • Akrivi KrouskaEmail author
  • Maria Virvou
Chapter
Part of the Intelligent Systems Reference Library book series (ISRL, volume 149)

Abstract

Technology advancements gave birth to social networks during the last decade. Many people tend to increasingly use them in order to share their personal opinion on current topics of their everyday life as well as express their emotions about situations in which they are interested. Hence, the emotions that are expressed in social networks can be positive, negative or neutral. To this direction, the analysis of people’s sentiments has drawn the attention of many scientists worldwide and offers a fertile ground for increasing research. Furthermore, a social network that is adopted by an ever growing percentage of people is Twitter. Twitter is an online news and social networking service where users post and interact with messages; such messages conceal people’s feelings and sentiments. Therefore, Twitter can be seen as a source of information and holds a vast amount of data that can be exploited for sentiment analysis research. In view of above, the purpose of this paper is to provide a guideline for the decision of optimal pre-processing techniques and classifiers for sentiment analysis over Twitter. In this context, three well-known Twitter datasets (OMD, HCR and STS-Gold) were used and a set of experiments was conducted. In particular, firstly, an extended comparison of sentiment polarity classification methods for Twitter text and the role of text preprocessing in sentiment analysis are discussed in depth. Secondly, four well-known learning-based classifiers (Naive Bayes, Support Vector Machine, k-Nearest Neighbors and C4.5) have been evaluated based on confusion matrices. Thirdly, the most common ensemble methods (Bagging, Boosting, Stacking and Voting) are examined and compared to base classifiers’ results. Finally, a case study concerning the application of Twitter sentiment analysis in an e-learning context is presented. The main result of the utilization of the Twitter-based learning application is that the exploitation of students’ emotional states can be used to enhance adaptivity in the learning content as well as deliver recommendations about activities and provide personalized assistance. Concerning data pre-processing, the experimental results demonstrate that feature selection and representation can affect the classification performance positively. Regarding the selection of the proper classifier, the superiority of Naive Bayes and Support Vector Machine, regardless of datasets, is proved, while the use of ensembles of multiple base classifiers can improve the accuracy of Twitter sentiment analysis.

Keywords

Sentiment analysis Data preprocessing Learning machines Ensembles Polarity detection Twitter 

References

  1. 1.
    Yadav, S.K.: Sentiment analysis and classification: a survey. Int. J. Adv. Res. Comput. Sci. Manag. Stud. 3(3), 113–121 (2015)Google Scholar
  2. 2.
    Saif, H., Fernandez, M., He, Y., Alani, H.: SentiCircles for contextual and conceptual semantic sentiment analysis of twitter. In: 11th International Conference on Semantic Web: Trends and Challenges (ESWC 2014), Crete, Greece (2014)Google Scholar
  3. 3.
    Medhat, W., Hassan, A., Korashy, H.: Sentiment analysis algorithms and applications: a survey. Ain Shams Eng. J. 5(4), 1093–1113 (2014)CrossRefGoogle Scholar
  4. 4.
    Bravo-Marquez, F., Mendoza, M., Poblete, B.: Meta-level sentiment models for big social data analysis. Knowl.-Based Syst. 69(1), 86–99 (2014)CrossRefGoogle Scholar
  5. 5.
    Martínez-Cámara, E., Martín-Valdivia, M.T., Ureña-López, L.A., Montejo-Ráez, A.R.: Sentiment analysis in twitter. Nat. Lang. Eng. 20(1), 1–28 (2014)CrossRefGoogle Scholar
  6. 6.
    Smailović, J., Grčar, M., Lavrač, N., Žnidaršič, M.: Stream-based active learning for sentiment analysis in the financial domain. Inf. Sci. 285(1), 181–203 (2014)CrossRefGoogle Scholar
  7. 7.
    Mostafa, M.M.: More than words: social networks’ text mining for consumer brand sentiments. Expert Syst. Appl. 40(10), 4241–4251 (2013)CrossRefGoogle Scholar
  8. 8.
    Cheong, M., Lee, V.C.S.: A microblogging-based approach to terrorism informatics: exploration and chronicling civilian sentiment and response to terrorism events via twitter. Inf. Syst. Front. 13(1), 45–59 (2011)CrossRefGoogle Scholar
  9. 9.
    Ortigosa, A., Martín, J.M., Carro, R.M.: Sentiment analysis in facebook and its application to e-learning. Comput. Hum. Behav. 31(1), 527–541 (2014)CrossRefGoogle Scholar
  10. 10.
    Zhang, L., Ghosh, R., Dekhil, M., Hsu, M., Liu, B.: Combining lexicon-based and learning-based methods for twitter sentiment analysis. HP Laboratories Technical Report (89) (2011)Google Scholar
  11. 11.
    Haddi, E., Liu, X., Shi, Y.: The role of text pre-processing in sentiment analysis. Proc. Comput. Sci. 17, 26–32 (2013)CrossRefGoogle Scholar
  12. 12.
    Krouska, A., Troussas, C., Virvou, M.: The effect of preprocessing techniques on Twitter sentiment analysis. In: 2016 7th International Conference on Information, Intelligence, Systems and Applications (IISA), pp. 1–5. IEEE (2016)Google Scholar
  13. 13.
    Troussas, C., Krouska, A., Virvou, M.: Evaluation of ensemble-based sentiment classifiers for Twitter data. In: 2016 7th International Conference on Information, Intelligence, Systems and Applications (IISA), pp. 1–6. IEEE (2016)Google Scholar
  14. 14.
    Shamma, D., Kennedy, L., Churchill, E.: Tweet the Debates: Understanding Community Annotation of Uncollected Sources. ACM Multimedia, ACM (2009)CrossRefGoogle Scholar
  15. 15.
    Speriosu, M., Sudan, N., Upadhyay, N., Baldridge, J.: Twitter polarity classification with label propagation over lexical links and the follower graph. In: Proceedings of the First Workshop on Unsupervised Methods in NLP, Edinburgh, Scotland (2011)Google Scholar
  16. 16.
    Saif, H., Fernez, M., He, Y., Alani, H.: Evaluation datasets for Twitter sentiment analysis: a survey and a new dataset, the STS-Gold. In: 1st International Workshop on Emotion and Sentiment in Social and Expressive Media: Approaches and Perspectives from AI (ESSEM 2013), Turin, Italy (2013)Google Scholar
  17. 17.
    Bravo-Marquez, F., Mendoza, M., Poblete, B.: Combining strengths, emotions and polarities for boosting twitter sentiment analysis. In: Proceedings of the 2nd International Workshop on Issues of Sentiment Discovery and Opinion Mining, WISDOM 2013 (2013). Da Silva, N.F., Hruschka, E.R., Hruschka, E.R., Jr.: Tweet sentiment analysis with classifier ensembles. Decis. Support Syst. 66, 170–179 (2014)Google Scholar
  18. 18.
    Krouska, A., Troussas, C., Virvou, M.: Comparative evaluation of algorithms for sentiment analysis over social networking services. J. Univ. Comput. Sci. 23(8), 755–768 (2017)Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2019

Authors and Affiliations

  • Christos Troussas
    • 1
  • Akrivi Krouska
    • 1
    Email author
  • Maria Virvou
    • 1
  1. 1.Software Engineering Laboratory, Department of InformaticsUniversity of PiraeusPiraeusGreece

Personalised recommendations