Advertisement

Hot news mining and public opinion guidance analysis based on sentiment computing in network social media

  • Zhang FengEmail author
Original Article
  • 41 Downloads

Abstract

The texts of social media event have feathers of massive-sparse, dynamic-heterogeneous, and obscure-vague, which increase the difficulty of event emotion computing. Aiming at the problem, we construct the dictionary supervised emotion computing model, which can be applied in hot news mining and public opinion guidance analysis based on sentiment computing in network social media. The text words and labels are used as the input of the models, and the profile distribution and emotion distribution of the texts, the word distribution of the profiles, and emotions are output by the models. In addition, the words with definite emotion are used as the constraint condition of the model to enhance the accuracy of text emotion calculation. Our proposed algorithm can express the emotion of the text by using the words and labels from labeled texts, and the emotion words value is calculated through a finite iteration of the network. We also make use of the word emotion in the basic word emotion dictionary to modify the network and then recompute the word emotion, which effectively overcomes the problem of emotion uncertainty of the traditional methods. Experiments show that the accuracy of our model is generally higher than that of ETM, MSTM, and SLTM. Therefore, our proposed method is effective and feasible.

Keywords

Social media Sentiment computing Opinion guidance Hot news mining ESmotion dictionary Profile number 

Notes

Funding information

This paper was funded by Zhejiang Public Welfare Technology Application Research Project (No. LGG19F020009).

References

  1. 1.
    Kim Y (2014) Convolutional neural networks for sentence classification. Empirical Methods in Natural Language Processing 25(8) :1746–1751Google Scholar
  2. 2.
    Medhat W, Hassan A, Korashy H (2014) Sentiment analysis algorithms and applications: a survey. Ain Shams Eng J 5(4):1093–1113CrossRefGoogle Scholar
  3. 3.
    Saif H et al (2016) Contextual semantics for sentiment analysis of Twitter. Inf Process Manag 52(1):5–19CrossRefGoogle Scholar
  4. 4.
    Martinezcamara E et al (2014) Sentiment analysis in Twitter. Nat Lang Eng 20(1):1–28CrossRefGoogle Scholar
  5. 5.
    Wollmer, Martin, et al. “YouTube movie reviews: sentiment analysis in an audio-visual context.” IEEE Intell Syst 28.3 (2013): 46–53.CrossRefGoogle Scholar
  6. 6.
    Munezero M, Montero CS, Mozgovoy M, et al. EmoTwitter – A fine-grained visualization system for identifying enduring sentiments in tweets. [C]// Computational Linguistics & Intelligent Text Processing. 2015Google Scholar
  7. 7.
    Cambria E et al (2012) Sentic computing for social media mark theory. Multimedia Tools and Applications 59(2):557–577CrossRefGoogle Scholar
  8. 8.
    Lin L et al (2014) Opinion mining and sentiment analysis in social networks: a retweeting structure-aware approach. IEEE/ACM International Conference Utility and Cloud Computing 890–895Google Scholar
  9. 9.
    Zhou G et al (2016) Cross-lingual sentiment classification with stacked autoencoders. Knowl Inf Syst 47(1):27–44CrossRefGoogle Scholar
  10. 10.
    Hochreiter R (2015) Computing trading strategies based on financial sentiment data using evolutionary optimization. Soft Comput 32:181–191Google Scholar
  11. 11.
    Ain QT, Ali M, Riaz A et al (2017) Sentiment analysis using deep learning techniques: a review [J]. Int J Adv Comput Sci Appl 8(6):1011–1026Google Scholar
  12. 12.
    Cambria E (2016) Affective computing and sentiment analysis. IEEE Intell Syst 31(2):102–107CrossRefGoogle Scholar
  13. 13.
    Palanisamy P, Vineet Y, Harsha E (2013) "Serendio: simple and practical lexicon based approach to sentiment analysis." Joint Conference on Lexical and Computational Semantics 543–548.Google Scholar
  14. 14.
    Arras L, et al. (2017) "Explaining recurrent neural network predictions in sentiment analysis.." Empirical Methods in Natural Language Processing 159–168Google Scholar
  15. 15.
    Rani S, Kumar P (2017) A sentiment analysis system to improve teaching and learning. IEEE Comput 50(5):36–43CrossRefGoogle Scholar
  16. 16.
    Paolanti M, et al. (2017) "Visual and textual sentiment analysis of brand-related social media pictures using deep convolutional neural networks." International Conference on Image Analysis and Processing 402–413Google Scholar
  17. 17.
    Wang B et al (2016) A multi-granularity fuzzy computing model for sentiment classification of Chinese reviews. Journal of Intelligent and Fuzzy Systems 30(3):1445–1460CrossRefGoogle Scholar
  18. 18.
    Sehgal D, Agarwal A K (2015) "Sentiment analysis of big data applications using Twitter data with the help of HADOOP framework." International Conference System Modeling & Advancement Research Trends (2016): 251-255.Google Scholar
  19. 19.
    Yu Y, Wang X, World Cup (2014) In the Twitter World: a big data analysis of sentiments in US sports fans’ tweets [J]. Comput Hum Behav 48:392–400CrossRefGoogle Scholar
  20. 20.
    Liu SM, Chen JH (2015) A multi-label classification based approach for sentiment classification [J]. Expert Syst Appl 42(3):1083–1093CrossRefGoogle Scholar
  21. 21.
    Luo X, Xu Z, Yu J et al (2011) Building association link network for semantic link on web resources [J]. IEEE Trans Autom Sci Eng 8(3):482–494CrossRefGoogle Scholar
  22. 22.
    Blei DM, Ng AY, Jordan MI (2003) Latent dirichlet allocation [J]. J Mach Learn Res 3:993–1022zbMATHGoogle Scholar
  23. 23.
    Yildirim I (2012) Bayesian Inference: Metropolis-Hastings Sampling [J]. Dept. of Brain and Cognitive Sciences, Univ. of Rochester, RochesterGoogle Scholar
  24. 24.
    Pool C, Nissim M (2016) Distant supervision for emotion detection using Facebook reactions [J]. arXiv preprint arXiv 34:1611–1625Google Scholar
  25. 25.
    Casella G, George EI (1992) Explaining the Gibbs sampler [J]. Am Stat 46(3):167–174MathSciNetGoogle Scholar
  26. 26.
    Rao Y, Li Q, Mao X, Wenyin L (2014) Sentiment topic models for social emotion mining [J]. Inf Sci 266(5):90–100CrossRefGoogle Scholar
  27. 27.
    Bao S, Xu S, Zhang L et al (2011) Mining social emotions from affective text [J]. IEEE transactions on Knowledge & Data. Engineering 24(9):1658–1670Google Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2018

Authors and Affiliations

  1. 1.Zhejiang Business CollegeHangzhouChina

Personalised recommendations