An Ensemble Neural Network Model for Benefiting Pregnancy Health Stats from Mining Social Media

  • Neha Warikoo
  • Yung-Chun ChangEmail author
  • Hong-Jie Dai
  • Wen-Lian Hsu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11292)


Extensive use of social media for communication has made it a desired resource in human behavior intensive tasks like product popularity, public polls and more recently for public health surveillance tasks such as lifestyle associated diseases and mental health. In this paper, we exploited Twitter data for detecting pregnancy cases and used tweets about pregnancy to study trigger terms associated with maternal physical and mental health. Such systems can enable clinicians to offer a more comprehensive health care in real time. Using a Twitter-based corpus, we have developed an ensemble Long-short Term Memory (LSTM) – Recurrent Neural Networks (RNN) and Convolution Neural Networks (CNN) network representation model to learn legitimate pregnancy cases discussed online. These ensemble representations were learned by a SVM classifier, which can achieve F1-score of 95% in predicting pregnancy accounts discussed in tweets. We also further investigate the words most commonly associated with physical disease symptoms ‘Distress’ and negative emotions ‘Annoyed’ sentiment. Results from our sentiment analysis study are quite encouraging, identifying more accurate triggers for pregnancy sentiment classes.


Ensemble deep learning Text mining of Twitter data Sentiment analysis Health surveillance Pregnancy health stats 



We are grateful to the anonymous reviewers for their insightful comments. This research was supported by the Ministry of Science and Technology of Taiwan under grant number MOST 106-2218-E-038-004-MY2, MOST 107-2634-F-001-005, and MOST 107-2319-B-400-001.


  1. 1.
    Woodall, J., Calisher, C.H.: ProMED-mail: background and purpose. Emerg. Infect. Dis. 7(3 Suppl.), 563 (2001)CrossRefGoogle Scholar
  2. 2.
    Mykhalovskiy, E., Weir, L.: The global public health intelligence network and early warning outbreak detection: a Canadian contribution to global public health. Can. J. Public Health 97(1), 42–44 (2006)Google Scholar
  3. 3.
    Brownstein, J.S., Freifeld, C.C., Madoff, L.C.: Digital disease detection — harnessing the web for public health surveillance. New England J. Med. 360(21), 2153–2157 (2009). Scholar
  4. 4.
    Huang, Y., et al.: Incorporating dependency trees improve identification of pregnant women on social media platforms. In: 2017 Proceedings of the International Workshops on Digital Disease Detection using Social Media (DDDSM-2017), Taipei, pp. 26–32 (2017)Google Scholar
  5. 5.
    Gomide, J.: Dengue surveillance based on a computational model of spatio-temporal locality of Twitter. In: Proceedings of the 3rd International Web Science Conference, p. 3. ACM (2011)Google Scholar
  6. 6.
    Diaz-Aviles, Stewart, A.: Tracking Twitter for epidemic intelligence: case study: Ehec/hus outbreak in Germany. In: 2011 Proceedings of the 4th Annual ACM Web Science Conference, pp. 82–85. ACM (2012)Google Scholar
  7. 7.
    Odlum, M.: How Twitter can support early warning systems in Ebola outbreak surveillance. In: 143rd APHA Annual Meeting and Exposition, 31 October–4 November 2015. APHA (2015)Google Scholar
  8. 8.
    McGough, S.F., Brownstein, J.S., Hawkins, J.B., Santillana, M.: Forecasting zika incidence in the 2016 latin america outbreak combining traditional disease surveillance with search, social media, and news report data. PLoS Negl. Trop. Dis. 11(1), e0005295 (2017). Scholar
  9. 9.
    Mejova, Y., Haddadi, H., Noulas, A., Weber, I.: # foodporn: obesity patterns in culinary interactions. In: Proceedings of the 5th International Conference on Digital Health 2015, pp. 51–58. ACM (2015)Google Scholar
  10. 10.
    Aphinyanaphongs, Y., Ray, B., Statnikov, A., Krebs, P.: Text classification for automatic detection of alcohol use-related tweets. In: International Workshop on Issues and Challenges in Social Computing (2014)Google Scholar
  11. 11.
    Leaman, R., Wojtulewicz, L., Sullivan, R., Skariah, A., Yang, J., Gonzalez, G.: Towards internet-age pharmacovigilance: extracting adverse drug reactions from user posts to health-related social networks. In: Proceedings of the 2010 Workshop on Biomedical Natural Language Processing, pp. 117–125 (2010)Google Scholar
  12. 12.
    Bian, J., Topaloglu, U., Yu, F.: Towards large-scale twitter mining for drug-related adverse events. In: Proceedings of the 2012 International Workshop on Smart Health and Wellbeing, pp. 25–32. ACM (2012)Google Scholar
  13. 13.
    Sarker, A., Gonzalez, G.: Portable automatic text classification for adverse drug reaction detection via multi-corpus training. J. Biomed. Inf. 53, 196–207 (2015)CrossRefGoogle Scholar
  14. 14.
    Dai, H.J., Touray, M., Jonnagaddala, J., Syed-Abdul, S.: Feature engineering for recognizing adverse drug reactions from Twitter posts. Information 7(2), 27 (2016). Scholar
  15. 15.
    Banjari, I., Kenjeri, D., Šolić K., Mandić , M.L.: Cluster analysis as a prediction tool for pregnancy outcomes. Collegium Antropol. 39(1), 247–252 (2015)Google Scholar
  16. 16.
    Laopaiboon, M.: ̈lmezoglu. Advanced maternal age and pregnancy outcomes: a multicountry assessment. BJOG: Int. J. Obstet. Gynaecol. 121(s1), 49–56 (2014)CrossRefGoogle Scholar
  17. 17.
    Wettach, C., Thomann, J., Lambrigger-Steiner, C., Buclin, T., Desmeules, J., von Mandach, U.: Pharmacovigilance in pregnancy: adverse drug reactions associated with fetal disorders. J. Perinat. Med. 41(3), 301–307 (2013)CrossRefGoogle Scholar
  18. 18.
    De Choudhury, M., Counts, S., Horvitz, E.: Predicting postpartum changes in emotion and behavior via social media. In: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, pp. 3267–3276. ACM (2013)Google Scholar
  19. 19.
    Chandrashekar, P.B., Magge, A., Sarker, A., Gonzalez, G.: Social media mining for identification and exploration of health-related information from pregnant women (2017). CoRR, abs/1702.02261Google Scholar
  20. 20.
    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997). Scholar
  21. 21.
    Lecun, Y., et al.: Comparison of learning algorithms for handwritten digit recognition. In: Fogelman, F., Gallinari, P. (eds.) International Conference on Artificial Neural Networks, Paris, pp. 53–60. EC2 & Cie (1995)Google Scholar
  22. 22.
    Kim, Y.: Convolutional neural networks for sentence classification. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014, October 2014, Doha, Qatar, A meeting of SIGDAT, a Special Interest Group of the ACL pp. 1746–1751 (2014)Google Scholar
  23. 23.
    Joachims, T.: Text categorization with Support Vector Machines: Learning with many relevant features. In: Nédellec, C., Rouveirol, C. (eds.) ECML 1998. LNCS, vol. 1398, pp. 137–142. Springer, Heidelberg (1998). Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Neha Warikoo
    • 1
    • 2
    • 3
  • Yung-Chun Chang
    • 4
    Email author
  • Hong-Jie Dai
    • 5
  • Wen-Lian Hsu
    • 3
  1. 1.Institute of Biomedical Informatics, National Yang-Ming UniversityTaipeiTaiwan
  2. 2.Bioinformatics Program, International Graduate Program Taiwan, Institute of Information Science, Academia SinicaTaipeiTaiwan
  3. 3.Institute of Information Science, Academia SinicaTaipeiTaiwan
  4. 4.Graduate Institute of Data Science, Taipei Medical UniversityTaipeiTaiwan
  5. 5.Department of Computer Science and Information EngineeringNational Taitung UniversityTaitungTaiwan

Personalised recommendations