Multi-kernel SVM based depression recognition using social media data

  • Zhichao Peng
  • Qinghua Hu
  • Jianwu DangEmail author
Original Article


Depression has become the world’s fourth major disease. Compared with the high incidence, however, the rate of depression medical treatment is very low because of the difficulty of diagnosis of mental problems. The social media opens one window to evaluate the users’ mental status. With the rapid development of Internet, people are accustomed to express their thoughts and feelings through social media. Thus social media provides a new way to find out the potential depressed people. In this paper, we propose a multi-kernel SVM based model to recognize the depressed people. Three categories of features, user microblog text, user profile and user behaviors, are extracted from their social media to describe users’ situations. According to the new characteristics of social media language, we build a special emotional dictionary consisted of text emotional dictionary and emoticon dictionary to extract microblog text features for word frequency statistics. Considering the heterogeneity between text feature and another two features, we employ multi-kernel SVM methods to adaptively select the optimal kernel for different features to find out users who may suffer from depression. Compared with Naive Bayes, Decision Trees, KNN, single-kernel SVM and ensemble method (libD3C), whose error reduction rates are 38, 43, 22, 21 and 11% respectively, the error rate of multi-kernel SVM method for identifying the depressed people is reduced to 16.54%. This indicates that the multi-kernel SVM method is the most appropriate way to find out depressed people based on social media data.


Chinese microblog Depression recognition Multi-kernel Social media SVM 



This work is partly supported by National Program on Key Basic Research Project under Grant 2013CB329304, National Natural Science Foundation of China under Grant 61222210 and New Century Excellent Talents in University under Grant NCET-12-0399.


  1. 1.
    Banitaan S, Daimi K (2014) Using data mining to predict possible future depression cases. Int J Public Health Sci 3(4):231–240Google Scholar
  2. 2.
    Burges CJ (1998) A tutorial on support vector machines for pattern recognition. Data Min Knowl Discov 2(2):121–167Google Scholar
  3. 3.
    Burns MN, Begale M, Duffecy J, Gergle D, Karr CJ, Giangrande E, Mohr DC (2011) Harnessing context sensing to develop a mobile intervention for depression. J Med Internet Res 13(3):e55Google Scholar
  4. 4.
    Caruana R, Niculescu-Mizil A (2006) An empirical comparison of supervised learning algorithms. In: Proceedings of ICML, pp 161–168Google Scholar
  5. 5.
    Chapelle O, Vapnik V (1999) Model selection for support vector machines. In: Proceedings of NIPS, pp 230–236Google Scholar
  6. 6.
    Chapelle O, Vapnik V, Bousquet O, Mukherjee S (2002) Choosing multiple parameters for support vector machines. Mach Learn 46(1–3):131–159zbMATHGoogle Scholar
  7. 7.
    Cortes C, Vapnik V (1995) Support-vector networks. Machine Learn 20(3):273–297zbMATHGoogle Scholar
  8. 8.
    Dang J, Li A, Erickson D, Suemitsu A, Akagi M, Sakuraba K (2010) Comparison of emotion perception among different cultures. Acoust Sci Technol 31(6):394–402Google Scholar
  9. 9.
    Dao B, Nguyen T, Phung D, Venkatesh S (2014) Effect of mood, social connectivity and age in online depression community via topic and linguistic analysis. In: Proceedings of International Conference on Web Information Systems Engineering, pp 398–407Google Scholar
  10. 10.
    Darwin C (1872) The expression of the emotions in man and animals, 1st edn. John Murray, LondonGoogle Scholar
  11. 11.
    De Choudhury M, Counts S, Horvitz E (2013) Social media as a measurement tool of depression in populations. In: Proceedings of the 5th Annual ACM Web Science Conference, pp 47–56Google Scholar
  12. 12.
    De Choudhury M, Counts S, Horvitz EJ, Hoff A (2014) Characterizing and predicting postpartum depression from shared Facebook data. In: Proceedings of the 17th ACM conference on Computer supported cooperative work and social computing, pp 626–638Google Scholar
  13. 13.
    De Choudhury M, Gamon M, Counts S, Horvitz E (2013) Predicting depression via social media. In: Proceedings of the ICWSM, pp 128–137Google Scholar
  14. 14.
    Do H, Kalousis A, Woznica A, Hilario M (2009) Margin and radius based multiple kernel learning. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pp 330–343Google Scholar
  15. 15.
    Dong Z, Dong Q (2006) HowNet and the computation of meaning. World Scientific, Singapore, pp 85–95Google Scholar
  16. 16.
    Doryab A, Min JK, Wiese J, Zimmerman J, Hong JI (2014) Detection of behavior change in people with depression. In: Proceedings of AAAI Workshop on MAIHA, pp 12–16Google Scholar
  17. 17.
    Ekman P (1992) An argument for basic emotions. Cognit Emot 6(3–4):169–200Google Scholar
  18. 18.
    Ellison NB (2007) Social network sites: definition, history, and scholarship. J Comput Mediat Commun 13(1):210–230MathSciNetGoogle Scholar
  19. 19.
    Ellison NB, Steinfield C, Lampe C (2007) The benefits of Facebook “friends:” Social capital and college students’ use of online social network sites. J Comput Mediat Comm 12(4):1143–1168Google Scholar
  20. 20.
    Filippone M, Camastra F, Masulli F, Rovetta S (2008) A survey of kernel and spectral methods for clustering. Pattern Recognit 41(1):176–190zbMATHGoogle Scholar
  21. 21.
    Fletcher R (1987) Practical methods of optimization, 2nd edn. Wiley, New JerseyzbMATHGoogle Scholar
  22. 22.
    Gilbert E, Karahalios K (2009) Predicting tie strength with social media. In: Proceedings of the SIGCHI conference on human factors in computing systems, pp 211–220Google Scholar
  23. 23.
    Gönen M, Alpaydın E (2011) Multiple kernel learning algorithms. J Mach Learn Res 12:2211–2268MathSciNetzbMATHGoogle Scholar
  24. 24.
    Haimson OL, Ringland K, Simpson S, Wolf CT (2014) Using depression analytics to reduce stigma via social media: BlueFriends. iConference (Social Media Expo)Google Scholar
  25. 25.
    Heidi L (2014) Medical research: if depression were cancer. Nature 515(7526):182–184Google Scholar
  26. 26.
    Kerri S (2014) Mental health: a world of depression. Nature 515(7526):180–181Google Scholar
  27. 27.
    Ku L, Chen H (2007) Mining opinions from the Web: Beyond relevance retrieval. J Am Soc Inf Sci Technol 58(12):1838–1850Google Scholar
  28. 28.
    Lin C, Chen W, Qiu C, Wu Y, Krishnan S, Zou Q (2014) LibD3C: ensemble classifiers with a clustering and dynamic selection strategy. Neurocomputing 123:424–435Google Scholar
  29. 29.
    Lin C, Huang Z, Yang F, Zou Q (2012) Identify content quality in online social networks. IET Commun 6(12):1618–1624Google Scholar
  30. 30.
    Neuman Y, Cohen Y, Assaf D, Kedma G (2012) Proactive screening for depression through metaphorical and automatic text analysis. Artif Intell Med 56(1):19–25Google Scholar
  31. 31.
    Nguyen T, Phung D, Dao B, Venkatesh S, Berk M (2014) Affective and content analysis of online depression communities. IEEE Trans Affect Comput 5(3):217–226Google Scholar
  32. 32.
    Park M, Cha C, Cha M (2012) Depressive moods of users portrayed in Twitter. In: Proceedings of the ACM SIGKDD Workshop on healthcare informatics, pp 1–8Google Scholar
  33. 33.
    Park M, McDonald DW, Cha M (2013) Perception differences between the depressed and non-depressed users in Twitter. In: Proceedings of ICWSM, pp 476–485Google Scholar
  34. 34.
    Park S, Lee SW, Kwak J, Cha M, Jeong B (2013) Activities on Facebook reveal the depressive state of users. J Med Internet Res 15(10):e217Google Scholar
  35. 35.
    Peng S, Hu Q, Chen Y, Dang J (2015) Improved support vector machine algorithm for heterogeneous data. Pattern Recognit 48(6):2072–2083zbMATHGoogle Scholar
  36. 36.
    Pennebaker JW, Francis ME, Booth RJ (2007) Linguistic inquiry and word count (Computer Software). LIWC IncGoogle Scholar
  37. 37.
    Rakotomamonjy A, Bach F, Canu S, Grandvalet Y (2007) More efficiency in multiple kernel learning. In: Proceedings of the 24th ICML, pp 775–782Google Scholar
  38. 38.
    Rakotomamonjy A, Bach F, Canu S, Grandvalet Y (2007) SimpleMKL. J Mach Learn Res 9:2491–2521MathSciNetzbMATHGoogle Scholar
  39. 39.
    Salton G, McGill MJ (1983) Introduction to modern information retrieval. McGraw-Hill computer science seriesGoogle Scholar
  40. 40.
    Schoen H, Gayo-Avello D, Takis MP, Mustafaraj E, Strohmaier M, Gloor P (2013) The power of prediction with social media. Internet Res 23(5):528–543Google Scholar
  41. 41.
    Vapnik V (2013) The nature of statistical learning theory. Springer Science & Business Media, BerlinzbMATHGoogle Scholar
  42. 42.
    Wang T, Rao J, Hu Q (2014) Supervised word sense disambiguation using semantic diffusion kernel. Eng Appl Artif Intell 27:167–174Google Scholar
  43. 43.
    Wang X, Zhang C, Ji Y, Sun L, Wu L, Bao Z (2013) A depression detection model based on sentiment analysis in micro-blog social network. In: Trends and Applications in Knowledge Discovery and Data Mining, pp 201–213Google Scholar
  44. 44.
    Wang X, Zhang C, Sun L (2013) An improved model for depression detection in micro-blog social network. In: Proceedings of the IEEE 13th ICDMW, pp 80–87Google Scholar
  45. 45.
    Wang Z, Chen S, Sun T (2008) MultiK-MHKS: a novel multiple kernel learning algorithm. IEEE Trans Pattern Anal Mach Intell 30(2):348–353Google Scholar
  46. 46.
    Wilson ML, Ali S, Valstar MF (2014) Finding information about mental health in microblogging platforms: a case study of depression. In: Proceedings of the 5th Information Interaction in Context Symposium, pp 8–17Google Scholar
  47. 47.
    Xu L, Lin H, Pan Y, Ren H, Chen J (2008) Constructing the affective lexicon ontology. J China Soc Sci Tech Inf 27(2):180–185Google Scholar
  48. 48.
    Yang B, Ollendick TH, Dong Q et al (1995) Only children and children with siblings in the People’s Republic of China: levels of fear, anxiety, and depression. Child Dev 66(5):1301–1311Google Scholar
  49. 49.
    Zhang H, Yu H, Xiong D, Liu Q (2003) HHMM-based Chinese lexical analyzer ICTCLAS. In: Proceedings of the second SIGHAN workshop on Chinese language processing, pp 184–187Google Scholar
  50. 50.
    Zou Q, Zeng J, Cao L, Ji R (2016) A novel features ranking metric with application to scalable visual and bioinformatics data classification. Neurocomputing 173:346–354Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2017

Authors and Affiliations

  1. 1.School of Computer Science and TechnologyTianjin UniversityTianjinChina

Personalised recommendations