From Social Media to Expert Reports: The Impact of Source Selection on Automatically Validating Complex Conceptual Models of Obesity

  • Mannila Sandhu
  • Philippe J. GiabbanelliEmail author
  • Vijay K. Mago
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11578)


Models are predominantly developed using either quantitative data (e.g., for structured equation models) or qualitative data obtained through questionnaires designed by researchers (e.g., for fuzzy cognitive maps). The wide availability of social media data and advances in natural language processing raise the possibility of developing models from qualitative data naturally produced by users. This is of particular interest for public health surveillance and policymaking, as social media provide the opinions of constituents. In this paper, we contrast a model produced by social media with one produced via expert reports. We use the same process to derive a model in each case, thus focusing our analysis on the impact of source selection. We found that three expert reports were sufficient to touch on more aspects of a complex problem (measured by the number of relationships) than several million tweets. Consequently, developing a model exclusively from social media may lead to oversimplifying a problem. This may be avoided by complementing social media with expert reports. Alternatively, future research should explore whether a much larger volume of tweets would be needed, which also calls for improvements in scalable methods to transform qualitative data into models.


Conceptual modeling Network analysis Social web mining Theme mining Twitter mining 



The authors are indebted to Mitacs Canada for providing the financial support which allowed MS to perform this research at Furman University, while mentored by PJG (local advisor) and VKM (home advisor). Publication costs are supported by an NSERC Discovery Grant for VKM. We thank Chetan Harichandra Mendhe for gathering the tweets under supervision of VKM.

Contributions. MS wrote the scripts to generate the results and analyzed them. PJG wrote the manuscript and designed the methods. MS was advised by PJG and VKM, who jointly initiated the study. All authors read and approved of this manuscript.


  1. 1.
    Centers for Disease Control and Prevention (CDC): Selected health conditions and risk factors, by age: United states, selected years 1988–1994 through 2015–2016Google Scholar
  2. 2.
    Peralta, M., et al.: Prevalence and trends of overweight and obesity in older adults from 10 European Countries from 2005 to 2013. Scand. J. Public Health 46, 522–529 (2018). Scholar
  3. 3.
    Lubbe, J.: Obesity and metabolic surgery in South Africa. S. Afr. Gastroenterology Rev. 16(1), 23–28 (2018)Google Scholar
  4. 4.
    Wang, Y., Wang, L., Qu, W.: New national data show alarming increase in obesity and noncommunicable chronic diseases in China. Eur. J. Clin. Nutr. 71(1), 149 (2017)CrossRefGoogle Scholar
  5. 5.
    Ng, M., et al.: Global, regional, and national prevalence of overweight and obesity in children and adults during 1980–2013: a systematic analysis for the global burden of disease study 2013. Lancet 384(9945), 766–781 (2014)CrossRefGoogle Scholar
  6. 6.
    Skinner, A.C., Perrin, E.M., Skelton, J.A.: Prevalence of obesity and severe obesity in US children, 1999-2014. Obesity 24(5), 1116–1123 (2016)CrossRefGoogle Scholar
  7. 7.
    Bleich, S.N., et al.: Interventions to prevent global childhood overweight and obesity: a systematic review. Lancet Diabetes Endocrinol. 6(4), 332–346 (2018)CrossRefGoogle Scholar
  8. 8.
    Hutchesson, M., et al.: eH ealth interventions for the prevention and treatment of overweight and obesity in adults: a systematic review with meta-analysis. Obes. Rev. 16(5), 376–392 (2015)CrossRefGoogle Scholar
  9. 9.
    Rajjo, T., et al.: Treatment of pediatric obesity: an umbrella systematic review. J. Clin. Endocrinol. Metab. 102(3), 763–775 (2017)Google Scholar
  10. 10.
    Teixeira, P.J., et al.: Successful behavior change in obesity interventions in adults: a systematic review of self-regulation mediators. BMC Med. 13(1), 84 (2015)MathSciNetCrossRefGoogle Scholar
  11. 11.
    National Institute for Health and Care Excellence: Managing overweight and obesity in adults-lifestyle weight management services. NICE Public Health Guideline, 53 (2014)Google Scholar
  12. 12.
    Blackburn, G.: Effect of degree of weight loss on health benefits. Obes. Res. 3(S2), 211s–216s (1995)CrossRefGoogle Scholar
  13. 13.
    Fink, D.S., Keyes, K.M.: Wrong answers: when simple interpretations create complex problems. In: Systems Science and Population Health, pp. 25–36 (2017)CrossRefGoogle Scholar
  14. 14.
    Frood, S., et al.: Obesity, complexity, and the role of the health system. Curr. Obes. Rep. 2(4), 320–326 (2013)CrossRefGoogle Scholar
  15. 15.
    Finegood, D.T.: The complex systems science of obesity. In: The Oxford Handbook of the Social Science of Obesity (2011)Google Scholar
  16. 16.
    Rutter, H., et al.: The need for a complex systems model of evidence for public health. Lancet 390(10112), 2602–2604 (2017)CrossRefGoogle Scholar
  17. 17.
    Giabbanelli, P.J.: Analyzing the complexity of behavioural factors influencing weight in adults. In: Giabbanelli, P.J., Mago, V.K., Papageorgiou, E.I. (eds.) Advanced Data Analytics in Health. SIST, vol. 93, pp. 163–181. Springer, Cham (2018). Scholar
  18. 18.
    Deck, P., Giabbanelli, P., Finegood, D.T.: Exploring the heterogeneity of factors associated with weight management in young adults. Can. J. Diabetes 37, S269–S270 (2013)CrossRefGoogle Scholar
  19. 19.
    Giabbanelli, P.J., Torsney-Weir, T., Mago, V.K.: A fuzzy cognitive map of the psychosocial determinants of obesity. Appl. Soft Comput. 12(12), 3711–3724 (2012)CrossRefGoogle Scholar
  20. 20.
    Jebb, S., Kopelman, P., Butland, B.: Executive summary: foresight ‘tackling obesities: future choices’ project. Obes. Rev. 8, vi–ix (2007)CrossRefGoogle Scholar
  21. 21.
    Xue, H., et al.: Applications of systems modelling in obesity research. Obes. Rev. 19(9), 1293–1308 (2018)CrossRefGoogle Scholar
  22. 22.
    Frerichs, L., et al.: Mind maps and network analysis to evaluate conceptualization of complex issues: a case example evaluating systems science workshops for childhood obesity prevention. Eval. Program Plan. 68, 135–147 (2018)CrossRefGoogle Scholar
  23. 23.
    Johnston, L.M., Matteson, C.L., Finegood, D.T.: Systems science and obesity policy: a novel framework for analyzing and rethinking population-level planning. Am. J. Public Health 104(7), 1270–1278 (2014)CrossRefGoogle Scholar
  24. 24.
    Drasic, L., Giabbanelli, P.J.: Exploring the interactions between physical well-being, and obesity. Can. J. Diabetes 39, S12–S13 (2015)CrossRefGoogle Scholar
  25. 25.
    Dubé, L., Du, P., McRae, C., Sharma, N., Jayaraman, S., Nie, J.-Y.: Convergent innovation in food through big data and artificial intelligence for societal-scale inclusive growth. Technol. Innov. Manag. Rev. 8, 49–65 (2018)CrossRefGoogle Scholar
  26. 26.
    Jha, S.K., Gold, R., Dube, L.: Convergent innovation platform to address complex social problems: a tiered governance model. In: Academy of Management Proceedings, Volume 2016, Academy of Management Briarcliff Manor, NY 10510 (2016)CrossRefGoogle Scholar
  27. 27.
    Finegood, D.T., Merth, T.D., Rutter, H.: Implications of the foresight obesity system map for solutions to childhood obesity. Obesity 18(S1), S13–S16 (2010)CrossRefGoogle Scholar
  28. 28.
    Giabbanelli, P.J., Baniukiewicz, M.: Navigating complex systems for policymaking using simple software tools. In: Giabbanelli, P.J., Mago, V.K., Papageorgiou, E.I. (eds.) Advanced Data Analytics in Health. SIST, vol. 93, pp. 21–40. Springer, Cham (2018). Scholar
  29. 29.
    Giabbanelli, P., et al.: developing technology to support policymakers in taking a systems science approach to obesity and well-being. Obes. Rev. 17, 194–195 (2016)Google Scholar
  30. 30.
    Owen, B., et al.: Understanding a successful obesity prevention initiative in children under 5 from a systems perspective. PloS one 13(3), e0195141 (2018)CrossRefGoogle Scholar
  31. 31.
    McGlashan, J., et al.: Quantifying a systems map: network analysis of a childhood obesity causal loop diagram. PloS one 11(10), e0165459 (2016)CrossRefGoogle Scholar
  32. 32.
    McGlashan, J., et al.: Comparing complex perspectives on obesity drivers: action-driven communities and evidence-oriented experts. Obes. Sci. Pract. 4, 575–581 (2018)CrossRefGoogle Scholar
  33. 33.
    Allender, S., et al.: A community based systems diagram of obesity causes. PLoS One 10(7), e0129683 (2015)CrossRefGoogle Scholar
  34. 34.
    Giles, B.G., et al.: Integrating conventional science and aboriginal perspectives on diabetes using fuzzy cognitive maps. Soc. Sci. Med. 64(3), 562–576 (2007)CrossRefGoogle Scholar
  35. 35.
    Voinov, A., et al.: Tools and methods in participatory modeling: selecting the right tool for the job. Environ. Model. Softw. 109, 232–255 (2018)CrossRefGoogle Scholar
  36. 36.
    Reddy, T., Giabbanelli, P.J., Mago, V.K.: The artificial facilitator: guiding participants in developing causal maps using voice-activated technologies. In: International Conference on Augmented Cognition (2019)Google Scholar
  37. 37.
    So, J., et al.: What do people like to “share” about obesity? A content analysis of frequent retweets about obesity on twitter. Health Commun. 31(2), 193–206 (2016)CrossRefGoogle Scholar
  38. 38.
    Chou, W.Y.S., Prestin, A., Kunath, S.: Obesity in social media: a mixed methods analysis. Transl. Behav. Med. 4(3), 314–323 (2014)CrossRefGoogle Scholar
  39. 39.
    Shaw Jr., G., Karami, A.: Computational content analysis of negative tweets for obesity, diet, diabetes, and exercise. Proc. Assoc. Inf. Sci. Technol. 54(1), 357–365 (2017)CrossRefGoogle Scholar
  40. 40.
    Karami, A., et al.: Characterizing diabetes, diet, exercise, and obesity comments on twitter. Int. J. Inf. Manag. 38(1), 1–6 (2018)CrossRefGoogle Scholar
  41. 41.
    Giabbanelli, P.J., Adams, J., Pillutla, V.S.: Feasibility and framing of interventions based on public support: leveraging text analytics for policymakers. In: Meiselwitz, G. (ed.) SCSM 2016. LNCS, vol. 9742, pp. 188–200. Springer, Cham (2016). Scholar
  42. 42.
    Harris, J.K., et al.: Communication about childhood obesity on twitter. Am. J. Public Health 104(7), e62–e69 (2014)CrossRefGoogle Scholar
  43. 43.
    Lydecker, J.A., et al.: Does this tweet make me look fat? A content analysis of weight stigma on twitter. Eat. Weight. Disord.-Stud. Anorex. Bulim. Obes. 21(2), 229–235 (2016)CrossRefGoogle Scholar
  44. 44.
    Lee, J.L., et al.: What are health-related users tweeting? A qualitative content analysis of health-related users and their messages on twitter. J. Med. Internet Res. 16(10), e237 (2014)CrossRefGoogle Scholar
  45. 45.
    Alnemer, K.A., et al.: Are health-related tweets evidence based? Review and analysis of health-related tweets on twitter. J. Med. Internet Res. 17(10), e246 (2015)Google Scholar
  46. 46.
    De Gagne, J.C., et al.: Uncovering cyberincivility among nurses and nursing students on twitter: a data mining study. Int. J. Nurs. Stud. 89, 24–31 (2019)CrossRefGoogle Scholar
  47. 47.
    May, C.N., et al.: Weight loss support seeking on twitter: the impact of weight on follow back rates and interactions. Transl. Behav. Med. 7(1), 84–91 (2016)MathSciNetCrossRefGoogle Scholar
  48. 48.
    Turner-McGrievy, G.M., Beets, M.W.: Tweet for health: using an online social network to examine temporal trends in weight loss-related posts. Transl. Behav. Med. 5(2), 160–166 (2015)CrossRefGoogle Scholar
  49. 49.
    Sui, Z., et al.: Recent trends in intensive treatments of obesity: is academic research matching public interest? Surg. Obes. Relat. Dis. (2019).
  50. 50.
    O’Leary, D.E.: Twitter mining for discovery, prediction and causality: applications and methodologies. Intell. Syst. Account. Financ. Manag. 22(3), 227–247 (2015)CrossRefGoogle Scholar
  51. 51.
    Boulos, M.N.K., et al.: Social web mining and exploitation for serious applications: technosocial predictive analytics and related technologies for public health, environmental and national security surveillance. Comput. Methods Programs Biomed. 100(1), 16–23 (2010)CrossRefGoogle Scholar
  52. 52.
    Paul, M.J., Dredze, M.: You are what you tweet: analyzing twitter for public health. Icwsm 20, 265–272 (2011)Google Scholar
  53. 53.
    Eichstaedt, J.C., et al.: Psychological language on twitter predicts county-level heart disease mortality. Psychol. Sci. 26(2), 159–169 (2015)CrossRefGoogle Scholar
  54. 54.
    Ediger, D., et al.: Massive social network analysis: mining twitter for social good. In: 2010 39th International Conference on Parallel Processing, pp. 583–593. IEEE (2010)Google Scholar
  55. 55.
    Tiggemann, M., et al.: Tweeting weight loss: a comparison of# thinspiration and# fitspiration communities on twitter. Body Image 25, 133–138 (2018)CrossRefGoogle Scholar
  56. 56.
    Culotta, A.: Estimating county health statistics with twitter. In: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, pp. 1335–1344. ACM (2014)Google Scholar
  57. 57.
    Abbar, S., Mejova, Y., Weber, I.: You tweet what you eat: studying food consumption through twitter. In: Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems, pp. 3197–3206. ACM (2015)Google Scholar
  58. 58.
    Alajajian, S.E., et al.: The lexicocalorimeter: gauging public health through caloric input and output on social media. PloS One 12(2), e0168893 (2017)CrossRefGoogle Scholar
  59. 59.
    Nguyen, Q.C., et al.: Building a national neighborhood dataset from geotagged twitter datafor indicators of happiness, diet, and physical activity. JMIR Public Health Surveill. 2(2), e158 (2016)CrossRefGoogle Scholar
  60. 60.
    Eke, P.I.: Using social media for research and public health surveillance. J. Dent. Res. 90(9), 1045 (2011)CrossRefGoogle Scholar
  61. 61.
    Patel, R., et al.: Social media use in chronic disease: a systematic review and novel taxonomy. Am. J. Med. 128(12), 1335–1350 (2015)CrossRefGoogle Scholar
  62. 62.
    Charles-Smith, L.E., et al.: Using social media for actionable disease surveillance and outbreak management: a systematic literature review. PloS One 10(10), e0139701 (2015)CrossRefGoogle Scholar
  63. 63.
    Waring, M.E., et al.: Social media and obesity in adults: a review of recent research and future directions. Curr. Diabetes Rep. 18(6), 34 (2018)CrossRefGoogle Scholar
  64. 64.
    Penn, A.: Moving from overwhelming to actionable complexity in population health policy: Can alife help? (2018)CrossRefGoogle Scholar
  65. 65.
    Silverman, E.: Bringing alife and complex systems science to population health research. Artif. Life 24(3), 220–223 (2018)CrossRefGoogle Scholar
  66. 66.
    Giabbanelli, P.J., Crutzen, R.: Using agent-based models to develop public policy about food behaviours: future directions and recommendations. Comput. Math. Methods Med. (2017).
  67. 67.
    Giabbanelli, P., Crutzen, R.: An agent-based social network model of binge drinking among Dutch adults. J. Artif. Soc. Soc. Simul. 16(2), 10 (2013)CrossRefGoogle Scholar
  68. 68.
    Khademi, A., Zhang, D., Giabbanelli, P.J., Timmons, S., Luo, C., Shi, L.: An agent-based model of healthy eating with applications to hypertension. In: Giabbanelli, P.J., Mago, V.K., Papageorgiou, E.I. (eds.) Advanced Data Analytics in Health. SIST, vol. 93, pp. 43–58. Springer, Cham (2018). Scholar
  69. 69.
    Zhang, D., et al.: Impact of different policies on unhealthy dietary behaviors in an urban adult population: an agent-based simulation model. Am. J. Public Health 104(7), 1217–1222 (2014)CrossRefGoogle Scholar
  70. 70.
    Giabbanelli, P.J., et al.: Modeling the influence of social networks and environment on energy balance and obesity. J. Comput. Sci. 3(1–2), 17–27 (2012)CrossRefGoogle Scholar
  71. 71.
    Verigin, T., Giabbanelli, P.J., Davidsen, P.I.: Supporting a systems approach to healthy weight interventions in British Columbia by modeling weight and well-being. In: Proceedings of the 49th Annual Simulation Symposium, Society for Computer Simulation International, p. 9 (2016)Google Scholar
  72. 72.
    Fallah-Fini, S., et al.: Modeling us adult obesity trends: a system dynamics model for estimating energy imbalance gap. Am. J. Public Health 104(7), 1230–1239 (2014)CrossRefGoogle Scholar
  73. 73.
    Mago, V.K., et al.: Fuzzy cognitive maps and cellular automata: an evolutionary approach for social systems modelling. Appl. Soft Comput. 12(12), 3771–3784 (2012)CrossRefGoogle Scholar
  74. 74.
    Giabbanelli, P.J., Jackson, P.J., Finegood, D.T.: Modelling the joint effect of social determinants and peers on obesity among Canadian adults. In: Dabbaghian, V., Mago, V. (eds.) Theories and simulations of complex social systems. ISRL, vol. 52, pp. 145–160. Springer, Heidelberg (2014). Scholar
  75. 75.
    Giabbanelli, P.J., Crutzen, R.: Creating groups with similar expected behavioural response in randomized controlled trials: a fuzzy cognitive map approach. BMC Med. Res. Methodol. 14(1), 130 (2014)CrossRefGoogle Scholar
  76. 76.
    Pillutla, V.S., Giabbanelli, P.J.: Iterative generation of insight from text collections through mutually reinforcing visualizations and fuzzy cognitive maps. Appl. Soft Comput. 76, 459–472 (2019)CrossRefGoogle Scholar
  77. 77.
    Giabbanelli, P.J., Jackson, P.J.: Using visual analytics to support the integration of expert knowledge in the design of medical models and simulations. Procedia Comput. Sci. 51, 755–764 (2015)CrossRefGoogle Scholar
  78. 78.
    Giabbanelli, P.J., Tawfik, A.A., Gupta, V.K.: Learning analytics to support teachers’ assessment of problem solving: a novel application for machine learning and graph algorithms. In: Ifenthaler, D., Mah, D.-K., Yau, J.Y.-K. (eds.) Utilizing Learning Analytics to Support Study Success, pp. 175–199. Springer, Cham (2019). Scholar
  79. 79.
    Jianqiang, Z., Xiaolin, G.: Comparison research on text pre-processing methods on twitter sentiment analysis. IEEE Access 5, 2870–2879 (2017)CrossRefGoogle Scholar
  80. 80.
    Singh, T., Kumari, M.: Role of text pre-processing in twitter sentiment analysis. Procedia Comput. Sci. 89, 549–554 (2016)CrossRefGoogle Scholar
  81. 81.
    Symeonidis, S., Effrosynidis, D., Arampatzis, A.: A comparative evaluation of pre-processing techniques and their interactions for twitter sentiment analysis. Expert. Syst. Appl. 110, 298–310 (2018)CrossRefGoogle Scholar
  82. 82.
    Keerthi Kumar, H.M., Harish, B.S.: Classification of short text using various preprocessing techniques: an empirical evaluation. In: Sa, P.K., Bakshi, S., Hatzilygeroudis, I.K., Sahoo, M.N. (eds.) Recent Findings in Intelligent Computing Techniques. AISC, vol. 709, pp. 19–30. Springer, Singapore (2018). Scholar
  83. 83.
    Barnes, M.: Solving the problem of childhood obesity within a generation. White House Task Force on Childhood Obesity Report to the President, Washington, DC (2010)Google Scholar
  84. 84.
    Daghofer, D.: From weight to well-being: time for shift in paradigms. Technical report, a discussion paper on the inter-relationships among obesity, overweight ... (2013)Google Scholar
  85. 85.
    Shah, N., Willick, D., Mago, V.: A framework for social media data analytics using Elasticsearch and Kibana. Wirel. Netw., 1–9 (2009)Google Scholar
  86. 86.
    Rehurek, R., Sojka, P.: Software framework for topic modelling with large corpora. In: In Proceedings of the LREC 2010 Workshop on New Challenges for NLP Frameworks. Citeseer (2010)Google Scholar
  87. 87.
    Robinson, K., Mago, V.: Birds of prey: identifying lexical irregularities in spam on twitter. Wirel. Netw. 1–8 (2018).

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Mannila Sandhu
    • 1
  • Philippe J. Giabbanelli
    • 2
    Email author
  • Vijay K. Mago
    • 1
  1. 1.Department of Computer ScienceLakehead UniversityThunder BayCanada
  2. 2.Computer Science DepartmentFurman UniversityGreenvilleUSA

Personalised recommendations