Applying Natural Language Processing to Understand Motivational Profiles for Maintaining Physical Activity After a Mobile App and Accelerometer-Based Intervention: The mPED Randomized Controlled Trial

Yoshimi Fukuoka, Teri G Lindgren, Yonatan Dov Mintz, Julie Hooper, Anil Aswani, Yoshimi Fukuoka, Teri G Lindgren, Yonatan Dov Mintz, Julie Hooper, Anil Aswani

Abstract

Background: Regular physical activity is associated with reduced risk of chronic illnesses. Despite various types of successful physical activity interventions, maintenance of activity over the long term is extremely challenging.

Objective: The aims of this original paper are to 1) describe physical activity engagement post intervention, 2) identify motivational profiles using natural language processing (NLP) and clustering techniques in a sample of women who completed the physical activity intervention, and 3) compare sociodemographic and clinical data among these identified cluster groups.

Methods: In this cross-sectional analysis of 203 women completing a 12-month study exit (telephone) interview in the mobile phone-based physical activity education study were examined. The mobile phone-based physical activity education study was a randomized, controlled trial to test the efficacy of the app and accelerometer intervention and its sustainability over a 9-month period. All subjects returned the accelerometer and stopped accessing the app at the last 9-month research office visit. Physical engagement and motivational profiles were assessed by both closed and open-ended questions, such as "Since your 9-month study visit, has your physical activity been more, less, or about the same (compared to the first 9 months of the study)?" and, "What motivates you the most to be physically active?" NLP and cluster analysis were used to classify motivational profiles. Descriptive statistics were used to compare participants' baseline characteristics among identified groups.

Results: Approximately half of the 2 intervention groups (Regular and Plus) reported that they were still wearing an accelerometer and engaging in brisk walking as they were directed during the intervention phases. These numbers in the 2 intervention groups were much higher than the control group (overall P=.01 and P=.003, respectively). Three clusters were identified through NLP and named as the Weight Loss group (n=19), the Illness Prevention group (n=138), and the Health Promotion group (n=46). The Weight Loss group was significantly younger than the Illness Prevention and Health Promotion groups (overall P<.001). The Illness Prevention group had a larger number of Caucasians as compared to the Weight Loss group (P=.001), which was composed mostly of those who identified as African American, Hispanic, or mixed race. Additionally, the Health Promotion group tended to have lower BMI scores compared to the Illness Prevention group (overall P=.02). However, no difference was noted in the baseline moderate-to-vigorous intensity activity level among the 3 groups (overall P>.05).

Conclusions: The findings could be relevant to tailoring a physical activity maintenance intervention. Furthermore, the findings from NLP and cluster analysis are useful methods to analyze short free text to differentiate motivational profiles. As more sophisticated NL tools are developed in the future, the potential of NLP application in behavioral research will broaden.

Trial registration: ClinicalTrials.gov NCT01280812; https://ichgcp.net/clinical-trials-registry/NCT01280812 (Archived by WebCite at http://www.webcitation.org/70IkGagAJ).

Keywords: accelerometer; barriers; behavioral change; fitness trackers; maintenance; mobile apps; motivation; physical activity; randomized controlled trial; women.

Conflict of interest statement

Conflicts of Interest: None declared.

©Yoshimi Fukuoka, Teri G Lindgren, Yonatan Dov Mintz, Julie Hooper, Anil Aswani. Originally published in JMIR Mhealth and Uhealth (http://mhealth.jmir.org), 20.06.2018.

Figures

Figure 1
Figure 1
Elbow curve used to determine the number of clusters to be used in K-means clustering. On the x-axis are the number of clusters which the algorithm was set to fit and on the y-axis is the mean squared error of the clustering. The red dot is located at the mark which corresponds to 3 clusters and corresponds to the closest number of clusters to the “bend” of the elbow curve.
Figure 2
Figure 2
Principal Components Analysis (PCA) Visualization of motivational profiles. The plot axes represent the first two principal components of the bag-of-words vector representations of the motivations given by patients. The purple cluster corresponds to the responses of patients who listed weight loss as their sole motivation for physical activity, the teal cluster corresponds to patients who were primarily motivated by illness prevention, and the yellow cluster corresponds to those patients primarily motivated to do physical activity due to health promotion.

References

    1. Rossi A, Dikareva A, Bacon SL, Daskalopoulou SS. The impact of physical activity on mortality in patients with high blood pressure: a systematic review. J Hypertens. 2012 Jul;30(7):1277–88. doi: 10.1097/HJH.0b013e3283544669.
    1. Mammen G, Faulkner G. Physical activity and the prevention of depression: a systematic review of prospective studies. Am J Prev Med. 2013 Nov;45(5):649–57. doi: 10.1016/j.amepre.2013.08.001.
    1. Gallaway P, Miyake H, Buchowski MS, Shimada M, Yoshitake Y, Kim AS, Hongu N. Physical Activity: A Viable Way to Reduce the Risks of Mild Cognitive Impairment, Alzheimer's Disease, and Vascular Dementia in Older Adults. Brain Sci. 2017 Feb 20;7(2) doi: 10.3390/brainsci7020022.
    1. Ford ES, Li C, Zhao G, Pearson WS, Tsai J, Churilla JR. Sedentary behavior, physical activity, and concentrations of insulin among US adults. Metabolism. 2010 Sep;59(9):1268–75. doi: 10.1016/j.metabol.2009.11.020.
    1. Olver IN. Prevention of breast cancer. Med J Aust. 2016 Nov 21;205(10):475–479.
    1. Gonçalves AK, Dantas Florencio GL, Maisonnette de Atayde Silva MJ, Cobucci RN, Giraldo PC, Cote NM. Effects of physical activity on breast cancer prevention: a systematic review. J Phys Act Health. 2014 Feb;11(2):445–54. doi: 10.1123/jpah.2011-0316.
    1. Amireault S, Godin G, Vézina-Im L. Determinants of physical activity maintenance: a systematic review and meta-analyses. Health Psychology Review. 2013 Mar;7(1):55–91. doi: 10.1080/17437199.2012.701060.
    1. Nigg CR, Borrelli B, Maddock J, Dishman RK. A theory of physical activity maintenance. Applied Psychology. 2008 Jul 08;57(4):544–560. doi: 10.1111/j.1464-0597.2008.00343.x.
    1. Luke A, Dugas LR, Durazo-Arvizu RA, Cao G, Cooper RS. Assessing physical activity and its relationship to cardiovascular risk factors: NHANES 2003-2006. BMC Public Health. 2011 May 25;11:387. doi: 10.1186/1471-2458-11-387.
    1. Carlson S, Densmore D, Fulton JE, Yore MM, Kohl III HW. Differences in physical activity prevalence and trends from 3 U.S. surveillance systems: NHIS, NHANES, and BRFSS. J Phys Act Health. 2009;6 Suppl 1:S18–27.
    1. Vansteenkiste M, Sierens E, Soenens B, Luyckx K, Lens W. Motivational profiles from a self-determination perspective: The quality of motivation matters. Journal of Educational Psychology. 2009;101(3):671–688. doi: 10.1037/a0015083.
    1. Pew Research Center: Internet & Technology. Washington, DC: Pew Research Center; 2018. Feb 05, [2018-05-15]. Mobile Fact Sheet
    1. Crain AL, Martinson BC, Sherwood NE, O'Connor PJ. The long and winding road to physical activity maintenance. Am J Health Behav. 2010;34(6):764–75.
    1. Schoeppe S, Alley S, Van Lippevelde W, Bray NA, Williams SL, Duncan MJ, Vandelanotte C. Efficacy of interventions that use apps to improve diet, physical activity and sedentary behaviour: a systematic review. Int J Behav Nutr Phys Act. 2016 Dec 07;13(1):127. doi: 10.1186/s12966-016-0454-y.
    1. Jurafsky D, Martin JH. Speech and Language Processing, 2nd Edition. Upper Saddle River, NJ: Pearson, Prentice Hall; 2009.
    1. Hazlehurst B, Lawrence JM, Donahoo WT, Sherwood NE, Kurtz SE, Xu S, Steiner JF. Automating assessment of lifestyle counseling in electronic health records. Am J Prev Med. 2014 May;46(5):457–64. doi: 10.1016/j.amepre.2014.01.001.
    1. Murff H, FitzHenry F, Matheny ME, Gentry N, Kotter KL, Crimin K, Dittus RS, Rosen AK, Elkin PL, Brown SH, Speroff T. Automated identification of postoperative complications within an electronic medical record using natural language processing. JAMA. 2011 Aug 24;306(8):848–55. doi: 10.1001/jama.2011.1204.
    1. Jensen PB, Jensen LJ, Brunak S. Mining electronic health records: towards better research applications and clinical care. Nat Rev Genet. 2012 May 02;13(6):395–405. doi: 10.1038/nrg3208.
    1. Polepalli RB, Houston T, Brandt C, Fang H, Yu H. Improving patients' electronic health record comprehension with NoteAid. Stud Health Technol Inform. 2013;192:714–8.
    1. Maddox T, Matheny MA. Natural Language Processing and the Promise of Big Data: Small Step Forward, but Many Miles to Go. Circ Cardiovasc Qual Outcomes. 2015 Sep;8(5):463–5. doi: 10.1161/CIRCOUTCOMES.115.002125.
    1. Fukuoka Y, Komatsu J, Suarez L, Vittinghoff E, Haskell W, Noorishad T, Pham K. The mPED randomized controlled clinical trial: applying mobile persuasive technologies to increase physical activity in sedentary women protocol. BMC Public Health. 2011 Dec 14;11:933. doi: 10.1186/1471-2458-11-933.
    1. Fukuoka Y, Gay C, Haskell W, Arai S, Vittinghoff E. Identifying Factors Associated With Dropout During Prerandomization Run-in Period From an mHealth Physical Activity Education Study: The mPED Trial. JMIR Mhealth Uhealth. 2015 Apr 13;3(2):e34. doi: 10.2196/mhealth.3928.
    1. Fukuoka Y, Haskell W, Vittinghoff E. New insights into discrepancies between self-reported and accelerometer-measured moderate to vigorous physical activity among women - the mPED trial. BMC Public Health. 2016 Dec 11;16(1):761. doi: 10.1186/s12889-016-3348-7.
    1. Mikolov T, Sutskever I, Chen K, Corrado GS, Dean J. Distributed representations of words and phrases and their compositionality. Neural information processing systems 2013; Dec, 2013; Lake Tahoe, CA. 2013.
    1. Goldberg Y, Levy O. word2vec Explained: deriving Mikolov et al.'s negative-sampling word-embedding method. Cornell University Library. 2014
    1. Sviridov A. GitHub Repository. 2017. Oct 09, [2018-05-15].
    1. Bird S. NLTK: The natural language toolkit. Proceedings of the COLING/ACL 2006 Interactive Presentation Sessions; Association for Computational Linguistics; 2006; Sydney, Australia. 2006. Jul, pp. 69–72.
    1. Rehurek R, Sojka P. Software framework for topic modelling with large corpora. Proceedings of LREC 2010 workshop New Challenges for NLP Frameworks; 2010; Valletta, Malta. University of Malta; 2010.
    1. James G, Witten D, Hastie T, Tibshirani R. An Introduction to Statistical Learning: with Applications in R. New York, NY: Springer-Verlag New York; 2013. Chapter 10: Unsupervised Learning.
    1. Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Bolndel M, Prettenhofer P, Weiss R, Duborurg V, Vanderplas J, Passos A, Cournapeau D, Brucher M, Perrot M, Duchesnay E. Scikit-learn: Machine learning in Python. Journal of Machine Learning Research. 2011;12:2825–2830.
    1. Wikipedia. Wikipedia Foundation, Inc; [2018-05-16]. Principal Component Analysis .
    1. Friederichs S, Bolman C, Oenema A, Lechner L. Profiling physical activity motivation based on self-determination theory: a cluster analysis approach. BMC Psychol. 2015;3(1):1. doi: 10.1186/s40359-015-0059-2.
    1. Yli-Piipari S, Watt A, Jaakkola T, Liukkonen J, Nurmi J. Relationships between physical education students' motivational profiles, enjoyment, state anxiety, and self-reported physical activity. J Sports Sci Med. 2009;8(3):327–36.
    1. Cerar K, Kondrič M, Sindik J. The profiling of university of Ljubljana students according to their motives for exercise participation. Zdr Varst. 2017 Jun 01;56(2):107–114. doi: 10.1515/sjph-2017-0014.
    1. Biddle SJH, Wang CKJ. Motivation and self-perception profiles and links with physical activity in adolescent girls. J Adolesc. 2003 Dec;26(6):687–701.
    1. Mayorga-Vega D, Viciana J. Adolescents' physical activity in physical education, school recess, and extra-curricular sport by motivational profiles. Percept Mot Skills. 2014 Jun;118(3):663–79. doi: 10.2466/06.10.PMS.118k26w0.
    1. Granero-Gallegos A, Baena-Extremera A, Pérez-Quero FJ, Ortiz-Camacho MM, Bracho-Amador C. Analysis of motivational profiles of satisfaction and importance of physical education in high school adolescents. J Sports Sci Med. 2012;11(4):614–23.
    1. Kalaja S, Jaakkola T, Liukkonen J, Watt A. Fundamental movement skills and motivational factors influencing engagement in physical activity. Percept Mot Skills. 2010 Aug;111(1):115–28. doi: 10.2466/06.10.25.PMS.111.4.115-128.
    1. Wang C, Chatzisarantis NL, Spray CM, Biddle SJ. Achievement goal profiles in school physical education: differences in self-determination, sport ability beliefs, and physical activity. Br J Educ Psychol. 2002 Sep;72(Pt 3):433–45.
    1. Naisseh M, Martinent G, Ferrand C, Hautier C. Relationship between parents' motivation for physical activity and their beliefs, and support of their children's physical activity: a cluster analysis. Psychol Rep. 2015 Aug;117(1):230–43. doi: 10.2466/06.21.PR0.117c17z0.
    1. Ríos D, Cubedo M, Ríos M. Graphical study of reasons for engagement in physical activity in European Union. Springerplus. 2013 Sep 26;2:488. doi: 10.1186/2193-1801-2-488.
    1. Fukuoka Y, Lindgren TG, Bonnet K, Kamitani E. Perception and Sense of Control Over Eating Behaviors Among a Diverse Sample of Adults at Risk for Type 2 Diabetes. Diabetes Educ. 2014 May;40(3):308–318. doi: 10.1177/0145721714522717.
    1. Teixeira P, Carraça EV, Markland D, Silva MN, Ryan RM. Exercise, physical activity, and self-determination theory: a systematic review. Int J Behav Nutr Phys Act. 2012 Jun 22;9:78. doi: 10.1186/1479-5868-9-78.
    1. McGrane N, Galvin R, Cusack T, Stokes E. Addition of motivational interventions to exercise and traditional physiotherapy: a review and meta-analysis. Physiotherapy. 2015 Mar;101(1):1–12. doi: 10.1016/j.physio.2014.04.009.
    1. Mikolov T, Yih W, Zweig G. Linguistic regularities in continuous space word representations. The 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies; Jun, 2013; Atlanta, GA. 2013. pp. 746–751.

Source: PubMed

Sponsors and Collaborators

Medical Conditions

Drug Interventions

3
Subscribe