Data Mining in the Development of Mobile Health Apps: Assessing In-App Navigation Through Markov Chain Analysis

Background Mobile apps generate vast amounts of user data. In the mobile health (mHealth) domain, researchers are increasingly discovering the opportunities of log data to assess the usage of their mobile apps. To date, however, the analysis of these data are often limited to descriptive statistics. Using data mining techniques, log data can offer significantly deeper insights. Objective The purpose of this study was to assess how Markov Chain and sequence clustering analysis can be used to find meaningful usage patterns of mHealth apps. Methods Using the data of a 25-day field trial (n=22) of the Start2Cycle app, an app developed to encourage recreational cycling in adults, a transition matrix between the different pages of the app was composed. From this matrix, a Markov Chain was constructed, enabling intuitive user behavior analysis. Results Through visual inspection of the transitions, 3 types of app use could be distinguished (route tracking, gamification, and bug reporting). Markov Chain–based sequence clustering was subsequently used to demonstrate how clusters of session types can otherwise be obtained. Conclusions Using Markov Chains to assess in-app navigation presents a sound method to evaluate use of mHealth interventions. The insights can be used to evaluate app use and improve user experience.

[1]  J. Bernhardt,et al.  Behavioral Functionality of Mobile Apps in Health Interventions: A Systematic Review of the Literature , 2015, JMIR mHealth and uHealth.

[2]  C. Vandelanotte,et al.  Are Health Behavior Change Interventions That Use Online Social Networks Effective? A Systematic Review , 2014, Journal of medical Internet research.

[3]  Lucy Yardley,et al.  A Framework for Analyzing and Measuring Usage and Engagement Data (AMUsED) in Digital Interventions: Viewpoint , 2019, Journal of medical Internet research.

[4]  Harri Oinas-Kukkonen,et al.  Understanding persuasion contexts in health gamification: A systematic analysis of gamified health behavior change support systems literature , 2016, Int. J. Medical Informatics.

[5]  Muffy Calder,et al.  Probabilistic Model Checking of DTMC Models of User Activity Patterns , 2014, QEST.

[6]  Sandra L. Calvert,et al.  Motivating Effects of Cooperative Exergame Play for Overweight and Obese Adolescents , 2012, Journal of diabetes science and technology.

[7]  Christian Koehler,et al.  Why we use and abandon smart devices , 2015, UbiComp.

[8]  Matthew Chalmers,et al.  Probabilistic Formal Analysis of App Usage to Inform Redesign , 2015, IFM.

[9]  Matthew Chalmers,et al.  Non-parametric Bayes to infer playing strategies adopted in a population of mobile gamers , 2015 .

[10]  Juho Hamari,et al.  Do badges increase user activity? A field experiment on the effects of gamification , 2017, Comput. Hum. Behav..

[11]  Corneel Vandelanotte,et al.  The effectiveness of e-& mHealth interventions to promote physical activity and healthy diets in developing countries: A systematic review , 2016, International Journal of Behavioral Nutrition and Physical Activity.

[12]  Padhraic Smyth,et al.  Model-Based Clustering and Visualization of Navigation Patterns on a Web Site , 2003, Data Mining and Knowledge Discovery.

[13]  Paula Forbes,et al.  mHealth applications for diabetes: User preference and implications for app development , 2016, Health Informatics J..

[14]  Hong Xue,et al.  A Systematic Review of Application and Effectiveness of mHealth Interventions for Obesity and Diabetes Treatment and Self-Management. , 2017, Advances in nutrition.

[15]  R. Whittaker,et al.  Do physical activity and dietary smartphone applications incorporate evidence-based behaviour change techniques? , 2014, BMC Public Health.

[16]  Lena Mamykina,et al.  No longer wearing: investigating the abandonment of personal health-tracking technologies on craigslist , 2015, UbiComp.

[17]  Ann Blandford,et al.  Understanding and Promoting Effective Engagement With Digital Behavior Change Interventions. , 2016, American journal of preventive medicine.

[18]  Denis Helic,et al.  Detecting Memory and Structure in Human Navigation Patterns Using Markov Chain Models of Varying Order , 2014, PloS one.

[19]  Yun Ma,et al.  Roaming across the Castle Tunnels: an Empirical Study of Inter-App Navigation Behaviors of Android Users , 2017, ArXiv.

[20]  Floor Sieverink,et al.  Opening the Black Box of Electronic Health: Collecting, Analyzing, and Interpreting Log Data , 2017, JMIR research protocols.

[21]  Rajeev Motwani,et al.  The PageRank Citation Ranking : Bringing Order to the Web , 1999, WWW 1999.

[22]  Marielba Zacarias,et al.  Approaching Process Mining with Sequence Clustering: Experiments and Findings , 2007, BPM.

[23]  Andreas Hotho,et al.  Photowalking the City: Comparing Hypotheses About Urban Photo Trails on Flickr , 2015, SocInfo.

[24]  Daniel R. Bateman,et al.  Categorizing Health Outcomes and Efficacy of mHealth Apps for Persons With Cognitive Impairment: A Systematic Review , 2017, Journal of medical Internet research.

[25]  T. Moon.  The expectation-maximization algorithm , 1996, IEEE Signal Process. Mag..

[26]  Heinz Mandl,et al.  How gamification motivates: An experimental study of the effects of specific game design elements on psychological need satisfaction , 2017, Comput. Hum. Behav..

[27]  D. Asch,et al.  Wearable devices as facilitators, not drivers, of health behavior change. , 2015, JAMA.

[28]  A. Staiano,et al.  Better Together: Outcomes of Cooperation Versus Competition in Social Exergaming. , 2015, Games for health journal.

[29]  Ann Blandford,et al.  Conceptualising engagement with digital behaviour change interventions: a systematic review using principles from critical interpretive synthesis , 2016, Translational behavioral medicine.

[30]  Mark Levene,et al.  Evaluating Variable-Length Markov Chain Models for Analysis of User Web Navigation Sessions , 2007, IEEE Transactions on Knowledge and Data Engineering.

[31]  Gerhard Weiss,et al.  Machine learning techniques in eating behavior e-coaching , 2017, Personal and Ubiquitous Computing.

[32]  Nachiappan Nagappan,et al.  What Drives People: Creating Engagement Profiles of Players from Game Log Data , 2015, CHI PLAY.

[33]  Jeffrey Heer,et al.  D³ Data-Driven Documents , 2011, IEEE Transactions on Visualization and Computer Graphics.

[34]  Lucy Yardley,et al.  A Visualization Tool to Analyse Usage of Web-Based Interventions: The Example of Positive Online Weight Reduction (POWeR) , 2015, JMIR human factors.