Open-access data platform for behavioural monitoring and visual analytics for mental health

Sharing personal data about daily behaviours and mental health can be useful for communication, peer-support and science, but such disclosure may also bring negative consequences. How can we design open-access platforms that are beneficial for individuals and society?


Passive data collected from smartphones, such as time spent on screen, location and text messages can be used for the assessment of affective states and behaviours [1]. Such personal and detailed data can be employed as a tool for self-reflection, an approach often used for encouraging behavioural change. Further uses of the data may involve opening the access of the self-tracked data to clinicians, peers, family member or researchers [2, 3]. However, when it comes to sharing such sensitive data, special care has to be taken, as it contains intimate details of the individuals' lives [4]. A major issue with data containing mental health assessments is the social stigma and discrimination that may come with it [5]. Therefore, the contribution of this PhD will come in the form of a conceptual framework [6] with design guidelines that can inform designers of future open access platforms, that may be used, in particular, for investigating and tackling digital stress symptoms among teens. The term digital stress refers to the negative psychological effects of being constantly connected to digital technologies [7]. In particular, the prevalence of technology usage among young users and teenagers and the lack of coping mechanisms can make them vulnerable to digital stress, thus the importance of such theme.

Project objectives:

Identify the challenges and requirements of the design of shared-access data platforms
Investigate how to address these needs in order to build systems that users can trust
Organise design guidelines in a conceptual framework for future developments


[1] Darius A Rohani, Maria Faurholt-Jepsen, Lars Vedel Kessing, and Jakob E Bardram. 2018. Correlations Between Objective Behavioral Features Collected From Mobile and Wearable Devices and Depressive Mood Symptoms in Patients With Affective Disorders: Systematic Review. JMIR Mhealth Uhealth 6, 8 (13Aug 2018), e165.

[2] Helena M. Mentis, Anita Komlodi, Katrina Schrader, Michael Phipps, Ann Gruber-Baldini, Karen Yarbrough, and Lisa Shulman. 2017. Crafting a View of Self-Tracking Data in the Clinical Visit. In Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems (CHI ’17). ACM, New York, NY,USA, 5800–5812.

[3] Ross JS and Krumholz HM. 2016. Open access platforms for sharing clinical trial data.JAMA316, 6(2016), 666.

[4] Camille Nebeker, John Harlow, Rebeca Espinoza Giacinto, Rubi Orozco-Linares, Cinnamon S. Bloss, and Nadir Weibel. 2017. Ethical and regulatory challenges of research using pervasive sensing and other emerging technologies: IRB perspectives. AJOB Empirical Bioethics 8, 4 (2017), 266–276.

[5] Christina Kelley, Bongshin Lee, and Lauren Wilcox.2017. Self-tracking for mental wellness: understanding expert perspectives and student experiences. In Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems. ACM, 629–641.

[6] Gabriela Marcu, Jakob E Bardram, and Silvia Gabrielli.2011. A framework for overcoming challenges in designing persuasive monitoring and feedback systems for mental illness. In2011 5th International Conference on Pervasive Computing Technologies for Healthcare (Pervasive Health) and Workshops. IEEE,1–8.

[7] Emily C Weinstein and Robert L Selman. 2016. Digital stress: Adolescents’ personal accounts. New media & society 18, 3 (2016), 391–409.



Giovanna Nunes Vilaza
PhD student
DTU Health Tech
+45 45 25 37 24
19 APRIL 2019