A system for collecting and analyzing experience-sampling data

被引:10
作者
Dennis, Simon [1 ,2 ]
Yim, Hyungwook [1 ,3 ]
Garrett, Paul [4 ]
Sreekumar, Vishnu [5 ]
Stone, Ben [1 ,2 ]
机构
[1] Univ Melbourne, Melbourne, Vic, Australia
[2] Unforgettable Res Serv Pty Ltd, Melbourne, Vic, Australia
[3] Univ Tasmania, Hobart, Tas, Australia
[4] Univ Newcastle, Callaghan, NSW, Australia
[5] NIH, Washington, DC USA
基金
澳大利亚研究理事会;
关键词
Experience sampling; Privacy; Data collection; Data analysis; PRIVACY;
D O I
10.3758/s13428-019-01260-y
中图分类号
B841 [心理学研究方法];
学科分类号
040201 ;
摘要
Online and sensor technologies promise to transform many areas of psychological enquiry. However, collecting and analyzing such data are challenging. In this article, we introduce the unforgettable.me experience-sampling platform. Unforgettable.me includes an app that can collect image, Global Positioning System, accelerometry, and audio data in a continuous fashion and upload the data to a server. The data are then automatically augmented by using online databases to identify the address, type of location, and weather conditions, as well as provide street view imagery. In addition, machine-learning classifiers are run to identify aspects of the audio data such as voice and traffic. The augmented data are available to participants in the form of a keyword search interface, as well as via several visualization mechanisms. In addition, Unforgettable Research Services partners with If This Then That (IFTTT), and so can accumulate data from any of over 600 sources, including social media, wearables, and other devices. Through IFTTT, buttons can be added as icons to smartphones to allow participants to register mood conveniently, as well as behaviors and physiological states such as happiness, microaggressions, or illness. Furthermore, unforgettable.me incorporates a mechanism that allows researchers to run experiments and analyze data within an authenticated environment without viewing users' private data.
引用
收藏
页码:1824 / 1838
页数:15
相关论文
共 20 条
  • [1] [Anonymous], 2013, BAYESIAN COGNITIVE M, DOI DOI 10.1017/CBO9781139087759
  • [2] [Anonymous], 2014, JAGS STAN
  • [3] Barber R. F., 2014, ARXIV14124451
  • [4] Cadwalladr C, 2017, GUARDIAN, P20
  • [5] Dennis S. J., 2017, Proceedings of the 39th annual conference of the cognitive science society, P295
  • [6] Differential privacy: A survey of results
    Dwork, Cynthia
    [J]. THEORY AND APPLICATIONS OF MODELS OF COMPUTATION, PROCEEDINGS, 2008, 4978 : 1 - 19
  • [7] Fancher R.E., 2012, PIONEERS PSYCHOL, V4th
  • [8] Hurlburt R.T., 2006, Phenomenology and the Cognitive Sciences, V5, P271, DOI DOI 10.1007/S11097-006-9024-0
  • [9] Larson R., 2014, Flow and the foundations of positive psychology, P21
  • [10] The BUGS project: Evolution, critique and future directions
    Lunn, David
    Spiegelhalter, David
    Thomas, Andrew
    Best, Nicky
    [J]. STATISTICS IN MEDICINE, 2009, 28 (25) : 3049 - 3067