8th International Conference on Pervasive Computing Technologies for Healthcare

Research Article

PopTherapy: Coping with Stress through Pop-Culture

  • @INPROCEEDINGS{10.4108/icst.pervasivehealth.2014.255070,
        author={Pablo Paredes and Ran Giald-Bachrach and Mary Czerwinski and Asta Roseway and Kael Rowan and Javier Hernandez},
        title={PopTherapy: Coping with Stress through Pop-Culture},
        proceedings={8th International Conference on Pervasive Computing Technologies for Healthcare},
        keywords={stress therapy interventions recommender coping therapy mobile machine learning popular crowd coping},
  • Pablo Paredes
    Ran Giald-Bachrach
    Mary Czerwinski
    Asta Roseway
    Kael Rowan
    Javier Hernandez
    Year: 2014
    PopTherapy: Coping with Stress through Pop-Culture
    DOI: 10.4108/icst.pervasivehealth.2014.255070
Pablo Paredes1,*, Ran Giald-Bachrach2, Mary Czerwinski2, Asta Roseway2, Kael Rowan2, Javier Hernandez3
  • 1: University of California - Berkeley
  • 2: Microsoft Research
  • 3: MIT Media Lab
*Contact email: paredes@eecs.berkeley.edu


Stress is considered to be a modern day “global epidemic"; so given the widespread nature of this problem, it would be beneficial if solutions that help people to learn how to cope better with stress were scalable beyond what individual or group therapies can provide today. Therefore, in this work, we study the potential of smart-phones as a pervasive medium to provide therapy for the general population - "popular therapy". The work melds two novel contributions: first, a micro-intervention authoring process that focuses on repurposing popular web applications as stress management interventions; and second, a machine-learning based intervention recommender system that learns how to match interventions to individuals and their temporal circumstances over time. After four weeks, participants in our user study reported higher self-awareness of stress, lower depression-related symptoms and having learned new simple ways to deal with stress. Furthermore, participants receiving the machine-learning recommendations without option to select different ones showed a tendency towards using more constructive coping behaviors.