Lessons from Three Longitudinal Sensor-based Human Behavior Assessment Trials and an Approach to Support Stakeholder Management: Qualitative Study

Research output: Contribution to journalArticleScientificpeer-review

Abstract

Background:
Pervasive technologies are a popular approach to investigating various phenomena outside the laboratory, providing valuable insights into real-world human behavior and interaction with the environment. However, conducting longitudinal experiments in the wild is still challenging due to the unpredictable behavior of users, changing environments, and the limitations of current technologies.

Objective:
This study aims to provide insights and lessons to researchers and technology developers regarding the challenges and their management when designing and conducting a human behavior monitoring study in natural settings.

Methods:
We developed a qualitative coding framework to categorize and address the unique challenges encountered in real-life studies that assess human behavior and environmental factors. We applied inductive reasoning to identify issues and mitigation actions to address these challenges in three study cases using annotated sensor data. These field cases involved stress and environmental assessment in office and school settings with 27 participants for 3.5 to 7 months from 2018 to 2019, work activity recognition at a construction site with 15 participants for 3 months in 2020, and stress recognition in location-independent knowledge work with 57 participants for 2 to 5 months from 2021 to 2022. Moreover, the stakeholder identification method was used to evaluate the influence of different stakeholders.

Results:
This study provides lessons on planning, implementing, and managing a longitudinal sensor-based human behavior field trial. The findings highlight the importance of engaging stakeholders and addressing their concerns and often contradictory expectations.

Conclusions:
Our findings suggest that field trial implementation should put additional effort to clarify the expectations of stakeholders and to communicate with them throughout the study process. The framework developed provides a structured approach that can be adopted and adapted by other researchers in the field, facilitating more robust and comparable studies across different contexts. Constantly managing the possible challenges will lead to better success in longitudinal trials and developing future technology-based solutions.
Original languageEnglish
JournalJournal of Medical Internet Research
DOIs
Publication statusAccepted/In press - 16 Sept 2024
MoE publication typeA1 Journal article-refereed

Fingerprint

Dive into the research topics of 'Lessons from Three Longitudinal Sensor-based Human Behavior Assessment Trials and an Approach to Support Stakeholder Management: Qualitative Study'. Together they form a unique fingerprint.

Cite this