Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

CAN-STRESS: A Real-World Multimodal Dataset for Understanding Cannabis Use, Stress, and Physiological Responses

Reza Rahimi Azghan, Nicholas C. Glodosky, Ramesh Kumar Sah, Carrie Cuttler, Ryan McLaughlin, Michael J. Cleveland, Hassan Ghasemzadeh

TL;DR

A dataset named CAN-STRESS, collected using Empatica E4 wristbands, which serves as a reliable and rich resource for studying the physiological correlates of cannabis use and stress in naturalistic settings.

Abstract

Coping with stress is one of the most frequently cited reasons for chronic cannabis use. Therefore, it is hypothesized that cannabis users exhibit distinct physiological stress responses compared to non-users, and these differences would be more pronounced during moments of consumption. However, there is a scarcity of publicly available datasets that allow such hypotheses to be tested in real-world environments. This paper introduces a dataset named CAN-STRESS, collected using Empatica E4 wristbands. The dataset includes physiological measurements such as skin conductance, heart rate, and skin temperature from 82 participants (39 cannabis users and 43 non-users) as they went about their daily lives. Additionally, the dataset includes self-reported surveys where participants documented moments of cannabis consumption, exercise, and rated their perceived stress levels during those moments. In this paper, we publicly release the CAN-STRESS dataset, which we believe serves as a highly reliable resource for examining the impact of cannabis on stress and its associated physiological markers. I

CAN-STRESS: A Real-World Multimodal Dataset for Understanding Cannabis Use, Stress, and Physiological Responses

TL;DR

A dataset named CAN-STRESS, collected using Empatica E4 wristbands, which serves as a reliable and rich resource for studying the physiological correlates of cannabis use and stress in naturalistic settings.

Abstract

Coping with stress is one of the most frequently cited reasons for chronic cannabis use. Therefore, it is hypothesized that cannabis users exhibit distinct physiological stress responses compared to non-users, and these differences would be more pronounced during moments of consumption. However, there is a scarcity of publicly available datasets that allow such hypotheses to be tested in real-world environments. This paper introduces a dataset named CAN-STRESS, collected using Empatica E4 wristbands. The dataset includes physiological measurements such as skin conductance, heart rate, and skin temperature from 82 participants (39 cannabis users and 43 non-users) as they went about their daily lives. Additionally, the dataset includes self-reported surveys where participants documented moments of cannabis consumption, exercise, and rated their perceived stress levels during those moments. In this paper, we publicly release the CAN-STRESS dataset, which we believe serves as a highly reliable resource for examining the impact of cannabis on stress and its associated physiological markers. I

Paper Structure

This paper contains 8 sections, 3 figures, 1 table.

Table of Contents

  1. Introduction
  2. Data Modalities
  3. Self-Reported Questionnaire
  4. Physiological Data from the Wristband
  5. Descriptive Analysis of Cannabis Users and Non-Users
  6. Group-Level Trends
  7. Machine Learning for User Classification
  8. Conclusion

Figures (3)

  • Figure 1: The process of collecting physiological data using wearable devices, storing it in a centralized web portal, and enabling access for various research applications addresses the limitations of laboratory-based studies. The stored data can be used to advance research in fields such as stress detection, activity recognition, and medical diagnostics.
  • Figure 2: Comparison of dataset features between cannabis users (n=39) and non-users (n=43). Each boxplot represents participant-level summary values: (1) total recording duration (hours), (2) mean self-reported stress rating across the day, (3) mean electrodermal activity (EDA, µS), and (4) mean heart rate (bpm)
  • Figure 3: SHAP summary plot showing the top 10 most important features influencing the model’s predictions. Features related to heart rate, heart rate variability, and electrodermal activity contribute most strongly