StudentLife

Abstract

Much of the stress and strain of student life remains hidden. The StudentLife continuous sensing app assesses the day-today and week-by-week impact of workload on stress, sleep, activity, mood, sociability, mental well-being and academic performance of a single class of 48 students across a 10 week term at Dartmouth College using Android phones. Results from the StudentLife study show a number of significant correlations between the automatic objective sensor data from smartphones and mental health and educational outcomes of the student body. We also identify a Dartmouth term lifecycle in the data that shows students start the term with high positive affect and conversation levels, low stress, and healthy sleep and daily activity patterns. As the term progresses and the workload increases, stress appreciably rises while positive affect, sleep, conversation and activity drops off. The StudentLife dataset is publicly available on the web.

The personal cockpit

“…Despite these challenges there is also growing interest in research on social interaction, such as the StudentLife project of Wang et al [222] that uses ubiquitous smartphone sensors to collect information to help improve the health and mental wellbeing of college students. Other work is exploring how interfaces can be designed to support group interaction, for example by recognizing and adapting to group configurations known as 'F-formations' [133,134].…”

Exploring User Needs for a Mobile Behavioral-Sensing Technology for Depression Management: Qualitative Study (Preprint)

“…In their study that involved 12 patients over a period of 12 weeks, they have shown that mobile behavioral sensing system could identify both depression and mania states with an accuracy of more than 70% and detect state-change with very high precision and recall [10] . The StudentLife project pioneered the use of mobile behavioral sensing technology for monitoring the daily behavior of college students to assess the impact of academic workload on the students' mental states [11]. In their 10-week study on a class of 48 Computer Science students, they found that social activities such as person-to-person conversations and sleep duration were important indicators of students' mental states.…”

Predicting Social Anxiety From Global Positioning System Traces of College Students: Feasibility Study (Preprint)

“…Importantly, embedded smartphone sensors (e.g., accelerometers, light sensors, GPS) are now advanced enough to allow for passive and continuous data collection [6,7], which are increasingly being used to enhance understanding of the relationship between objective behavior and mental health status [7][8][9][10][11][12][13]. For example, Saeb and colleagues [8,14] provided preliminary evidence that extracting location-based mobility features could be used to detect depression level.…”

“…For example, Saeb and colleagues [8,14] provided preliminary evidence that extracting location-based mobility features could be used to detect depression level. However, virtually all studies leveraging passive data in the context of mental health has focused on depression or general mood [7,9,15,16]. While some studies have attempted to use other forms of passive data in the context of social anxiety [17], none have investigated the feasibility of using mobility features to detect social anxiety symptoms.…”

“…Important contributions [7,9,14] have been made to determine how smartphonebased behavior sensing of users' health-related behavior data relates to users' mental health status and stress levels. We follow the key steps from these valuable early studies and extend the features and questions addressed, as outlined below: (1) recruiting participants and deploying a mobile application for data collection, (2) collecting data such as GPS locations, recognized activities, or self-reported data from participants during the study, (3) assessing participants' mental health status using validated clinical measures, (4) extracting meaningful features/metrics from participants' data (e.g., time spent in each different type of location), and (5) correlating these features/metrics with participants' mental health status (e.g., Pearson correlation between number of distinct locations and clinically validated measures).…”