Automatically detecting problematic use of smartphones

Abstract

Smartphone adoption has increased significantly and, with the increase in smartphone capabilities, this means that users can access the Internet, communicate, and entertain themselves anywhere and anytime. However, there is growing evidence of problematic use of smartphones that impacts both social and heath aspects of users' lives. Currently, assessment of overuse or problematic use depends on one-time, self-reported behavioral information about phone use. Due to the known issues with self-reports in such types of assessments, we explore an automated, objective and repeatable approach for assessing problematic usage. We collect a wide range of phone usage data from smartphones, identify a number of usage features that are relevant to this assessment, and build detection models based on Adaboost with machine learning algorithms automatically detecting problematic use. We found that the number of apps used per day, the ratio of SMSs to calls, the number of event-initiated sessions, the number of apps used per event initiated session, and the length of non-eventinitiated sessions are useful for detecting problematic usage. With these, a detection model can identify users with problematic usage with 89.6% accuracy (F-score of .707).

Smartphone Addiction and Associated Psychological Factors

“…A significant positive relationship between daily use and smartphone addiction was also revealed. This indicates that daily smartphone users are more likely to be addicted, which is consistent with previous research (Shin & Dey, 2013). SNS applications were found to be the most popular used by participants, which fits with the narcissism theory (Twenge & Campbell, 2013) as research suggests SNS applications significantly encourage narcissism (Keating, 2014;Mehdizadeh, 2010).…”

“…In fact, they are viewed as a mandatory device within industrialized cultures (Kwon et al, 2013). However, there is evidence to suggest that there is an over-dependence on smartphones that can lead to destructive public health inferences (Monk, Carroll, Parker, & Blythe, 2004;Palen, Salzman, & Youngs, 2001;Paragras, 2005;Sarwar, 2013), including antisocial feelings of rejection within families (Rosman, 2006) and negative clinical health implications (Shin & Dey, 2013) such as addiction (Lopez-Fernandez, Honrubia-Serrano et al, 2013). Rosen, Cheever, and Carrier (2012) defined negative relationships between psychological health and technology overuse as an "iDisorder."…”

Didn't you see my message?

“…Therefore, not being able to respond fast to a message may violate the expectations of the sender and lead to tensions in the relationship. This pressure may explain why people frequently check their phones for new messages and updates [17,21].…”

Mining User Attributes Using Large-Scale APP Lists of Smartphones

“…Based on real logs of mobile users, including usage logs of applications, GPS data, system information, global system for mobile communications data, call logs, and sensor data, users' usage patterns of mobile application in real-time and mobile environment may be discovered [21], [22]. Shin and Dey [23] proposed a model to automatically detect users' problematic usage smartphones. Mo et al [24] used GPS, call log, media, Bluetooth, calendar, acceleration, and application use frequency to predict phone users' demographic information, such as gender, job type, marital status, and age.…”