Smartphone dependence classification using tensor factorization

Abstract

Excessive smartphone use causes personal and social problems. To address this issue, we sought to derive usage patterns that were directly correlated with smartphone dependence based on usage data. This study attempted to classify smartphone dependence using a data-driven prediction algorithm. We developed a mobile application to collect smartphone usage data. A total of 41,683 logs of 48 smartphone users were collected from March 8, 2015, to January 8, 2016. The participants were classified into the control group (SUC) or the addiction group (SUD) using the Korean Smartphone Addiction Proneness Scale for Adults (S-Scale) and a face-to-face offline interview by a psychiatrist and a clinical psychologist (SUC = 23 and SUD = 25). We derived usage patterns using tensor factorization and found the following six optimal usage patterns: 1) social networking services (SNS) during daytime, 2) web surfing, 3) SNS at night, 4) mobile shopping, 5) entertainment, and 6) gaming at night. The membership vectors of the six patterns obtained a significantly better prediction performance than the raw data. For all patterns, the usage times of the SUD were much longer than those of the SUC. From our findings, we concluded that usage patterns and membership vectors were effective tools to assess and predict smartphone dependence and could provide an intervention guideline to predict and treat smartphone dependence based on usage data.

Factors associated with smartphone addiction risk in preschool children

“…In the present study, using smartphones to watch TV shows and videos significantly increased the odds of smartphone addiction risk, whereas using smartphones for education and games did not. This finding differs from the factors associated with smartphone addiction risk among school-age children or adolescents, which included games, SNS, instant messaging, and habitual use [16][17][18][19][20][21][22][23]25]. The factors were also related to parental intervention, self-control, self-esteem, and friendship [25,26,35,36].…”

“…For the present study, the purpose of smartphone use was classified according to the methods used in prior studies on smartphone addiction to identify factors related to addiction risk: surfing the web, games, TV or video watching, music, web toon/fiction, messengers, SNS [16][17][18][19][20][21][22][23]25], and education.…”

“…In South Korea, the prevalence of smartphone addiction risk among children aged less than 10 rose from 17.9% in 2016 to 20.7% in 2018, which was the largest increase in any of the age groups [4]. Problematic smartphone use typically involves not the telephone but rather the device's internet capability [15][16][17][18][19][20][21][22][23], which is an application capability designed for a particular purpose [24]. Problematic use of the applications for entertainment (gaming being one of its forms), instant messengers and social networking services (SNS) can be generally more likely to contribute to smartphone addiction [18,19,[21][22][23]25].…”

Smartphone Use Patterns of Smartphone-dependent Children

“…The duration and the frequency of smartphone were calculated as the average values of these parameters per day during the last 1 month. Applications were classified by type as learning, news, web searching, web surfing, games, television /videos, music, webtoons, messengers, and SNS [9,15]. The webtoon category included web novels, and messengers included text messages and instant messengers.…”

Comportamiento epidemiológico de la dependencia del teléfono móvil: una perspectiva criminológica

“…One of the aspects that has greatly hindered the determination of this parameter is the use of multiple measurement systems; in some cases, these are surveys based on semi-structured interviews, and in other cases they are scales validated in certain populations [17]. There is no universally validated scale, but some of them have useful psychometric characteristics.…”