Identifying Behavioral Phenotypes of Loneliness and Social Isolation with Passive Sensing: Statistical Analysis, Data Mining and Machine Learning of Smartphone and Fitbit Data

Abstract

Background Feelings of loneliness are associated with poor physical and mental health. Detection of loneliness through passive sensing on personal devices can lead to the development of interventions aimed at decreasing rates of loneliness. Objective The aim of this study was to explore the potential of using passive sensing to infer levels of loneliness and to identify the corresponding behavioral patterns. Methods Data were collected from smartphones and Fitbits (Flex 2) of 160 college students over a semester. The participants completed the University of California, Los Angeles (UCLA) loneliness questionnaire at the beginning and end of the semester. For a classification purpose, the scores were categorized into high (questionnaire score>40) and low (≤40) levels of loneliness. Daily features were extracted from both devices to capture activity and mobility, communication and phone usage, and sleep behaviors. The features were then averaged to generate semester-level features. We used 3 analytic methods: (1) statistical analysis to provide an overview of loneliness in college students, (2) data mining using the Apriori algorithm to extract behavior patterns associated with loneliness, and (3) machine learning classification to infer the level of loneliness and the change in levels of loneliness using an ensemble of gradient boosting and logistic regression algorithms with feature selection in a leave-one-student-out cross-validation manner. Results The average loneliness score from the presurveys and postsurveys was above 43 (presurvey SD 9.4 and postsurvey SD 10.4), and the majority of participants fell into the high loneliness category (scores above 40) with 63.8% (102/160) in the presurvey and 58.8% (94/160) in the postsurvey. Scores greater than 1 standard deviation above the mean were observed in 12.5% (20/160) of the participants in both pre- and postsurvey scores. The majority of scores, however, fell between 1 standard deviation below and above the mean (pre=66.9% [107/160] and post=73.1% [117/160]). Our machine learning pipeline achieved an accuracy of 80.2% in detecting the binary level of loneliness and an 88.4% accuracy in detecting change in the loneliness level. The mining of associations between classifier-selected behavioral features and loneliness indicated that compared with students with low loneliness, students with high levels of loneliness were spending less time outside of campus during evening hours on weekends and spending less time in places for social events in the evening on weekdays (support=17% and confidence=92%). The analysis also indicated that more activity and less sedentary behavior, especially in the evening, was associated with a decrease in levels of loneliness from the beginning of the semester to the end of it (support=31% and confidence=92%). Conclusions Passive sensing has the potential for detecting loneliness in college stu...

CoRhythMo: A Computational Framework for Modeling Biobehavioral Rhythms from Mobile and Wearable Data Streams

“…We utilized a dataset of smartphone, Fitbit, and survey data collected from 138 first-year undergraduate students at an American university who were recruited for a health and well-being research study. The dataset was previously used in [23] to detect loneliness among college students. Smartphone data was collected through the AWARE framework [57] and included calls, messages, screen usage, Bluetooth, Wi-Fi, audio, and location.…”

“…They find that circadian movement (regularity of the 24h cycle of GPS change), normalized entropy(mobility between favorite locations), location variance (GPS mobility independent of location), phone usage features, usage duration, and usage frequency were highly correlated with the depression score. Doryab et al [23] studied loneliness detection through data mining and machine learning modeling of students' behavior from smartphone and Fitbit data and showed different patterns of behavior related to loneliness including less time spent off campus and in different academic facilities as well less socialization during evening hours on weekdays among students with high level of loneliness.…”

“…The total loneliness scores range from 20 to 80, with higher scores indicating higher levels of loneliness. As there is no standard cutoff for loneliness scores in the literature, we followed the same approach in [23] to divide the UCLA scores into two categories where the scores of 40 and below were categorized as 'low loneliness', and the scores above 40 were categorized as 'high loneliness'.…”

Investigating the Relationships between Mobility Behaviours and Indicators of Subjective Well–Being Using Smartphone–Based Experience Sampling and GPS Tracking

“…Beyond studies of depression, research has also linked movement patterns to other indicators of subjective well‐being, including loneliness (Ben‐Zeev et al, 2015; Doryab et al, 2019; Wang et al, 2014), stress (Ben‐Zeev et al, 2015; Sano et al, 2015; Umematsu, Sano, & Picard, 2019; Yamamoto et al, 2018; Zakaria, Balan, & Lee, 2019), happiness (Jaques et al, 2015; Umematsu et al, 2019), affect and mood (Chow et al, 2017; DeMasi & Recht, 2017; LiKamWa, Liu, Lane, & Zhong, 2013; Ma, Xu, Bai, Sun, & Zhu, 2012; Sano et al, 2018), anxiety (Sano et al, 2018), and energy (DeMasi & Recht, 2017; LiKamWa et al, 2013; Sano et al, 2018). Importantly, however, one large‐scale study (Servia‐Rodríguez et al, 2017) found no meaningful relationships between mood and GPS‐based movement patterns in a dataset of 18,000 people collected over a span of three years.…”

Personality In Conversational UI design.

“…(Keywords = "Personality, psychological Models, Social Mining");(Demiris 2018;Stocco, Savell, and Cybenko 2010; Bheemaiah, n.d.;Carducci 2013;Cheng 2017; Glaser 2016b Glaser , [a] 2016Nishida et al 2014;Rojc, Mlakar, and Kačič 2017; "7. Conversational Spaces" 2016, "New Models of Social Intelligence," n.d.;Simonton 1985;Padua 2012; Isomura, Parr, and Friston, n.d.) (Singh 2019;Doryab et al 2019; "Social Network Mining" 2014; Lappas 2011; Atzmueller 2012) S.I habits include, determination from multi -sensor cues, social contexts, habits of social contexts, as…”