MoodScope

LiKamWa, Robert; Liu, Yunxin; Lane, Nicholas D.; Lin, Zhouchen

doi:10.1145/2462456.2464449

Cited by 287 publications

(113 citation statements)

References 23 publications

Supporting

Mentioning

108

Contrasting

Order By: Relevance

“…This was an explorative uncontrolled pilot study, replicating the methods of LiKamWa et al [13]. A small group of Dutch university students (N=27) self-monitored their mood on their mobile phones for 6 weeks.…”

Section: Methodsmentioning

confidence: 99%

“…This app prompted participants to rate their mood on their smartphone at five set time points per day (ie, approximately 09:00, 12:00, 15:00, 18:00, and 21:00). As in the study by LiKamWa et al [13], we assessed mood through the circumplex model of affect [18], which conceptualizes mood as a two-dimensional construct comprising different levels of valence (positive/negative affect) and arousal. Levels on both dimensions were tapped on a 5-point scale scored from -2 to 2 (low to high).…”

Section: Methodsmentioning

confidence: 99%

“…In a pioneering study, LiKamWa et al [13] explored personalized regression modeling to predict day-to-day fluctuations of self-monitored mood from unobtrusively collected proxy variables of social activity, physical activity, and general mobile phone use. With mobile phone-logged data collected from 32 participants over 2 months, they found the predictive accuracy of personalized models to be high.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Mobile Phone-Based Unobtrusive Ecological Momentary Assessment of Day-to-Day Mood: An Explorative Study

Asselbergs¹,

Ruwaard²,

Ejdys³

et al. 2016

J Med Internet Res

190

120

View full text Add to dashboard Cite

BackgroundEcological momentary assessment (EMA) is a useful method to tap the dynamics of psychological and behavioral phenomena in real-world contexts. However, the response burden of (self-report) EMA limits its clinical utility.ObjectiveThe aim was to explore mobile phone-based unobtrusive EMA, in which mobile phone usage logs are considered as proxy measures of clinically relevant user states and contexts.MethodsThis was an uncontrolled explorative pilot study. Our study consisted of 6 weeks of EMA/unobtrusive EMA data collection in a Dutch student population (N=33), followed by a regression modeling analysis. Participants self-monitored their mood on their mobile phone (EMA) with a one-dimensional mood measure (1 to 10) and a two-dimensional circumplex measure (arousal/valence, –2 to 2). Meanwhile, with participants’ consent, a mobile phone app unobtrusively collected (meta) data from six smartphone sensor logs (unobtrusive EMA: calls/short message service (SMS) text messages, screen time, application usage, accelerometer, and phone camera events). Through forward stepwise regression (FSR), we built personalized regression models from the unobtrusive EMA variables to predict day-to-day variation in EMA mood ratings. The predictive performance of these models (ie, cross-validated mean squared error and percentage of correct predictions) was compared to naive benchmark regression models (the mean model and a lag-2 history model).ResultsA total of 27 participants (81%) provided a mean 35.5 days (SD 3.8) of valid EMA/unobtrusive EMA data. The FSR models accurately predicted 55% to 76% of EMA mood scores. However, the predictive performance of these models was significantly inferior to that of naive benchmark models.ConclusionsMobile phone-based unobtrusive EMA is a technically feasible and potentially powerful EMA variant. The method is young and positive findings may not replicate. At present, we do not recommend the application of FSR-based mood prediction in real-world clinical settings. Further psychometric studies and more advanced data mining techniques are needed to unlock unobtrusive EMA’s true potential.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Mobile Phone-Based Unobtrusive Ecological Momentary Assessment of Day-to-Day Mood: An Explorative Study

Asselbergs¹,

Ruwaard²,

Ejdys³

et al. 2016

J Med Internet Res

190

120

View full text Add to dashboard Cite

show abstract

“…For instance, in day 1 the predicted SIAS is calculated from the prediction of day 1 only, in day 2 the predicted SIAS is the average of predicted SIAS of day 1 and day 2 and so on. Figure 1 shows the evolution of RMSE over time obtained by averaging the RMSE of all participants in day i∈ [1,15] . We notice that for our method, the average RMSE is decreasing over time after the third day.…”

Section: Figurementioning

confidence: 99%

“…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.…”

Section: Introductionmentioning

confidence: 99%

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

Boukhechba¹,

Chow²,

Fua³

et al. 2018

Preprint

View full text Add to dashboard Cite

Background: Social anxiety is highly prevalent among college students. Current methodologies for detecting symptoms are based on client self-report in traditional clinical settings. Self-report is subject to recall bias while visiting a clinic requires a high level of motivation. Assessment methods that use passively collected data hold promise for detecting social anxiety symptoms and supplementing self-report measures. Continuously collected location data may provide a fine-grained and ecologically valid way to assess social anxiety in situ. Objective: The current study examines the feasibility of leveraging non-invasive mobile sensing technology to passively assess college students' social anxiety symptom level. Specifically, we explore the different relationships between mobility and social anxiety to build a predictive model that assesses social anxiety from passively generated Global Positioning System (GPS) data. Methods: 228 undergraduate participants were recruited from a Southeast American university. Social anxiety symptoms were assessed using self-report instruments at a baseline laboratory session. An app installed on people's personal mobile phones passively sensed data from the GPS sensor for two weeks. The proposed framework supports longitudinal, dynamic tracking of college students to evaluate the relationship between their social anxiety and movement patterns in the college campus environment. We first extracted several mobility features: (1) cumulative staying time in each different location, (2) the distribution of visits over time, (3) the entropy of locations, and (4) the frequency of transitions between locations. Next, we studied the correlation between these features and participants' social anxiety scores to enhance understanding of how students' social anxiety levels are associated with their mobility. Finally, we used a neural network-based prediction method to predict social anxiety symptoms from the extracted daily mobility features. Results: Several mobility features correlate with social anxiety level. Location entropy is negatively associated with social anxiety (r=-0.67 during weekdays and r=-0.51 during weekends). More (vs. less) socially anxious students were found to avoid public areas and engage in less leisure activities during evenings and weekends, choosing instead to spend more time at home after school (4pm-12am). Our prediction method based on extracted mobility features from GPS trajectories successfully classified participants as high or low socially anxious with an accuracy of 85% and predicted their social anxiety score (on a scale of 0 to 80) with a rootmean-square error of 7.06. Conclusions: Results indicate that extracting and analyzing mobility features may help to reveal how social anxiety symptoms manifest in the daily lives of college students. Given the ubiquity of mobile phones in our society, understanding how to leverage passively sensed data has strong potential to address the growing needs for mental health monitoring and treatment.

show abstract