Using Smartphones to Measure (and Intervenein) Daily Life
@neal_lathiaComputer LaboratoryUniversity of Cambridge
BackgroundSmartphones as Research ToolsCase 1: Subjective Wellbeing & BehaviourCase 2: Smoking CessationChallenges, Opportunities, Questions
Background
Smartphones as Research Tools
“by 2025, when most of today’s psychology undergraduates will be in their mid-30s, morethan 5 billion people on our planet will be usingultra-broadband, sensor-rich smartphones farbeyond the abilities of today’s iPhones, Androids,and Blackberries.”
G. Miller. The Smartphone Psychology Manifesto. Perspectives on PsychologicalScience. 7:3 May 2012.
AccelerometerGPS / Wi-FiGyroscopeBluetoothMicrophoneHumidityTemperaturePhone / Text LogsDevice LogsSocial Media APIsApp Usage
Accelerometer | Physical ActivityGPS / Wi-Fi | MobilityGyroscope | OrientationBluetooth | Co-LocationMicrophone | Ambient AudioHumidity | EnvironmentTemperature | EnvironmentPhone / Text Logs | SocialisingDevice Logs | NetworkSocial Media APIs | SocialisingApp Usage | Information Needs
Case 1: Subjective Wellbeing & Behaviour
N. Lathia, G. Sandstrom, P. Rentfrow, C. Mascolo (in prep). HappyPeople Live Active Lives. 2015.
“A sample of 222 undergraduates was screenedfor high happiness using multiple confirmingassessment filters. We compared the upper 10%of consistently very happy people with averageand very unhappy people. The very happy peoplewere highly social, and had stronger romantic andother social relationships than less happygroups...”
Diener, Seligman. Very Happy People. In Psychological Science 13 (1). Jan 2002.
“A sample of 222 undergraduates was screenedfor high happiness using multiple confirmingassessment filters. We compared the upper 10%of consistently very happy people with averageand very unhappy people. The very happy peoplewere highly social, and had stronger romantic andother social relationships than less happygroups...”
Diener, Seligman. Very Happy People. In Psychological Science 13 (1). Jan 2002.
Hemminki, Nurmi, Tarkoma. Accelerometer-Based Transportation Mode Detectionon Smartphones. In ACM Sensys 2013.
Statistical: mean, standard deviation, median, etc.Time: auto-correlation, mean-crossing rate, etc.Frequency: FFT, spectral energy, etc.Peak: volume, intensity, skewness, etc.Segment: e.g., velocity change rate
r(24,201) = .37, p < .001 d = .80
r(10,376) = .03, p < .001 d = .07 r(2,969) = .10, p < .001 d = .19
F(2, 10,288) = 39.08, p < .001
F(2, 9,627) = 32.52, p < .001
M = .57
M = .22
M = -.14
Happiness: M = .23
M = .27
M = -.26
27Hour of the Day Hour of the Day
Sen
sed
ph
ysic
al a
ctiv
ity
Case 2: Smoking Cessation
Naughton et al. (in prep). The feasibility of a context aware smokingcessation app (Q Sense): A mixed methods study. 2015.
Ferguson, Shiffman. The relevance and treatment of cue-induced cravings intobacco dependence. In J Subst Abuse Treat. April 2009.
“cue-induced cravings: intense,episodic cravings typicallyprovoked by situational cuesassociated with drug use [...]smokers exposed to smoking-related cues demonstrateincreased craving [...]”
Stress, Depression, Urges,Situation, Social (Other Smokers).
Stress, Depression, Urges,Situation, Social (Other Smokers).
Challenges, Opportunities, Questions
https://github.com/xsenselabshttp://easym.emotionsense.com/
11,311
5,212
3,902
2,978
2,401
1,924
1,514
Using Smartphones to Measure (and Intervenein) Daily Life