emotion sense: from design to deployment

37
Emotion Sense: From Design to Deployment @neal_lathia – October 2014

Upload: neal-lathia

Post on 03-Jul-2015

240 views

Category:

Mobile


0 download

DESCRIPTION

Research talk @ St. Andrew's University, October 2014

TRANSCRIPT

Page 1: Emotion Sense: From Design to Deployment

Emotion Sense:From Design to Deployment@neal_lathia – October 2014

Page 2: Emotion Sense: From Design to Deployment

Background

Collecting Sensor Data

First Trial

Re-design & launch

Market & react

Analyse data

Apply to new domains

Page 3: Emotion Sense: From Design to Deployment

Background

Collecting Sensor Data

First Trial

Re-design & launch

Market & react

Analyse data

Lathia et. al. “Smartphones for Large-Scale Behaviour Change Interventions.” IEEE Pervasive.

Apply to new domains

Lathia et. al. “Open-Source Smartphone Libraries for Computational Social Science.” MCSS 2013.

Lathia et. al. “Contextual Dissonance: Design Bias in Sensor Based Experience Sampling Methods.” Ubicomp 2013.

Ongoing work.

Page 4: Emotion Sense: From Design to Deployment

Background

Collecting Sensor Data

First Trial

Re-design & launch

Market & react

Analyse data

Lathia et. al. “Smartphones for Large-Scale Behaviour Change Interventions.” IEEE Pervasive.

Apply to new domains

Page 5: Emotion Sense: From Design to Deployment
Page 6: Emotion Sense: From Design to Deployment

● …[short term] to collect research data about moods and behaviours as people experience them

● …[long term] to explore whether machine learning approaches could infer people's subjective responses/complex behaviours

● …[vision] to understand the extent that behavioural support can be automated and personalised with sensor data

Page 7: Emotion Sense: From Design to Deployment

Background

Collecting Sensor Data

First Trial

Re-design & launch

Market & react

Analyse data

Apply to new domains

Lathia et. al. “Open-Source Smartphone Libraries for Computational Social Science.” MCSS 2013.

Page 8: Emotion Sense: From Design to Deployment

“... a number of challenges remain in the development of sensor-based applications [...] there is mixed API and operating system (OS) support to access the low-level sensors...”

“A Survey of Mobile Phone Sensing,” Lane et. al

Page 9: Emotion Sense: From Design to Deployment
Page 10: Emotion Sense: From Design to Deployment

● Everything as a “sensor”● Simple API with two modes (get, subscribe);

sensor data in two lines of code● API exposes battery issues, configuration to

programmer● Student project-led evaluation● https://github.com/xsenselabs

Android ESSensorManager

Page 11: Emotion Sense: From Design to Deployment

Background

Collecting Sensor Data

First Trial

Re-design & launch

Market & react

Analyse data

Apply to new domains

Lathia et. al. “Contextual Dissonance: Design Bias in Sensor Based Experience Sampling Methods.” Ubicomp 2013.

How should we design the relationship between interacting and collecting 'labelled' data?

Page 12: Emotion Sense: From Design to Deployment

We built a system that includes: sensor data collection, ESM interfaces, etc., and remote reconfiguration.

Page 13: Emotion Sense: From Design to Deployment

22 users; 1-month; questions about mood & current context (location, sociability); background sensing from many sensors; triggers remotely reconfigured weekly.

Page 14: Emotion Sense: From Design to Deployment
Page 15: Emotion Sense: From Design to Deployment

Dissonance; a tension or clash resulting from the combination of two disharmonious elements

Page 16: Emotion Sense: From Design to Deployment

Dissonance; between using sensor states to trigger ESM surveys while using sensor data to quantify context and behaviour.

Page 17: Emotion Sense: From Design to Deployment
Page 18: Emotion Sense: From Design to Deployment

Background

Collecting Sensor Data

First Trial

Re-design & launch

Market & react

Analyse data

Apply to new domains

Page 19: Emotion Sense: From Design to Deployment
Page 20: Emotion Sense: From Design to Deployment
Page 21: Emotion Sense: From Design to Deployment
Page 22: Emotion Sense: From Design to Deployment
Page 23: Emotion Sense: From Design to Deployment
Page 24: Emotion Sense: From Design to Deployment
Page 25: Emotion Sense: From Design to Deployment
Page 26: Emotion Sense: From Design to Deployment
Page 27: Emotion Sense: From Design to Deployment
Page 28: Emotion Sense: From Design to Deployment
Page 29: Emotion Sense: From Design to Deployment
Page 30: Emotion Sense: From Design to Deployment

Background

Collecting Sensor Data

First Trial

Re-design & launch

Market & react

Analyse data

Apply to new domains Ongoing work.

Page 31: Emotion Sense: From Design to Deployment

We have:State/trait surveysContext labelsSensor data

Page 32: Emotion Sense: From Design to Deployment

signals of behaviour

Page 33: Emotion Sense: From Design to Deployment
Page 34: Emotion Sense: From Design to Deployment

Background

Collecting Sensor Data

First Trial

Re-design & launch

Market & react

Analyse data

Apply to new domains Ongoing work.

Page 35: Emotion Sense: From Design to Deployment

Generalise sensor-enhanced experience sampling tool. Currently in alpha testing.

Page 36: Emotion Sense: From Design to Deployment
Page 37: Emotion Sense: From Design to Deployment

Emotion Sense:From Design to Deployment@neal_lathia – October 2014