Interesting question! I have to say I'm not sure exactly what you mean, but it seems like you're interested in external computer-based metrics of emotion and where implementation could have an impact on society.

 There are several readily measurable indices of emotional arousal, including skin conductance, facial muscular activation, blood pressure, respiratory rate, and more. These measures must be thoughtfully deployed as there are many things that they don't mean (for example, lie detectors can tell you the person may be lying but you don't know why or in which direction). 

 I would be interested to see some real-time data on emotional arousal in on-duty police officers who are involved in altercations during the course of their daily activity. It would be interesting to relate these activations with the officers' histories of weapon use on the job, histories of possible PTSD development, and more. 

In my view, important challenges are (1) long-term, (2) always-on, (3) in the wild sensing (and affecting). In the care domain, the transport, and the safety this is of interest. For example, for children with a chronic disease, we will sense child's (affective etc.) state over a long period of time in the Horizon2020 project, Personal Assistant for healthy Lifestyle (PAL, will start in March 2015). Second example: the monitoring of the emotional of railway traffic controllers. Third: the monitoring of emotional state of naval officers on a ship's bridge.

E.g.,

Esther J.G. van der Drift, Robbert-Jan Beun, Rosemarijn Looije, Olivier A. Blanson Henkemans, and Mark A. Neerincx. 2014. A remote social robot to motivate and support diabetic children in keeping a diary. In Proceedings of the 2014 ACM/IEEE international conference on Human-robot interaction (HRI '14). ACM, New York, NY, USA, 463-470.

Neerincx, M.A., Harbers, M., Lim, D. and Van der Tas, V. (2014). Automatic Feedback on Cognitive Load and Emotional State of Traffic Controllers. In: D. Harris (Ed.): EPCE 2014, LNAI 8532, pp. 42–49. Springer International Publishing Switzerland.

Neerincx, M.A., Kennedie, S., Grootjen, F., and Grootjen, M. (2009). Modelling Cognitive Task Load and Emotion for Adaptive Maritime Interfaces. In: Lecture Notes in Artificial Intelligence. Schmorrow, D.D.; Estabrooke, I.V.; Grootjen, M. (Eds.), Foundations of Augmented Cognition: Neuroergonomics and Operational Neuroscience. Proceedings of the 5th International Conference of the Augmented Cognition, pages 260 – 269. Berlin/Heidelberg: Springer.

From my perspective, working in a related field, the most important question is why you need emotion sensing systems? If the answer is because you want to improve health, then that is the challenge, not the sensing systems as systems, but the success of the health improving interventions. And then the challenge become, how one create good health interventions, how do one stop the destructive behavior and motivate the health improving behavior. Here I think social and cultural aspects, long time behavior and learning/mastery curves is important.

What cultural and social values do the system promote and reproduce?

How do one maintain the health improving behavior over time?

How do one create good and challenging learning and mastery experiences (curves) over time?

In our project RHYME we create multi-sensory Internet of Things (interactive MSE) to motivate social and aesthetic co-creation for children with severe disabilities and their families. Here we use musical improvisation (advanced musical algorithms) and sensory stimulation to motivate social co-creation (positive and equal creative behavior that promote both aesthetical experiences and musical mastery). 

http://rhyme.no/

Thank you all for engaging in this discussion. Would love to know more about your Horizon project Mark.

Also, Birgitta, your work RHYME project is interesting. We have been considering doing something similar based on textile and jewelleries for mental health and well-being...

Is the project still on going?

regards,

You might be interested in our paper "Emotions in context: examining pervasive affective sensing systems, applications, and analyses"

http://link.springer.com/article/10.1007%2Fs00779-015-0842-3

I see that many researchers are interesteed in affective computing and emotion recognition. I would like to share here this CFP:

http://webintelligence2017.com/program/workshops/acer-2017/

I hope that in the workshop, many of the questions about affective computing and emotion recognition will be answered.

The deadline for the workshop ACER http://webintelligence2017.com/program/workshops/acer-2017/

has been extended to May the 21st, together with all the other workshops of SCM/IEEE/WIC WI conference.

We are interested to speak to you about the asked topic at ACER.

You should submit before the deadline, which be this time strict.

Please, clickon the "Recommend" link if you want that this opportunity will reach other researchers, too. Thanks

Interesting workshop Valentine, I will ask my students to consider it.

Thanks Eliman!

One of the challenges is that EQ tests cannot consider differentiation between a computer without emotion and a human with emotion. Computers answer some questions of these tests excellently such as identification of emotion in one photo or a text. This issue is due to the use of a computerized algorithm, nor emotional intelligence of computer.

In a project, we aim at increasing the emotional intelligence of agents. Since the emotion understanding ability was not considered in the previous researches, this project introduced an emotion understanding framework for intelligent agents.

https://www.researchgate.net/project/Emotion-understanding-framework-for-intelligent-agents

Article Agents with Ability to Understand Emotions

Article An emotion understanding framework for intelligent agents ba...

Conference Paper Machine Understanding and Avoidance of Misunderstanding in A...

Article Agents with four categories of understanding abilities and t...