Affectiva: Measuring Emotion Over the Web

I just read about a new company called Affectiva, which "grew out of collaborative research at the MIT Media Lab to help people better measure and communicate emotion."

This blog has previously discussed how human behaviour and sentiment is being analysed using data from the web:
(i) Web search volume can can improve forecasts of the current level of activity for a number of different economic time series, including automobile sales, home sales, retail sales, and travel behaviour (Google research paper on "predicting the present").
(ii) What people are searching for today can be predictive of what they will do in the near future (Yahoo! PNAS paper)
(iii) There have been various initiatives to make sense of sentiment data from Twitter
(iv) Facebook are analysing a rich seam of social networking and affect data
(v) Dan Hopkins and Gary King have developed an automated program to gather sentiment from online blogs

What makes Affectiva different to all of the above, is that (through their project Affdex), they have provided a way to collect web-data on physically expressed human emotions, not stated mood or revealed (search) preferences. Data on facial expressions and gestures — while people interact naturally with media, or other online experience — can be collected using Affdex. One could argue that this is closer to the objective truth than self-reported affect or observed behaviour.

Also, Affectiva's Q Sensor project measures galvanic skin response using a wearable, wireless biosensor. The sensor also measures temperature and activity.

NBER - Sadness, Suicidality and Grades

Sadness, Suicidality and Grade

K)

Jeffrey S. DeSimone NBER Working Paper No. 16239 July 2010 This study examines the past year relationship between GPA and experiencing a combination of two primary depression symptoms, feeling sad and losing interest in usual activities for at least two consecutive weeks, among high school students during 2001–2009. The GPA loss associated with sadness, as defined above, falls from slightly less than a plus/minus mark to around 0.1 point when commonly co-occurring behaviors are held constant. Nonetheless, this effect is significantly larger than those of having considered or planned suicide and equivalent to having attempted suicide, which seemingly signify more severe depression. Moreover, sadness lowers the probability of earning A grades, and raises that of receiving grades of C or below, by over 15%. Coefficient sizes are similar when comparison groups are restricted to students engaging in correlated behaviors and in matching and instrumental variable models, suggesting that sadness causally reduces academic performance.

Taller People Live Better Lives?

This is according to the Gallup-Healthways Well-Being Index daily poll of the United States population, as reported on the NYT Economix Blog. Taller people evaluate their lives more favourably, and they are more likely to report a range of positive emotions. They are more likely to experience stress and anger, and if they are women, to worry.

Emotions, Rationality and Investments - Bird and Fortune

Someone emailed this to me - makes me wish Yes Minister was still around

Political Economy of Emotions

The idea that powerful emotions have their own political economy is explored in the paper below by Glaeser on hatred

http://ideas.repec.org/a/tpr/qjecon/v120y2005i1p45-86.html

More On Emotional Mapping

Thanks to Ana Andjelic and Paul der Van for writing up about ifeelnyc.com. This website allows you to see where people go and what they do when they are in various moods, in London, New York and Toronto. It seems like this brings us to the bi-directional causality problem. That is, do people go to certain places because of their mood? Or do places affect mood? Or a bit of both?

The Effects of Weather on Daily Mood

An interesting study from this months issue of 'Emotion' examines the effects of six weather parameters (temperature, wind power, sunlight, precipitation, air pressure, and photoperiod) on mood (positive affect, negative affect, and tiredness).

Using a multi-level approach they find "Sunlight had a main effect on tiredness and mediated the effects of precipitation and air pressure on tiredness. These individual differences in weather sensitivity could not be explained by the Five Factor Model personality traits, gender, or age."

Decision-making, impulsivity and time perception

Wittman and Paulus point to the experience of time as a core determinant of the perceived costs involved in waiting for delayed beneficial outcomes in their recent TRENDS article on delay discounting. They discuss the cognitive-processing mechanisms that determine the sense of time and include an interesting discussion of the relationships between emotional distress, decision-making and time perception.

Wittman et al. (2008)

BEING EMOTIONAL DURING DECISION MAKING—GOOD OR BAD? AN EMPIRICAL INVESTIGATION

This paper examines the link between affective experience and decision-making performance. In a stock investment simulation, 101 stock investors rated their feelings on an Internet Web site while making investment decisions each day for 20 consecutive business days. Contrary to the popular belief that feelings are generally bad for decision making, we found that individuals who experienced more intense feelings achieved higher decision-making performance. Moreover, individuals who were better able to identify and distinguish among their current feelings achieved higher decision-making performance via their enhanced ability to control the possible biases induced by those feelings.


MYEONG-GU SEO & BARRETT