Archive | mood RSS feed for this section

Crowdsourcing Empathetic Responses and Cognitive Reappraisals

22 May

At the Collective Intelligence conference in April, Rob Morris presented a paper that he and Rosalind Picard wrote, titled   “Crowdsourcing Collective Emotional Intelligence”.

It sounds crazy, I know, but they figured out how to structure micro-tasks on Amazon Mechanical Turk such that they elicited empathetic responses and cognitive reappraisals from anonymous workers with no training in psychotherapy.  For example, the system starts with a stressor text that a distressed user might enter, such as, “I’m going to flunk out of school and I’ll never get a job, I know it!”

Generating empathetic responses was fairly straightforward. They post the stressor comment and some guidelines for generating an empathetic response:

(1) address the user directly, (e.g., “Michael, I’m sorry to hear …”), (2) let the user know that his/her emotion makes sense, given the situation, and (3) share how you might feel if you were in a similar situation.

Turkers generate candidate responses and other Turkers vote on whether the candidate responses are appropriately empathetic. In an experiment, these responses were rated as much more empathetic than responses generated in response to the instruction to simply make the stressed user feel better about his/her situation (5.71 vs. 4.14 on a 7-point scale.)

Even more interestingly, the crowd could follow a structured process to generate cognitive reappraisals. They first ask some turkers to classify the stressor statement as having some cognition distortion or not. A distortion means, “logical fallacies within negative statements (Beck, 1979).” The example statement about flunking out never getting is a distortion  because there’s no way the speaker could know that s/he’ll never get a job in the future. On average, workers made this binary classification correctly 89% of the time. Using several workers to classify a single statement could increase accuracy.

When the worker marks a statement as a cognitive distortion, they are asked to give a “thought-based reappraisal” explaining the nature of the distortion. No complex training is needed for the workers: they are simply given some sample responses for inspiration.

When the work does not indicate a distortion, the worker is asked to give a “situation-based reappraisal” that suggests a different way of thinking about the situation. Workers are introduced to the concept and given a few examples of good and bad appraisals (the latter are needed to dissuade workers from offering advice or making unrealistic assumptions about the original speaker’s situation, two common errors they observed.) Some workers were asked to come up with their own reappraisal suggestions, while others were asked to try specific strategies such as finding a silver lining or taking a long-term perspective.)

Responses were limited to four sentences. In the experiment, reappraisals solicited in the way described above  were rated as better at offering a positive way to think about the situation (5.45 vs. 4.41) than when workers were asked to simply make the stressed user feel better about his/her situation.

Overall, this suggests that the crowd can, with little training, be a useful source of informational feedback and emotional support.

Tracking and Sharing Moods With My Wife (Part I)

19 Sep

Inspired by others’ experiences reported in my last post, my wife and I want to try tracking and sharing our moods for a while. I’ve now spent spent several hours searching and evaluating the many different apps out there. Surprisingly, I haven’t found anything that will do it.

Here were the features I was looking for, and where various otherwise promising apps seemed to fall flat:

  • Very simple to record a mood, with optional text note, on iPhones. MoodScope, for example, has no iPhone app, and while the card metaphor for recording a score on each of several dimensions makes for a beautiful interface, it takes a long time to record a mood.
  • Ability to share with my wife, any only my wife, the updates I post. The simplest way, I think, would be to post them to Facebook, and then configure Facebook privacy settings to only share posts from that app with her. The only app I found that came close to offering this was MoodPanda, but in order to share with anyone on Facebook, I had to shared with everyone on MoodPanda. One app, from Track & Share, let’s you email a CSV of your data to anyone. Most apps had no export at all. I was surprised not to find “share with buddies” or at least “share with caregiver” or “share with lifecoach” as a common feature. If anyone works for any of the companies that have developed these apps, I’m curious whether this is just a low priority feature, or whether it was a deliberate design decision.
  • Alerts at random times to prompt input (like in Experience Sampling.) One app, GottaFeeling, sends four random reminders per day, but the number and time weren’t configurable, and it didn’t meet my other needs above. The Harvard University research project, Track Your Happiness, uses experience sampling (it sends you text messages or emails at random times) but doesn’t seem to have the sharing facility.

So, at least for now, here’s our plan:

  • We set up two new twitter accounts that are not publicly followable and that follow each other.
  • We agree on a very simple micro-format: each tweet begins with a number from 1-10, and then a space, and then any text or pics or links we want.
  • I’ll write a program that harvests the data and puts it into nice graphs for us occasionally.
  • I’m not sure what I’ll do about the alerts at random times. I couldn’t find an iPhone app that does that. If I had a Mac and wanted to learn iPhone programming, I suppose it would be a simple task to create one, but I don’t think I’m going there. Perhaps write a program that sends SMS messages at random times? Looks like there are cloud services that will send out SMS messages for you at a very low price (e.g., Twilio).

Wanna Know How I Feel?

19 Sep

There are a bunch of apps that track your self-reported mood. (See a compilation)

One of them, Jon Cousins’ MoodScope, encourages people to share their moods with a few buddies. Buddies can check the web site, or be notified each time you record a new mood score.

Cousins tells a great story about how he was inspired to create the tool, based on his own experience. He was tracking his mood for a while. When he started publishing it to five buddies, he immediately stopped having ups and downs, and that continued with do dips for more than a year. Watch the video, skipping to around minute 6 or 7 if you don’t want the full runup.

Alexandra Carmichael has a slightly different story about the social effects of sharing mood data. In her case, it didn’t magically eliminate mood swings, but she reports a few other findings. First, after about a month her moods began to align with her friend’s. Second, sharing moods with the friend strengthened the friendship; now they are best friends. And even though it hasn’t magically made her happy all the time, she thinks that the sharing and reflecting together about their moods makes her accountable for taking care of herself and “reminds me of who I am and how I want to live”.

Sharing something as personal as our moods clearly puts us in a vulnerable position. But perhaps that’s why it’s so powerful.