Is there software to practice reading expressions?
post by lsusr · 2024-04-23T21:53:00.679Z · LW · GW · 8 commentsThis is a question post.
Contents
Answers 9 Matt Goldenberg 2 joec None 8 comments
I took the Reading the Mind in the Eyes Test test today. I got 27/36. Jessica Livingston got 36/36.
Reading expressions is almost [LW · GW] mind reading. Practicing reading expressions should be easy with the right software. All you need is software that shows a random photo from a large database, asks the user to guess what it is, and then informs the user what the correct answer is. I felt myself getting noticeably better just from the 36 images on the test.
Short standardized tests exist to test this skill, but is there good software for training it? It needs to have lots of examples, so the user learns to recognize expressions instead of overfitting on specific pictures.
Paul Ekman has a product, but I don't know how good it is.
Answers
Paul Ekmans software is decent. When I used it (before it was a SaaS, just a cd) it just basicallyflashed an expression for a moment then went back to neutral pic. After some training it did help to identify micro expressions in people
I think with a decent training set, this could make a pretty nice Anki deck. The difficulty in this would be getting the data and accurate emotional expression labels.
A few ideas:
1. Pay highschool/college drama students to fake expressions. The quality of the data would be limited by their acting skill, but you could get honest labels.
2. Gather up some participants and expose them to a variety of things, taking pictures of them under different emotional states. This could run into the problem of people misreporting their actual emotional state. Learning with these might make the user more susceptible to deception.
3. Screenshot expressions from movies/videos where the emotional state of the subjects are clear from context.
8 comments
Comments sorted by top scores.
comment by ö · 2024-04-24T12:05:06.991Z · LW(p) · GW(p)
The test scores me as 'normal' with 29/36. I remember doing a similar (maybe the same) test and scoring decidedly below average about two years ago.
I understand the attraction of having this skill trainable in its own context like flashcards but consider it a false shortcut. I think it is more about directing attention.
Setting aside a few cycles of my attention to practice in every day life worked for me and I think it should be wildly superior to treating it as a problem of categorizing features.
1. You get so much more context to infer from and that hints at things you should be able to detect. After all, the true version of the skill is not 'detect <basic emotion x >' but 'emulate people roughly and extract information'. For that to actually happen you want to keep detecting new features and explore them. Not be x% better at separating desire vs. attention.
2. You also train actually using the skill in the background (that is becoming aware that a person feels x instead of just being able to answer if you should happen to ask yourself about what they might feel). This is also the hard part in my opinion.
It is frustrating, but every time I want to modify anything about my mind it comes down to a mindfulness exercise.
EDIT: 1. basically says this is a case of What Are You Tracking In Your Head? [LW · GW]
↑ comment by joec · 2024-04-24T19:35:35.014Z · LW(p) · GW(p)
How did you do this? Did you simply ask yourself "how does this person feel" in a social context? Did you get feedback through asking people how they felt afterward? If so, how do you deal with detecting states of mind that others are unlikely to openly admit (e.g. embarrassment, hostility, idolization)?
Replies from: ö↑ comment by ö · 2024-04-24T21:27:26.844Z · LW(p) · GW(p)
I kind of implicitly assumed we are not talking about missing the obvious stuff (like someone staring at you angrily in a 1 to 1 conversation). That would probably best be explicitly learned by flashcards.
Everything but basic emotions has a lot of hidden states and the tracking becomes much more of a thing. But that state is not all that hidden. You actually know a lot about the people in your life.
The hard part is coming up with enough hypotheses and not separating true from false. I call it to myself 'generating social conspiracy theories' to get rid of my inhibition to state a bad theory. Whatever you come up with usually will not be too bad. Evaluating the truth of 'my colleague is stressed' is usually easy. But it will make you aware that they are or aren't and how that influences their behavior. That is what you actually learn and what will make you aware of their stress in the future.
I never felt like there is a lack of 'obvious' things to become aware of. Either things are so interconnected that everything is kind of accessible with enough layers of such perceptions, or I am playing on too basic of a level of this game to get to interesting cases. I feel like I am learning some deep art, so I am probably a total beginner to something most are much more capable at just by using their intuition..
The disappointing part of course is that reading strangers minds is hard with huge error bars and reading huge parts of the mind of close people is basically expected.
I might be arguing something totally besides Lsusrs original point, but I do not think that facial expressions carry very far and this (cognitive empathy) does the thing he seems to be after.
comment by Jacob G-W (g-w1) · 2024-04-23T22:19:46.591Z · LW(p) · GW(p)
*Typo: Jessica Livingston not Livingstone
Replies from: lsusrcomment by quetzal_rainbow · 2024-06-16T13:07:23.255Z · LW(p) · GW(p)
I am curious whether you have found good training software and if it had any influence on your personal interactions. I got 36/36 on first try, but I am the most clueless person in any ambiguous social situation.
comment by abstractapplic · 2024-04-25T10:13:51.868Z · LW(p) · GW(p)
I (to my own surprise) got an "above average" score when I took this test a few years back, which I attribute mostly to the lack of emotional and circumstantial 'noise' in the images. I don't think being able to tell what is being emoted by a professional actor told to display exactly one (1) emotion, with no mediating factors, has much connection with being able to read actual people.
(. . . though a level-2 version with tags like "excited but hesitant" or "proud and angry" or "cheerful; unrelatedly, lowkey seasick" could actually be extremely useful, now I think on it.)