Brain Scan Can Predict Math Mistakes

itwbennett writes "Computer Science Ph.D. candidate Federico Cirett says that he can predict with 80 percent accuracy when someone is about to make a mistake on a math question. Using an EEG machine, Cirett can identify the patterns in a volunteer's thinking that are likely to result in an error 20 seconds or so before it's made. 'If we can detect when they are going to fail, maybe we can change the text or switch the question to give them another one at a different level of difficulty, but also to keep them engaged,' Cirett said. 'Brain wave data is the nearest thing we have to really know when the students are having problems.' He will present a paper on his findings at the User Modeling, Adaptation and Personalization conference in July."

Comments

How wonderful

[durrr]

A patronizing system that tells you that you've already failed before you've actually done so that gives you amateurish problems so it can see you succeed.

I hope it comes with a robot arm that tears the test paper out from under your pen, pats you on the head and give you a first grade replacement problem. Bonus for cheering with a nonenthusiastic voice whenever you pass a problem.

Re:How wonderful

[Garth Smith]

I majored in math and spend many hours tutoring math. Here is a key in tutoring, you need to give challenging but SOLVABLE problems! Otherwise you just frustrate and make math something to hate. If I got stuck on some math homework and couldn't figure it out, that sucked. I figured out pretty quick if I was stuck for 5 minutes, just wait and go ask for help.

What I found interesting about the article is that the mention of the word "math" is enough for some people to show signs of imminent failure. I have often come across this while tutoring and the best thing that I could do to help these people is to remove a fear of math from them. Show them that they CAN do some easier math, and then move on from there.

This is key in educating anyone in any topic. Challenging but SOLVABLE problems! Your attitude only makes society hate mathematics more, when they should be shown the wonder and excitement of it!

Re:How wonderful

[GSloop]

I believe you intended to be funny or sarcastic here, but many of the replies down-stream also seem to miss the point.

Provided you can believe the article...
There are *patterns* of thinking that indicate a student is about to make a mistake, that they otherwise may well be capable of solving correctly.

It's not that they can't handle that difficulty, or don't know the subject matter; it's that their brain is going into patterns that indicate it will simply be unable to reproduce the known material, and the student will fail on that problem, even if they have the requisite knowledge and skill to successfully answer the question.

It would seem a monumental failure to test someone and not actually measure the skill they have accurately.

Now, the solution? There are a myriad of them, and some are obviously better than others.

The prime solution, it seems in my mind, is to then give the subject a view of their brain and thinking that produced this likelihood of failure. You'd teach them how to recognize the onset of the thinking/brain patterns, and how to re-direct their thinking to help alleviate this bad construct.

Teaching someone how to do that would be incredible. It wouldn't involve "going easy" on them, and wouldn't give them results they couldn't achieve on their own. Once they were able to move out of the "bad" patterns, they could go right back to doing the test and you would get a much more accurate measurement of what the test-taker actually knew.

Further, almost certainly some people are much worse at getting stuck in these brain patterns - and their results from testing are probably much worse than the rest of the population and they are measured very inaccurately.

In spite of all the "humor" and snowflake BS thrown at the concept, I see this as something that could greatly improve the quality and skill of the people who utilized it. It could allow us to tap the potential of people who otherwise would be lost as "not very good" who really only fail the measurement system. [Or more accurately, the measurement system fails them.]

Why throw away many who *do* have the requisite knowledge - simply because we don't know how to help them perform better?
Why not help people perform better and learn where their brain limitations cost them - and better yet, teach them how to modify their thinking and work output to give them better results?

-Greg

Snowflakes

[girlintraining]

'Brain wave data is the nearest thing we have to really know when the students are having problems.

Most people have been raised with the notion that it's more important to appear competent than be competent. There's several college-themed cartoons out there about that express hatred for "The Question Guy"... and most people are acutely aware that asking questions on material is a great way to earn the irritation and ostracism of your peers, who feel they have better things to do than get an education and really just want to go through the motions and get out.

This is another technology that's trying to solve a social problem, and like every attempt in that regard, it will fail, be impractical, and people will try to defeat it -- because they don't see the point and they don't want to appear incompetent. In 20 years, we'll be getting coached on how to have the right brain wave patterns for getting through the airport unmolested, how to cheat on your final and not get detected by the brain wave readers, etc.

The problem is in our social values and attitudes. It's systemic and institutional. No technology can fix that, however advanced.

Re:Snowflakes

[jellomizer]

Well there are a bunch of different question guys.
1. Question to show off. Ask an intelligent question that helps lead the professor into the next chapter. Sometimes it isn't to show off, but because how the material is presented, it get the person to stir about the points brought up in class and starts thinking too much so they get confused and needs to point out the details in the next part.

2. The Stupid Question. These are questions that you ask because you weren't paying attention 5 minutes ago. Or because you failed to learn the course before.

3. The Question that takes too long. If the Teacher/Professor cannot explain it to you after 2 questions you should take it off line, and not disrupt the class any further.

4. The Question everyone has, but is afraid to ask. When one poor brave sole asks the question everyone else was afraid to ask. This often happens when the professor is trying to go to fast and/or uses proofs by intimidation to get to the next spot. "So we find this value, and as anyone can see it brings us to this conclusion...."

5. The honest question. Others in the class may get it, but you are missing a small piece and you just can't quite visualize it. A quick answer and you are on your way.

For the most part it is difficult to judge what type of question you are asking until after you asked it.

Suggestion

[Dorsch]

There should be a system like that for posting on the internet... "Error Code 427 - there is a 80% probability you're posting bullshit. Your post was discarded."

Old Technology

[squidflakes]

That's nothing, I had an ex-girlfriend who could predict with 100% accuracy when I was going to say or do something stupid, usually in response to her being upset.

Re:Maybe there's something wrong with me...

[Garth Smith]

Say we get this system to 100% accuracy. We know ahead of time that little Jimmy will not be able to solve this math problem. Little Jimmy has exhausted his options and has become stuck. Then what is the point of wasting time having him stare at it? I would take this as an alert that little Jimmy needs help, to intervene, and get little Jimmy learning again.

Re:Maybe there's something wrong with me...

[icebike]

Say we get this system to 100% accuracy. We know ahead of time that little Jimmy will not be able to solve this math problem. Little Jimmy has exhausted his options and has become stuck. Then what is the point of wasting time having him stare at it? I would take this as an alert that little Jimmy needs help, to intervene, and get little Jimmy learning again.

Isn't that the old "allow no failure" school of thought repackaged?

On the other hand, if Little Jimmy stares at it a little longer, or perhaps is allowed to actually get it wrong (horrors), and then reason out why it was wrong, his learning will probably be better and longer lasting. Or if we give him a few more seconds, perhaps he will have an epiphany as his prior learning bubbles to the surface of his oat-meal brain. But most likely, jumping in 20 seconds before he offers the wrong answer isn't telling him anything he already doesn't know.

Chances are, it has nothing what so ever to do with math, but merely detects the changes in the brain that signal resignation, or the formation of Jimmy's realization that he does not know the answer or the path to the answer. His brain isn't working on math any more, its resigning him to the fact he can't solve this problem. It takes people a while to come to grips with this fact. Saving him 20 seconds AFTER he has already puzzled out this fact, but BEFORE he brings himself to write something wrong, amounts to no saving at all.

Let him spend that 20 seconds of mental anguish before writing down his guess. Chances are its a valuable part of the learning process. Why jump into micromanagement mode of a learning process we still don't understand?

Re:Maybe there's something wrong with me...

[CaptainLugnuts]

With most Americans' working knowledge of math it would be easier to make a machine that just says 'Wrong Answer."