×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

How Facial Analysis Software Could Help Struggling Students

samzenpus posted about 10 months ago | from the turn-that-frown-upside-down dept.

Education 90

moon_unit2 writes "Tech Review has a story on research showing that facial recognition software can accurately spot signs that programming students are struggling. NC State researchers tracked students learning java and used an open source facial-expression recognition engine to identify emotions such as frustration or confusion. The technique could be especially useful for Massive Open Online Courses — where many thousands of students are working remotely — but it could also help teachers identify students who need help in an ordinary classroom, experts say. That is, as long as those students don't object to being watched constantly by a camera."

cancel ×
This is a preview of your comment

No Comment Title Entered

Anonymous Coward 1 minute ago

No Comment Entered

90 comments

why is this familiar to me? (0)

Anonymous Coward | about 10 months ago | (#44156781)

I know xkcd is usually oblig, but for the constant camera in your face, lets go with some oblig. Penny Arcade [penny-arcade.com]

Re:why is this familiar to me? (1)

Luckyo (1726890) | about 9 months ago | (#44158761)

I think this one is better:
http://www.penny-arcade.com/comic/2013/06/14 [penny-arcade.com]

Re:why is this familiar to me? (0)

Anonymous Coward | about 9 months ago | (#44159061)

I think this one is better: http://www.penny-arcade.com/comic/2013/06/14 [penny-arcade.com]

Actually, I think people are focusing too much on the camera aspect of Google Glass and are ignoring the potential benefits of the display.

LOL (-1)

Anonymous Coward | about 10 months ago | (#44156793)

Can it detect when I piss in timothy's ass?

Good and Bad (0)

Anonymous Coward | about 10 months ago | (#44156811)

Just like anything, it depends on how this technology is used. A big part of being successful is learning to deal with the times when you're flat out lost and have no clue what you're doing, but are still expected to produce results. If someone else deals with these situations for you, then there are things you will never learn.

Re:Good and Bad (1)

i kan reed (749298) | about 10 months ago | (#44156879)

But, like most problems, if technology can solve it for you, why wouldn't you use it?

Re:Good and Bad (0)

Anonymous Coward | about 10 months ago | (#44156927)

I've operated for years on the assumption that if technology can remember things for me then shouldn't it, particularly since I'm so poor at it. Then I found out last week that not exercising that part of the brain can lead to early onset alsheimers. Maybe we don't get the consequences of all this yet.

Re:Good and Bad (0)

Anonymous Coward | about 10 months ago | (#44156937)

LEOs could and would abuse it.

Re:Good and Bad (1)

jeffmeden (135043) | about 9 months ago | (#44158063)

LEOs could and would abuse it.

"The murder suspect is currently sitting in their Java 152 lab, trying to figure out the difference between a Jbutton and a Jtogglebutton... Their mood is 'mad enough to kill someone' so we are pretty sure they did it. Lets go pick them up!"

Re:Good and Bad (1)

CanHasDIY (1672858) | about 10 months ago | (#44156973)

But, like most problems, if technology can solve it for you, why wouldn't you use it?

Well, that depends.

If the problem is that I need to learn concept X, but the technology provides the solution for me, then the problem isn't really solved, because I still don't know concept X.

Re:Good and Bad (0)

Anonymous Coward | about 9 months ago | (#44157353)

I would say the challenge, work is pretty boring if there is never anything challenging, technology makes a lot of things easier, and often its a good thing, but you have to evolve with the technology and then take up something extra as your responsibility, not just let the technology replace you bit by bit, for your own good.

Re: Good and Bad (0)

Anonymous Coward | about 9 months ago | (#44158475)

But the PEOPLE part of teaching is to lead students around roadblocks. I could totally see this integrated into your math homework app. It could automatically adjust the homework problems when you get blocked to lead you through to the answers.

This leads to two evolutions in teaching. First the ability to keep students moving... Even if they have to step backwards. Automatically adjusting the level of work builds confidence instead of just leaving a student in a corner and getting upset. Second, it makes homework time about MASTERY and not about filling out a specific page of problems, as the system could adjust them based on time spent and level achieved.

What they need is FINANCIAL analysis (0)

Anonymous Coward | about 10 months ago | (#44156831)

Seriously, if people would do a ROI analysis and figure out how long it will take them to pay off the loans they are taking out, fewer would spend $100,000.00 get PhDs in Medieval English and then whine about not being able to find a job that will pay for their loans.

Re:What they need is FINANCIAL analysis (1)

Anonymous Coward | about 10 months ago | (#44156987)

Listen to this guy. He's the lead Fry Cook at his Burger King.

Re:What they need is FINANCIAL analysis (0)

Anonymous Coward | about 9 months ago | (#44157255)

Actually, I am a systems engineer and can't log in because I am at work.

Re:What they need is FINANCIAL analysis (2)

h4rr4r (612664) | about 10 months ago | (#44157033)

That is a compelling argument for subsidized post secondary education.

Re:What they need is FINANCIAL analysis (0)

Anonymous Coward | about 9 months ago | (#44157357)

The subsidizing of post-secondary education is the cause of that education becoming so expensive.

Re:What they need is FINANCIAL analysis (2)

h4rr4r (612664) | about 9 months ago | (#44157417)

I meant completely.

Actually it is the availability of credit that does that, not the subsidy. As a good example look at the cost of in state tuition, where the tax payer foots part of the bill vs out of state at the public university.

Re:What they need is FINANCIAL analysis (0)

Anonymous Coward | about 9 months ago | (#44158251)

No, it is a compelling argument for forcing people to accept the financial reality of their interest and realize that they better off getting that interest as a minor to some other degree that will actually pay the bills.
 
Just because one wants to learn about something, it does not follow that one has a right to be provided education in that thing at anyone else's expense or for free. If one isn't smart enough to figure out that one is about to spend $120,000 on a degree that will pay $20,000 per year, one needs to be told that, not given a free education in it.

Re:What they need is FINANCIAL analysis (2)

Grygus (1143095) | about 9 months ago | (#44160235)

If everything comes down to a cost benefit analysis, we lose everything that isn't profitable. Have you ever worked for a company that valued its "profit centers" at the expense of the rest of the workforce? It is a narrow and short-sighted viewpoint, divorced from reality. Not everything needs to be approached as a business.

Re:What they need is FINANCIAL analysis (0)

Anonymous Coward | about 9 months ago | (#44157177)

Few students actually pay for their grad school education in medieval English or the humanities in general. If a school wants you (if you have decent undergrad grades, a high GRE score, and obvious potential), *they* pay *you* to attend via fellowships, research assistantships, and teaching assistantships. The people paying for their PhD or MA out of pocket (or via loans) are the ones whom the schools didn't think highly enough of to give them fellowships, or are enrolled in med school, law school, ed school, or some other postgrad track with an oversupply of applicants. Almost no one taking medieval English is not teaching some undergrad classes—which works out for the universities too, because that means they don't have to hire expensive professors. The only people shortchanged are the undergrads, who don't get real professors but always TA's.

Re:What they need is FINANCIAL analysis (3, Informative)

celticryan (887773) | about 9 months ago | (#44157965)

While there certainly are some humanities students who get support - most of them do not receive full support from their institution. Typically, half time TA with no tuition coverage. This can also be the case for engineering PhDs at some institutions. Almost all science PhD students are typically guaranteed 2 years TA plus tuition even at the very smallest schools. In addition, non-STEM related PhDs take longer (about 1.5 years longer at the median). This leads to more student loan debt for non-STEM PhDs compared to STEM PhDs. Please see this study for a very nice comparison: The Price of a Science PhD [air.org]

In addition, you make what I believe to be two assumptions by implication about Universities:
1. That professors are hired to teach.
2. That TAs will do a worse job teaching than professors.

Professors are NOT hired to teach - the exception is small private colleges without graduate programs. Professors are hired to bring research money into the University. The University takes in the region of 40-60% off the top of grants "for institutional research support." While this is not always the case (for some grants, the granting institution require the university to commit matching funds) it is more than the norm. Secondly, while professors are typically more knowledgeable in the subject and typically have more experience teaching (by virtue of spending the time as a TA during graduate school), that does not mean they are the better teachers. The best teachers I ever had were evenly split between professors and TAs. While not scientific, my colleagues experiences were similar.

Re:What they need is FINANCIAL analysis (0)

Anonymous Coward | about 9 months ago | (#44159559)

Your assumptions might work for science degrees but do not hold for medieval English programs, which was what GP was whinging about. Medieval English (and other similar humanities) is not driven in the least by research grants. I've dated psych and not-modern English grad students; the former lived in a world where professors were ranked and valued in terms of how much grant money they pulled in, and everyone collaborated on papers and published often and as teams; the latter's world was one of individual work, no collaboration, and little in the way of research grants. Totally different worlds. I'll agree, though, that professors aren't necessarily valued according to their teaching ability: it's often more their publication speed that determines their worth to the University.

Re:What they need is FINANCIAL analysis (0)

Anonymous Coward | about 9 months ago | (#44157839)

It wasn't that long ago where one could get a degree in -anything-, and have a good career. Don't blame the students who at least are trying to better themselves.

Remember: China pays for student educations. Germany does. Russia does. Chile does. Japan does. In fact, the only first world nation that does not is the US.

Re:What they need is FINANCIAL analysis (0)

Anonymous Coward | about 9 months ago | (#44162465)

It wasn't that long ago where one could get a degree in -anything-, and have a good career.

That was back when colleges were for intelligent people. Now most of them let in all sorts of trash.

That 'Everyone needs to go to college' nonsense is just that: nonsense. Most people shouldn't go to college, and many employers need to stop being imbeciles by requiring degrees.

I'd pay money... (2)

Chris Mattern (191822) | about 10 months ago | (#44156861)

...to get everybody in the class to show up wearing one of these. [charlessizemore.com]

Re:I'd pay money... (1)

gl4ss (559668) | about 10 months ago | (#44156969)

...to get everybody in the class to show up wearing one of these. [charlessizemore.com]

"excellent mr robinson, everyone in your class was extremely pleased with your teaching according to the auto-stats!"

Marketing Research on Slashdot? (0)

Anonymous Coward | about 10 months ago | (#44156887)

is it me or are these questions more blatantly marketing test-questions?

What about asking for help? (0)

Anonymous Coward | about 10 months ago | (#44156917)

Seriously? What ever happend to the idea of a student being responsible for asking for help when they need it?

Re:What about asking for help? (1)

hawguy (1600213) | about 10 months ago | (#44157067)

Seriously? What ever happend to the idea of a student being responsible for asking for help when they need it?

Yeah, I don't understand why this is needed - if the student needs help, he can ask for help. If he chooses to go it alone without seeking help even when he is frustrated and doesn't know what he's doing, that doesn't bode well for his success in the "real world", so he probably deserves to fail out of the class.

I certainly don't want my computer's camera watching me in case it detects that I need help. If I want help I can ask for it and I don't want the professor interrupting me with "help" when the system detects the stress in my face when the cause of the stress is because my dog died... or I'm tired... or I really need to go to the bathroom.

Re:What about asking for help? (0)

Anonymous Coward | about 9 months ago | (#44157205)

Because some teachers want to have additional tools to proactively help struggling students that maybe tok shy or embarrased to ask for help. How terrible of an idea that is. Clearly the point of being a teacher is not helping their students, right?

Re:What about asking for help? (1)

Ignacio (1465) | about 9 months ago | (#44157283)

Learning when and how to ask for help is part of getting along in society.

Re:What about asking for help? (4, Insightful)

hawguy (1600213) | about 9 months ago | (#44157399)

Because some teachers want to have additional tools to proactively help struggling students that maybe tok shy or embarrased to ask for help. How terrible of an idea that is. Clearly the point of being a teacher is not helping their students, right?

When you graduate and get a job, your boss isn't going to be using those same tools to check in on you to see when you're struggling and need help. Asking for help when you need it is part of the educational process. Giving students a crutch because they are "too shy" to ask for help doesn't really help them in the long run. If they are too shy to ask their instructor for help (the person they are paying to teach them), then how will they ever be able to say to their boss "Hey, I don't think I know how to get starting on this project, can you point me in the right direction".

Besides, teachers already have tools to see when you're struggling and don't know the material - those tools are tests and homework.

Re:What about asking for help? (0)

Anonymous Coward | about 9 months ago | (#44158187)

So just ignoring them and their problems because they are shy is going to help them how exactly? Some people when they are younger need more help. It is not a crutch. It is being a decent teacher and human being.

Re:What about asking for help? (1)

Calydor (739835) | about 9 months ago | (#44162067)

Maybe by actively demonstrating that there is nothing to be shy about, and that needing help does not get you ridiculed and/or ignored?

Re:What about asking for help? (1)

Vitriol+Angst (458300) | about 9 months ago | (#44162337)

This actually does help students get ready for the real world;
Your employer is going to spy on you. Get used to it.

If you're frustrated in your efforts to cut the "liberty manacles" off your foot, facial recognition will pick that up and an assistant will come by to help you put a new, more form-fitting manacle on your leg.

Students and workers who are too shy to ask for a higher quality leg manacle don't need to overcome shyness. In fact, this shyness is seen as a quality in many workers.

Re:What about asking for help? (0)

Anonymous Coward | about 9 months ago | (#44162745)

If he chooses to go it alone without seeking help even when he is frustrated and doesn't know what he's doing, that doesn't bode well for his success in the "real world", so he probably deserves to fail out of the class.

And maybe he will overcome the frustration and solve the problem by himself. It will take him more time, but he will learn more and his frustration tolerance will go up at the same time. None of these is a bad thing.

He will be able to do more then those who do not even try to solve problems on their own.

Re:What about asking for help? (1)

seebs (15766) | about 9 months ago | (#44160845)

Couple things:
1. They may not know. I know it sounds weird, but students don't always know when they don't know what's going on.
2. I have known a fair number of people whose parents or teachers taught them not to "make waves" -- say, asking for help. They just freeze up and quietly fail. Yeah, they can get better from that, but getting better requires, in part, getting at least some help they need but can't ask for.

No (1)

The Cat (19816) | about 10 months ago | (#44156951)

A teacher could help struggling students.

I remember when technology was fun. It's getting really sour and ominous, and I am starting to fear for future generations.

Re:No (1)

Anonymous Coward | about 9 months ago | (#44157249)

Yeah, I could kinda understand it being used in a mooc, but in a normal class? Isn't it your teachers job to spot people that need extra help? And if they can't do that, aren't they really lacking a very valuable skill and may have to rethink their career path? A big part of teaching seems to be knowing when and who needs a bit more help.

Re:No (0)

Anonymous Coward | about 9 months ago | (#44157305)

I am starting to fear for future generations.

Just now? You been hiding in that box since you got your low UID? "{^o^}"

Schools have been plaqued students with false positives since well before any of them had a computer, now they can generate them at a faster rate with the assistance of what may well become the alledged "mind reading" tool replacement for the polygraph. Great, like the polygraph they will be used for lie creation and as a torture device claiming to be fact till disproven and banned from courts, oh wait, though formerly declared not usable in courts they still use them and often required in many positions. Welcome to the new technological variant on the game of persecutional gossip.

They're doing it wrong. (2)

Zero__Kelvin (151819) | about 10 months ago | (#44156965)

"NC State researchers tracked students learning java and used an open source facial-expression recognition engine to identify emotions such as frustration or confusion. "

Unless it identified almost all of them it wasn't working ;-0

I would be more interested in the ones who don't show that emotion, since they are the ones so lost and confused that they have abandoned all hope and given up. If you are trying to learn Java, and you aren't frustrated and confused, you're doing it wrong.

Re:They're doing it wrong. (-1)

Anonymous Coward | about 9 months ago | (#44157919)

I disagree. What I found was that for programming classes in college you either already knew how to program or you struggled greatly. The classes almost never taught anyone to code. So I would identify the relaxed students, confirm they have a decent grade and aren't just the abandon all hope type you mention, and then cull the rest of the class. Sure, it might be harsh, but most of the people in comp sci or similar programs don't belong there and aren't going to succeed. That doesn't mean the people aren't smart enough, it just means they aren't going to do well in comp sci. Get them focused on something they will be successful in.

Re:They're doing it wrong. (0)

Anonymous Coward | about 9 months ago | (#44158863)

Java is a pretty damn simple language...

Re:They're doing it wrong. (1)

SunTzuWarmaster (930093) | about 9 months ago | (#44159157)

This is not necessarily true. Emotional states can be picked up via computer, and are correlated significantly with learning outcomes. See "Affect and learning: An exploratory look into the role of affect in learning with AutoTutor" (2004) for some more information on the subject.

So can an effective instructor (0)

Anonymous Coward | about 10 months ago | (#44156997)

If an instructor can't detect who is struggling, they are not a very good teacher and should find another job where ignoring people they are there to help is ok.

If a student can't open their mouth and say "I am struggling" and have to depend on an external agent to recognize this and help them, they deserve to continue struggling.

The answer to the problems posed by MOOCs is to teach human beings (instructors and students) to be self-responsible and willing to communicate, not to dream up some half-assed technological solution that can't perform the task better than a human.

Re:So can an effective instructor (1)

dgatwood (11270) | about 9 months ago | (#44157299)

If an instructor can't detect who is struggling, they are not a very good teacher and should find another job where ignoring people they are there to help is ok.

Government employee, it is, then.

Re:So can an effective instructor (0)

Anonymous Coward | about 9 months ago | (#44159193)

Instructors are not always available. The ability Intelligent Tutoring Systems and other automated instructional systems to detect when a learner is struggling is critical to its ability to effectively instruct.

Ah yes, Facial Analyze. (1)

santax (1541065) | about 10 months ago | (#44157017)

I did a lot of that in my time. Although I can see why one would automate some parts (like getting a sample to analyze the facial from), but I really don't see any fun in letting the software do everything.

Either this or... (0)

Anonymous Coward | about 10 months ago | (#44157031)

...the teacher could just be encouraging of students asking questions and then helping them out. And when they get home, parents could take an interest in their lives.

"Facial recognition software to detect struggling students.." gg

Ego, Ego and Ego. (1)

jellomizer (103300) | about 10 months ago | (#44157069)

You have Teacher and Professor ego to deal with. Will the students care, probably less so than the teachers, whose goal is to make them look like a better person than the rest of society. If you were to show that kids are struggling in their class and it isn't due to their own laziness, will make them look like a less of the perfect person. Off to complain to the union about this. Screw if kids are missing out in a good education it is always about the teachers, If they are teachers they must be trying work for the students best interests.

"Struggling students" huh? (4, Funny)

Taibhsear (1286214) | about 10 months ago | (#44157085)

Nice try NSA...

Re:"Struggling students" huh? (1)

s.petry (762400) | about 9 months ago | (#44158493)

^THIS^! Any excuse they can find to make it a "normal" will be given, no matter how many people tell them that it's dangerous. I think people are finally starting to catch on to the game, but they are slow to waken. The more people nudging them the sooner they awake.

Because it isn't already obvious. (0)

Anonymous Coward | about 10 months ago | (#44157087)

It's dead easy to spot who is struggling. A good first hint is, "fails exam, still doesn't show up to class." Another is, "shows up to class, spends it all watching YouTube videos." And, my favourite, "Asks bloody stupid questions that make it clear this student passed the pre-reqs by pity alone."

Identifying the students is easy. Successful interventions is much harder, and to some extent, futile. Sure, you can recommend additional reading, pair up high-performers with low-performers for peer teaching, or re-teach the same concept in multiple ways (boring & disengaging the high-performing students), but some fraction of students will do poorly anyway. And when a otherwise high-performing students struggles, they either directly seeking out assistance from the instructor (one-on-one teaching, recommendations additional resources, etc), or independently self-teach around the problem concept. You don't need to identify them, because they take responsibility for their own learning and either ask for help or fix the problem.

With a small group (100 for sure, certainly MOOCs), students will perform on a beautiful gaussian curve, with some stellar, "Why are you even taking this class?!" students and some, "So, you know you're going to fail and you're not doing anything to change that? Great." students. The eventual grade distribution is as predictable as the rash of grandmother-funerals, sick notes, and other absences that pop up during exam-season.

So, as a student, I would find this tech presumptuous and invasive, and as an instructor I'd find it utterly useless.

Huh? Now? Really? (1)

Anonymous Coward | about 10 months ago | (#44157091)

That is, as long as those students don't object to being watched constantly by a camera.

I don't meant to sound like a card-carrying member of the Fringe Lunatic Association, but after the multiple recent revelations that the LEO's ride around photographing cars and license plates [aclu.org], USPS photographs all mail [thesmokinggun.com], the NSA collects metadata on all phone calls [newyorker.com], the FBI and NSA together mine data from social networks [guardian.co.uk]—in short, that the US government in fact does all those things that the fringe lunatics warned about for years—it's hard to trust a university, whether state-run or private, with a camera to watch me at my computer in much the same way that it's impossible to trust Microsoft to watch me with an always-on X-Box One camera/mic setup [rollingstone.com].* I feel that recent events have given students very good reason to question whether the benefits of automatic frustration-recognition software are worth the risk that some sort of data might make its way from the camera to an FBI/NSA/Fusion database, despite the sturdiest ringfences and firewalls of promises, hope, and trust. Really, if the MOOC designers are really concerned about frustration, why not just include an "I'm frustrated! Give me a hint!" button on the user interface? Why monitor faces through a camera, and why propose the idea at the same time that MS's creepy XBox camera idea went down in flames?

Wonder if they eat their own dog food? (1)

140Mandak262Jamuna (970587) | about 10 months ago | (#44157103)

Were they testing the "facial expression recognizing software" by training the camera on themselves as they were developing the software?

One of my friends did his masters thesis project in code quality metrics. As part of it he wrote some code that will find the average LOC per function, code/comment ratio etc etc and spit out a letter grade. His thesis guru was a fiend. He fed the source code of this analysis code into itself. Poor guy graded himself a C-minus or something.

If you're confused... (0)

Anonymous Coward | about 10 months ago | (#44157109)

I always thought that if you were a student and confused (aside from being the normal state of affairs for a student) it would be the student's responsibility to speak up and ask for help. Perhaps it would be more helpful for Profs and TAs if they got a report when more than x% of the class is confused. And I'm sure administrators would like to see those numbers too come tenure time!

Re:If you're confused... (1)

Lunix Nutcase (1092239) | about 9 months ago | (#44157247)

Why? Any good teacher will always seek to proactively help a struggling student. The education system must be pretty shit these days if attitudes like yours is the norm.

You Know What Else Works? Timers. (5, Insightful)

CanHasDIY (1672858) | about 9 months ago | (#44157139)

Assignment 12-A is designed to require an average student approximately 20 minutes to solve.

Student #001A solves the problem in 3.5 minutes - Too easy for his skill level

Student #312Q solves the problem in 42.3 minutes - he is struggling and needs further assistance

Problem solved, and you didn't have to spend a dime placing spy-cams at every workstation. You're welcome.

Re:You Know What Else Works? Timers. (2)

dgatwood (11270) | about 9 months ago | (#44157487)

No, that's a worthless metric. People take different amounts of time for wildly varying reasons. When I was in school, it often took me a ridiculous amount of time to actually solve problems, not because I was struggling, but because the problems were so freaking boring that I would spend ten seconds working on a problem, then five minutes daydreaming, then ten more seconds working on it, then five more minutes daydreaming, etc.

And the more bored I was, the more distracted I was. The lowest grade I ever made on a test was in American history, when I was placed over next to the door to the next classroom. So I was hearing discussions of more interesting subjects than what I was working on, and a few minutes before the end of the class, I realized I was nowhere near finished. I started panicking and got finished, minus the bits I didn't know (and there were certainly some of those), but to this day, I still have problems focusing when there are pretty much any other noises to distract me.

Unfortunately, this means that your overly simplistic time-based metric would have predicted that I needed extra tutoring, extra practice work, and needed to be placed in a remedial class, whereas in point of fact, the opposite was true. I was in the smart class, and I was still bored out of my mind. So if your goal is to utterly torture many of your best and brightest, do exactly what you've proposed. If your goal is to identify struggling students, you need a much better metric than time spent.

Re:You Know What Else Works? Timers. (0)

Anonymous Coward | about 9 months ago | (#44157955)

That depends on whether or not you get to leave after the test. If your reward for finishing early is getting to leave, you will more than likely focus for the 3.5 minutes.

Re:You Know What Else Works? Timers. (1)

dgatwood (11270) | about 9 months ago | (#44158023)

Name one K-12 school that allows students to leave before the closing bell. :-)

Re:You Know What Else Works? Timers. (1)

CanHasDIY (1672858) | about 9 months ago | (#44159507)

No, that's a worthless metric. People take different amounts of time for wildly varying reasons. When I was in school, it often took me a ridiculous amount of time to actually solve problems, not because I was struggling, but because the problems were so freaking boring that I would spend ten seconds working on a problem, then five minutes daydreaming, then ten more seconds working on it, then five more minutes daydreaming, etc.

Then you would fall into the "further assistance" category.

Unfortunately, this means that your overly simplistic time-based metric would have predicted that I needed extra tutoring, extra practice work, and needed to be placed in a remedial class

Not necessarily; presuming ideal circumstances, it would actually mean that the teacher would need to take you aside for a few minutes to determine what further assistance you needed. If, in fact, the problem was that the class was too slow paced for you (and the teacher were competent enough to notice this; again, we're assuming an ideal system), then they would take the appropriate action.

Re:You Know What Else Works? Timers. (1)

SunTzuWarmaster (930093) | about 9 months ago | (#44159247)

If you know the student has been struggling for the last 30 minutes, do you continue on this instructional vector, or adjust course? If you adjust course, how do you do so? If you are going to adjust course, what to you base it on? That the student is taking too long? That their facial responses indicate confusion? Frustration? Anger?

There is a field of educations and computer science research behind these decisions, which you have conveniently ignored.

Re:You Know What Else Works? Timers. (1)

SunTzuWarmaster (930093) | about 9 months ago | (#44159289)

See http://iaied.org/about/ [iaied.org], http://www.educationaldatamining.org/ [educationa...mining.org], http://its2012.teicrete.gr/ [teicrete.gr], and others for more information.

Re:You Know What Else Works? Timers. (1)

CanHasDIY (1672858) | about 9 months ago | (#44159623)

See http://iaied.org/about/ [iaied.org], http://www.educationaldatamining.org/ [educationa...mining.org], http://its2012.teicrete.gr/ [teicrete.gr], and others for more information.

...

^ Serves to reinforce my assumption that you make your fortune selling overpriced computerized "tutoring" crap...

What does all that fancy tech do, that a properly trained human can't?

Re:You Know What Else Works? Timers. (1)

SunTzuWarmaster (930093) | about 9 months ago | (#44160295)

Serves to reinforce my assumption that you make your fortune selling overpriced computerized "tutoring" crap...

First: I don't recall that you made that point.
Disclaimer: I work with intelligent tutoring systems daily.
Full disclaimer: I work for a non-profit.

What does all that fancy tech do, that a properly trained human can't?

The big thing is: be replicated.

Human tutoring on a one-to-one basis is remarkably effective. In fact, it is approximately 1-2 letter grades better than classroom instruction (depending on the source*). There are obvious limitations on these educational gains (28 person classroom needs 28 teachers!). A good portion, if not the majority, of people are trying to copy what a human tutor does, in order to make this level of education better, faster, cheaper, sleepless, or more available.

I would ask you to consider your own question for a number of other technologies:

What does all that fancy tech do, that a properly trained human can't?

What does this line assembly manufacturing robot do that a human can't?
What does this ATM do that a human can't?
What does this automatic check recognition system do that a human can't?

There is a list: work through the night, be easily replicated, serve in areas where the human can't/won't go, access content from the internet as soon as it becomes available, etc.

*See VanLehn 2011, Bloom 1984

Re:You Know What Else Works? Timers. (2)

CanHasDIY (1672858) | about 9 months ago | (#44159617)

Seems an intentional over complication of what should be a trivial matter to me; speaking of which... what do you do for a living? Sell fancy computerized "education enhancement" equipment?

FWIW, if you need computers and software to tell you what emotion another person is expressing, you fail as a human; reading body language is a basic skill we all (should, anyway) learn as infants.

Re:You Know What Else Works? Timers. (1)

Vitriol+Angst (458300) | about 9 months ago | (#44162325)

No, no, no!

They have to have the cameras using facial recognition to HELP people who are confused. Even if using a timer is very straightforward - this is SO IMPORTANT that they've got to spend every effort to get the last confused person.

Kind of like how the NSA spends billions of dollars to track everything, so we can get the last person who doesn't like America.

And the XBox One doesn't want you to turn off the Kinect camera because otherwise Al Qaeda might get training by playing Black Ops 2.

Just helping to inform people so we can keep America safe and less confused. You're welcome.

>> I also don't work for the NSA as a subcontractor. Trust me.

what a load of technoutopian horse shit (0)

Anonymous Coward | about 9 months ago | (#44157233)

They would be better off teaching the students "What the Face Reveals" and teaching them how to be better human beings than teaching a machine to find better ways to remove humanity from human interaction

Detecting problems with learning Java? Trivial! (1)

gweihir (88907) | about 9 months ago | (#44157311)

Java is a horribly convoluted mess and completely unsuitable for learning programming of any kind. Hence every student struggles and that makes detecting it quite trivial.

And this is needed why? (1)

roc97007 (608802) | about 9 months ago | (#44157471)

Rather than dealing with the privacy issues and with the inevitable plethora of false positives, wouldn't it make more sense to have a button called "Raise Hand" or "Express Confusion" or "I'm lost"? In fact, very much like the buttons that already exist on distance learning interfaces?

Is this supposed to handle the case where users are confused but can't make themselves ask for help? Or is this setting up a framework to later require that all distance learning students have a camera trained on them? I was going to preface that with "tinfoil hat time" but constant surveillance seems to be less and less the stuff of conspiracy theories and more and more the stuff of daily life.

Re:And this is needed why? (0)

Anonymous Coward | about 9 months ago | (#44157991)

This. I'd much rather control my input to the system with a button or slider than via my face+camera. Sometimes class is not the only thing in my life with an emotional impact.

Most of the time I addend classes in person, I ended up doing some unrelated stuff during the easy parts. It would be funny to appear confused for all the easy parts of class because I was debugging my game project (Gee, that was in person, I guess I might have confused my professors. At least they knew I had the laptop up and was likely distracted)

Same goes for the new xBox face analysis tech. Just because you can make a game that plays different when you are sad or angry does not mean you should. Given the amount of neural feedback involved in faking facial expressions (at least for people who don't do it a lot), this is also a bit of mind control (though just emotionally so)

And for completeness: what about the people for whom this does not work at all? (Deformations, lack of compute power/bandwidth or camera etc, like the dark, hate the whole concept, have other people in the background etc)

Re:And this is needed why? (1)

roc97007 (608802) | about 9 months ago | (#44158551)

> Sometimes class is not the only thing in my life with an emotional impact.

Man, no kidding. Two years ago I got a text from my daughter "man with gun school in lockdown". I wonder what facial recognition would have made of that.

(It turned out ok; the person in question was fleeing a robbery and there were reports he had crossed school property.)

Tweak the algo (0)

Anonymous Coward | about 9 months ago | (#44157571)

1 spot the horny female students
2 ???
3 profit

open source!? (1)

majbthrd (66951) | about 9 months ago | (#44157773)

The Slashdot post says "open source facial-expression recognition engine", but the article links to a commercial web site that makes no indication that their product is open-source.

Shot in the dark (2)

Okian Warrior (537106) | about 9 months ago | (#44157831)

The problem with this type of innovation is that it's a shot in the dark.

We haven't the first clue for the most effective way to teach people. We study things in HS because the subjects are "classics", not because they are useful (Geometry versus Probability, for instance). The "walk around lecturing in front of passive students" model doesn't fit with the need to be rambunctious. The fixed, level-based scale of achievement: "all children should be at this level of achievement at this age, else they are disabled" doesn't take into account variations in maturity or birth date. (Be born a day earlier, get put into a class where you're competing with class mates a year older.)

For reference, check out redirect [amazon.com]. The author carefully details a large number of education techniques and social services which have no scientific basis whatsoever. Predictably, when actually studied, many of these ideas do more damage than good; for instance, regarding teen pregnancy, government teaching initiatives tend to increase the teen pregnancy rate.

There's simply no evidence that a) this system works to the degree of accuracy needed, b) doesn't have a high false-positive rate due to unforseen factors such as drapes waving in the background, c) can be used to any good effect (double-blind studies anyone?) as a teaching aid.

Our track record for using technology to help education is not good.

It makes for a good story, though. "We don't know the best way to teach, but here's something that should work!"

Here's another thought problem for you. Recall the 2009 Star Trek movie which shows a young Spock standing in a pit while a computer presents audio and video lessons. (I don't think the pit model works, but a student in front of a screen seems natural enough.)

Assume that you have control over this content, and can do double-blind studies of minor changes. Each video is a computer program, so any small piece can be redone without retaping the entire lesson. The program allows student interaction.

What features would your ideal teaching machine have, what sorts of things would you teach, what sorts of experiments could you do to home in on the optimum teaching method?

tu3girl (-1)

Anonymous Coward | about 9 months ago | (#44158079)

[amazingkreskin.com] from the FrreBSD Or a public club,

Why not just use smart phone technology.. (1)

bhlowe (1803290) | about 9 months ago | (#44158427)

Using phone apps that do much more make more sense than trying to scan a room full of faces trying to detect the difference between constipation and consternation.. Students can run an iPhone/Android app that let students answer questions from their instructors... the quiz results can be used to get immediate feedback on the learning process..

So many solutions... (0)

Anonymous Coward | about 9 months ago | (#44160743)

...to a non-problem. If a student is confused, he has the responsibility of seeking help.

only crappy teachers would need this (1)

dryo (989455) | about 9 months ago | (#44160985)

To quote Sugata Mitra, any teacher that can be replaced by a computer should be.

Neat, but is it useful? (1)

manu0601 (2221348) | about 9 months ago | (#44161433)

In a real class, spotting the struggling student is obvious. Teachers already do what the proposed system acheive

It is interesting for a MOOC. But if MOOC teachers have to handle struggling students, I fear it will destroy MOOC viability

Interesting tech, but it's not open source (1)

2b (11200) | about 9 months ago | (#44163595)

CERT looks really cool, but it doesn't appear to be open source; at least there doesn't seem to be a download link anywhere. It looks as if there's a company called "Emotient" that's commercializing the tech. It might have been open source at some point but it looks proprietary now.

Check for New Comments
Slashdot Account

Need an Account?

Forgot your password?

Don't worry, we never post anything without your permission.

Submission Text Formatting Tips

We support a small subset of HTML, namely these tags:

  • b
  • i
  • p
  • br
  • a
  • ol
  • ul
  • li
  • dl
  • dt
  • dd
  • em
  • strong
  • tt
  • blockquote
  • div
  • quote
  • ecode

"ecode" can be used for code snippets, for example:

<ecode>    while(1) { do_something(); } </ecode>
Sign up for Slashdot Newsletters
Create a Slashdot Account

Loading...