Flawed Algorithms Are Grading Millions of Students’ Essays • Hacker News Board

Re: Flawed Algorithms Are Grading Millions of Students’ Essays

#291

Post by na_ka_na » Fri, Aug 30, 2019, 6:42 PM UTC

robinwassen wrote: post #198

I am working with reducing the time teachers spend on exams and assessments. I have access to a cleaned and manually scored dataset of 550k essays that is exponentially growing. Looked at creating at a model based on this dataset to automatically score essays with NLP parameters such as grammar, structure, spelling, word complexity, sentiment, relative text length etc. The problem that I encountered was actually how…

Here are some thoughts: 1. Instead of grading, maybe you can use it for training, tutoring. If a student is learning to write essays, I'm assuming it's hard for them to get any feedback. 2. But then there's probably not enough money to be earned there.

One trick might be to write an independent AI to summarize the essay back and see how closely it matches the essay title. This might weed out gibberish essays with sound English sentences.

Re: Flawed Algorithms Are Grading Millions of Students’ Essays

#292

Post by mlyle » Fri, Aug 30, 2019, 7:52 PM UTC

chessturk wrote: post #285

mlyle wrote: post #164

Earlier quoted context omitted.

Hey uh, that actually seems valuable. I'd believe that ML could spot abuse that humans miss pretty well from signals like non-overt references in homework and school records, if one could come up with an adequate training set. Much more likely than teaching ML to score reasoned and creative activity in any reasonable way.

This is so dangerous. Society's bigotry is going to flood that bad boy so quick you might as well name it Gobbels. I love ML. I want children to be safe. This is not the place for ML or AI or Quantum or any tech. What needs to exist is better resources for those children, that mother grading the tests, the teachers of those children, and social services that are meant to support them. If you want to make a difference…

> Don't go building a automaton King Solomon who decides why this kid should be taken from these parents because speaking Spanish was worth -0.1 on some goddamn weight trained on data generated from a racist society.

Totally what I advocated for and not a strawman attack /s. Indeed, the chance that such an algorithm could be racist or classist and there being needs to avoid bad correlations and have appropriate controls is important.

I think there are opportunities here. Ideally ed-tech doesn't take humans out of the loop, but asks schoolteachers and administrators questions like, "Hey, are you sure students A, B, and C are being supported correctly for subject Z? Are you sure students D, E doesn't have some kind of abuse or other significant home problem? It sure looks like student F is in this subpopulation that research shows benefits from educational intervention Y. You might want to keep your eye out for that."

And then the teacher goes "Oh, crap. Now that I think about D, there were always these little things 1, 2, and 3 that seemed off... maybe this is worth a referral to social services to check on what's up."

Or "Oh, ... maybe F's struggles in reading really are a speech problem and we should handle that"

Re: Flawed Algorithms Are Grading Millions of Students’ Essays

#293

Post by MisterBastahrd » Fri, Aug 30, 2019, 8:45 PM UTC

Here's a thought: if classwork and homework is getting so overwhelming that teachers can't possibly grade all of it, then it's overwhelming for the STUDENTS too, and they shouldn't freaking be assigning so much busywork. You don't need a 5 page essay to determine whether a kid has read a book. You can figure that out really quickly in a classroom discussion without anyone having to lift a pencil.

Re: Flawed Algorithms Are Grading Millions of Students’ Essays

#294

Post by dragonwriter » Fri, Aug 30, 2019, 8:50 PM UTC

MisterBastahrd wrote: post #293

Here's a thought: if classwork and homework is getting so overwhelming that teachers can't possibly grade all of it, then it's overwhelming for the STUDENTS too, and they shouldn't freaking be assigning so much busywork. You don't need a 5 page essay to determine whether a kid has read a book. You can figure that out really quickly in a classroom discussion without anyone having to lift a pencil.

> Here's a thought: if classwork and homework is getting so overwhelming that teachers can't possibly grade all of it, then it's overwhelming for the STUDENTS too

There's no necessary connection there, especially if one of the reasons that teachers are being overwhelmed is that the teacher/student ratio is increasing.

> You don't need a 5 page essay to determine whether a kid has read a book.

No, you need it to determine whether a student has (1) read and understood a book well enough to apply structured thought to the contents and (2) has developed the writing skills to write a 5-page essay.

Determining whether a student read a book is rarely, on its own, of significant interest in school.

Re: Flawed Algorithms Are Grading Millions of Students’ Essays

#295

Post by pault » Fri, Aug 30, 2019, 9:38 PM UTC

dahart wrote: post #133

> Utah has been using AI as the primary scorer on its standardized tests for several years. “It was a major cost to our state to hand score, in addition to very time consuming,” said Cydnee Carter, the state’s assessment development coordinator. The automated process also allowed the state to give immediate feedback to students and teachers, she said. Yes, education takes time and costs money. Yes, not educating is b…

The instant feedback mechanism is just begging for someone to turn it into a GAN by writing the other half. I would absolutely love to hear that some particularly clever high school student was able to train an ML algorithm to consistently fool the grading algorithm, thus instantly rendering all of their efforts worthless and dragging the administrators through the mud at the same time.

Re: Flawed Algorithms Are Grading Millions of Students’ Essays

#296

Post by eukaryote31 » Sat, Aug 31, 2019, 2:57 AM UTC

robinwassen wrote: post #198

I am working with reducing the time teachers spend on exams and assessments. I have access to a cleaned and manually scored dataset of 550k essays that is exponentially growing. Looked at creating at a model based on this dataset to automatically score essays with NLP parameters such as grammar, structure, spelling, word complexity, sentiment, relative text length etc. The problem that I encountered was actually how…

Current Transformer models are looking pretty good at complex end-to-end tasks (at least, better than the shallow regression with hand-picked features that ETS probably uses). In a few years, complete end-to-end evaluation may not be so impossible, especially with so much data.

Re: Flawed Algorithms Are Grading Millions of Students’ Essays

#297

Post by bryanrasmussen » Sat, Aug 31, 2019, 4:10 AM UTC

C1sc0cat wrote: post #226

bryanrasmussen wrote: post #219

Earlier quoted context omitted.

I went to high school in Utah, long before this automated scoring. It sounds awful but considering the quality of the education I received there perhaps not that bad after all. My best Utah education anecdote - In the first day of British literature class the teacher came in and asked "Does anyone here know what A.D means?" someone said After Death - she said no. I figured this was my time to shine so I raised my eag…

How is this relevant in a Lit class - presumably you hid the fact you where a Catholic / Anglican from her.

Actually I am and was an atheist, but I had recently been on an "I'm going to read the encyclopedia!" mission.

Re: Flawed Algorithms Are Grading Millions of Students’ Essays

#298

Post by yoz-y » Sat, Aug 31, 2019, 7:05 AM UTC

bradstewart wrote: post #266

yoz-y wrote: post #195

Earlier quoted context omitted.

> Turns out the instructions said the essay would be scored on verbal efficiency; getting the point across clearly with the fewest words. I started playing around and realized that the more words I added, the higher the score, whether they were relevant or grammatical or not. Frankly, this does not change anything from my experience in school decades ago. The teachers always said that the length does not matter and w…

Is it possible that the students who wrote shorter papers were in fact presenting incomplete arguments and/or thoughts? Writing clearly and concisely is extremely difficult.

It is possible but all of them? Also by “short” I usually mean four pages which was the usual recommendation for a paper length. To have a good grade one would need to write ten. The subject was usually something vapid so most of that must have been drivel.

Re: Flawed Algorithms Are Grading Millions of Students’ Essays

#299

Post by yoz-y » Sat, Aug 31, 2019, 7:06 AM UTC

chessturk wrote: post #281

MertsA wrote: post #249

Earlier quoted context omitted.

Historically on the written portion of the SAT length is substantially correlated to the final score.

I'm not sure that's an issue by itself. If the prompt is broad enough, a minimum length can be reasonable for essays. It certainly could be a problem if the prompt was too narrow, or time constraints, or some other factor. Do you think the correlation by itself indicates something negative/inefficient I'm missing?

I think that the required length should be bounded on both sizes and penalised if the paper is either too short or too long.

Re: Flawed Algorithms Are Grading Millions of Students’ Essays

#300

Post by bryanrasmussen » Sat, Aug 31, 2019, 10:56 AM UTC

xamuel wrote: post #248

bryanrasmussen wrote: post #231

Earlier quoted context omitted.

Good point, I better teach my kid this skill so she can go on to a job programming one of these "AIs" idiocracy will happen not because people get any stupider, but because the bots reward the stupid ones first.

Maybe Idiocracy was right about the whole "It's got electrolytes!" meme, except swap out electrolytes for neural networks.

Now I need a video of Luke Wilson saying "What are neural networks? Do you even know?"