Slashdot Log In
Computer Program Makes Essay Grading Easier
Posted by
CowboyNeal
on Thu Apr 07, 2005 11:35 PM
from the scantron-grows-stronger dept.
from the scantron-grows-stronger dept.
phresno writes "c|Net is running a short article on Prof. Bent at the Columbia, Mo., University. The Prof. has developed a computer program which he now uses to grade his sociology students' essays. He claims the program can discern content, and argument flow within sentence and paragraph structure, and has saved him over two hundred hours of reading per semester. How long before he's replaced entirely by his own program to cut down on staff costs?"
This discussion has been archived.
No new comments can be posted.
The Fine Print: The following comments are owned by whoever posted them. We are not responsible for them in any way.
Full
Abbreviated
Hidden
Loading... please wait.
Cheating (Score:4, Insightful)
Re:Cheating (Score:5, Insightful)
Parent
Re:Cheating (Score:5, Interesting)
If done successfully, you might get a good grade in sociology for something that would deserve a good grade in computer science
Parent
Re:Cheating (Score:5, Insightful)
Parent
term papers... (Score:4, Insightful)
For a term paper, you additionally have to use correct grammer and spelling. Also, do not try to argue something stupid. Don't take a contrary opinion to the professor or to popular opinion on the college campus. You won't be able to convince the grader, and they'll think that if your argument isn't convincing, then it must be flawed and you deserve a bad or mediocre grade.
These are things that I wish someone had told me when I was an undergrad.
Parent
Re:term papers... (Score:5, Interesting)
I really, really, really wish someone told me this. I lost a letter grade in a class because I had a differing point of view from the professor. I wrote a kick ass term paper, I spent countless hours in the library doing research, I had other people proof read my paper. It was one of the best papers I wrote. But it was the exact opposite of what the professor believed.
We expect our teachers will grade us on our work. But every now and then we get a professor who probably spends too much time writing letters to the editorial section of the new york times.
Parent
Re:term papers... (Score:4, Interesting)
You CAN disagree with the prof, but you'd better be prepared to go into bat.
L
Parent
Re:term papers... (Score:5, Insightful)
Parent
It's about following instructions. (Score:5, Interesting)
When I was in college in the late '80's, the "trick" to getting good grades really was to understand what the professors were looking for, and give it to them.
For example, I had a professor who distributed pre-printed pieces of paper that had a line drawn around it indicating the margin (something like two inches at the top, a half inch on the right and bottom, and three inches on the left. The large margins on the left and top were for the prof's notes and comments to us.) We had to type (with a typewriter) our papers to fit within the bounds of the margins, and spelling and grammar counted (and this was a Psychology class, not an English class.) He would not accept more than the one page. Another professor required papers be written in a specific topical order. If you deviated from those models, you got marked down.
The point was not that the profs were trying to be devious, but to make us take into account the instructions they gave us. If we followed the instructions, we got better grades. If we didn't, we would get marked down. And yes, content did count too.
Yes, it was a hassle, but the result is that now, when my bossed give me instructions, I follow them. The times when I deviate are the times when I really hear about it. Lesson learned!
Parent
"A well thought out Slashshdot Post" (Score:4, Funny)
First, moving around quickly, and with purpose, is a true sign of character. Secondarily, bustle(e.g. hustle) yields more product for the working types. "Hustle and bustle are like my right and left arms," said Li'l Spicy in his famous "Hustle and Bustle Are Like My Right and Left Arms" speech. Webster's defines bustle as "excited and often noisy activity; a stir." A stir, indeed. Finally, sometimes gross stuff can be funny.
Here are some links:
- Turn It In [turnitin.com]
- Penny Arcade [penny-arcade.com]
It is now my intention to play video games for several hours.Sources:
The Brothers Chaps (2004).Homestar Runner. Retrieved April 8, 2005 from www.homestarrunner.com
Random Source (2005). that you won't read because you were too lazy. Retrieved April 8, 2005 from www.toreadthisfar.com
(I have four words for this post: "Too much half-asleep effort")
Parent
Re:Cheating (Score:5, Informative)
Parent
Better teaching tool than grading tool (Score:4, Interesting)
You remember peer editing in 4th grade? Did that have any value? Not really - but if you got instant feedback on papers, that makes it easier to just write better in the first place.
Especially if this technology is combined with this technology [slashdot.org].
Parent
Re:Better teaching tool than grading tool (Score:5, Interesting)
the red squigle under the mispelled word
Back when I was grading papers, I used to recommend the exact opposite to the students -- turn off the "instant" spell-checker, then run the "full" spell-checker and re-read the paper. I found that, in many cases, students would correct anything that had a red squiggle underneath it, but would get a false sense of security that all of the errors had been detected by the word processor.
Oddly enough, when they had a squiggle-free page before them, they were much more attentive to detail and caught the "spelled-correctly-but-used-inappropriately" words.
Parent
For cargo-cult pseudo-sciences only. (Score:4, Insightful)
Yes, it might well be a better learning technique from a usability standpoint
Cargo cults a la Feynman are all about form, and this tool can indeed detect the presence of form and even distinguish form that is considered "good" by some metric from form that is considered "bad".
But unless it actually understands what is being written through deep semantic analysis performed against a thorough database of relation-interlinked concepts, then there is no way the tool can detect hard scientific content (to the small extent that it occurs in sociology) from gibberish that just obeys the right forms.
As Brent himself says, "In sociology, we want them to learn the terms." And that pretty much sums it up.
Parent
Cheating? Teaching! (Score:5, Insightful)
Would be great for high-school students. Have students write an essay or paper and analyze it right in front of them. Then the program highlights their errors (or what the program perceives as an error). Even better, complaining students would help fix bugs in the software because they know their intent - they could send off a highlighted error-ridden version to the developers with an explanation of why they think they are right.
Better yet, give it to everyone! It's not like you can cheat, you still have to rewrite and resubmit your papers. Shit, I say build it into text boxes on slashdot and wikipedia to start!
please do not hold this post to the standard of the Qualrus [qualrus.com] (real page of the software)
Parent
Re:Cheating? Teaching! (Score:4, Insightful)
That would be counterproductive. If the program actually works with even 70% reliability, I'll eat my hat. In other words, I guarantee it's worse than the average student. Natural language processing is AI-complete. Every six months somebody claims to have solved the problem, and it always turns out to be another Eliza ("Did you come to me because the fact that question that concerns you is the real reason?") or babelfish ("To celebrate the score and seven years, our suffered ancestors brought ahead on this continent a new nation, taken in freedom and devoted to the proposal which all gecreeerde people are equal") or, frequently, even worse.
"I have a computer program that understands English sentences" is roughly the same as "I have some really great real estate a quarter-mile north of downtown Chicago that will fetch a fortune on the market, but because I'm in a hurry I'll let you have it for half price."
Parent
Re:Cheating (Score:5, Insightful)
The real question in this scenario is whether or not they will learn enough by cheating to have gained something valuable.
If they have to write a program to beat the teacher's program, are the students not learning something very valuable (at least in the marketable business skills department)?
Also, in order to write a program that creates essays that conform to the teachers program, will it not also be necessary to learn the grammar and logic rules the teacher considers to be important and even ponder those rules for extended periods of time?
It seems to me that the cheater (or at least the first cheater) will do more work than the professor did and thereby become quite familiar with English grammar, organization of arguments, and computer programming. All of these are useful skills.
Parent
Re:Cheating (Score:4, Insightful)
If they have to write a program to beat the teacher's program, are the students not learning something very valuable (at least in the marketable business skills department)?
No. Only the person who writes the cheating program does.
See, that's the beauty of the internet, my friend. I don't even have to know how to program to beat CSS encryption on DVDs. I merely have to download said program from someone else (maybe even the only person in the entire world) who does know how.
Also, in order to write a program that creates essays that conform to the teachers program, will it not also be necessary to learn the grammar and logic rules the teacher considers to be important and even ponder those rules for extended periods of time?
My previous point aside, why do you assume that the class is on English? Why should a history teacher give a damn about your understanding of English? Even IF it was an English class... all of my college-level English classes haven't even touched on grammar or syntax. Those things are assumed.
Moreover, beyond looking for keywords, how does this program actually prove that the student knew what he or she was talking about? I think we have all come across beautifully expressed babble. What prevents a student (or a script?) from doing the same? Lastly, how can this guy claim victory while at the same time admitting that he never read the papers? How has he proven the program was functioning as intended?
For all of those seriously interested in this program: I've got a anti-baboon charm here to sell to you. Does it work, you ask? Well you don't see any baboons do you!?!
-Grym
Parent
Fire the professor... (Score:4, Interesting)
If a professor does not care enough to read my papers, then to hell with him. There is more that a professor does than just check grammer, or look for passages that deals with the question and used terms from the book. The best professors I had were the ones who wrote all over the margins, sharing their thoughts about my ideas. Those are the ones who I would meet in their office to chat with. They are the ones who I went to for advice.
I had one teacher in english who graded the first paper, reading them all. She then never read another paper, only skimmed them. She pretty much gave out the same grade on all your papers you got on your first paper. I got an "A" on my paper, and another student got a "D". So I was working with the "D" student, and no matter what was done, the "D" grades went up to "C-" but stuck. So for the last paper, we switched our papers. Guess what? My paper was still an "A" even though it belonged to the other student, and the other paper was a "C". We went to the teacher to explain what we did, and rather than the professor owning up to what was done, we the students got blamed.
This really pisses me off. Professors get paid over $70,000 a year, some over $100,000 a year, they work 20 hours a week, and they have job security and a union. Then they want to slack off. Fucking asshats. Something like this makes me want to vote to remove public funding from schools, to always vote no whenever there is a refferendum to increase property tax. With those kinds of professors, people might as well get their education at the public library.
Parent
Re:Fire the professor... (Score:5, Insightful)
I used to give short answer/essay questions to my astronomy students the first couple of semesters I taught the big non-major course. It took a tremendous amount of time to grade which was one reason I stopped, but not the primary reason. I'm a novelist, and I know how to write, and there was a consistently high fraction of exams written so badly it was very painful to read. Perhaps I should have kept at it, with the idea that it's good for the students. But a few essays in a science class won't dent the problem that starts in k-12 education.
Parent
Re:Fire the professor... (Score:4, Insightful)
With regards to students' written work: My field is meteorology. I too used to give students in my survey-level meteorology class opportunities to "express themselves" via short answers (a paragraph or two) on exams. I stopped because it was so hard to grade many of them because they were written so poorly. In addition to that, it is very difficult to grade short answers in a consistent way. For many of the short-answer questions I would usually end up just writing a number down ("Hmm.. this feels like a 3-points-out-of-5 answer") which real doesn't feel right... but what do you do when the concepts are confused, spelling and grammar are terrible but they have expressed some knowledge of the material?
I have talked with professors who have been doing this stuff for a much longer time than I (some of whom are into the latest trends in teaching etc.) and many of them are gravitating towards all objective tests (multiple choice and true false) for their survey level classes (and some upper level). A well-written objective test should adequately test a student's knowledge of the material in a fair way, especially in the sciences where there truly are right and wrong answers. Still, I don't like giving these kinds of tests - it just doesn't feel right - but like grading the others even less.
In my upper level classes all of my testing is subjective, and I do assign papers such as case studies where a storm system is described and analyzed. Some of my seniors can write well, most of them are so-so and a few are truly terrible. I tell them up front that spelling, grammar, style etc. counts on these assignments, and I find that if you tell students that these things are part of their grade they will put in an effort to write well.
I suppose I could just "blame the high schools" but I think the problem is deeper than that. In the US grade inflation is a huge problem in many universities and at the college level, student evaluations of faculty are often very highly regarded (and if you are evaluated poorly it can keep you from getting tenured or promoted). So a logical response is for faculty to go easy on students, rightly assuming that this will return higher evaluations. I don't know if that is a part of the writing problem, but I know an A today isn't an A 20 years ago at many universities.
Parent
Re:Fire the professor... (Score:4, Informative)
Well, there are some professors that meet that description, but at a reasonable university, those tend to be in the minority. At a reasonable university, most faculty work more like 60-80 hours a week, particularly if they are active in research. I certainly have pulled many more all-nighters as a professor than I did as a student and I pulled a lot of them as a student. A few things that students tend to overlook:
There are terrible professors and great professors at every university- the fractions may change from place to place, but with some seeking out and strategy, usually it's possible to do well.
Parent
Re:Fire the professor... (Score:5, Insightful)
One of my teachers at school tried that. Unfortunately what happened is that in each group the rest of the members (the groups were arranged so each group was mixed ability) ganged up on the 'smart but weak/shy' one to do all the work then goofed off.
Actually, now I come to think about it, that's exactly what happens in the workplace.
Stephen
Parent
Re:Cheating (Score:4, Funny)
I spent 3 minutes reading about it and I gave up.
Parent
Hmmm (Score:5, Insightful)
Angst
Re:Hmmm (Score:5, Insightful)
Parent
Re:Hmmm (Score:5, Insightful)
What's the point of the class? In Calculus 1, the point is to learn concepts and methods that allow you to perform basic operations, as proven by your ability to work out problems on homework and tests. You're not asked to be creative or anything--that comes later, in 300 or 400 level classes or graduate work. First, you have to learn the basics.
I imagine sociology isn't that much different--at least, it wasn't in Poli Sci when I was in college. First, you have to learn a bunch of basic facts and rules and concepts, and demonstrate that you have a know them. You should be able to talk about them, define them, and answer questions about them. Anybody who's being creative in a freshman sociology class is ahead of the game.
And don't give me no shit about "I spent hours making it, you should spend hours reading it". That's like the
I mean, shit--it took me DAYS to write my first couple of C programs in CS 101. Does that mean that the professor is shorting my education if he takes 10 seconds to grade it?
Parent
Calculus (Score:5, Funny)
Parent
Structure (Score:5, Insightful)
So it measures structure and argument.
How's it going to measure creativity of thought? Are we going to just pump out logic machines from colleges?
Re:Structure (Score:5, Insightful)
Parent
Re:Structure (Score:4, Insightful)
He's a sociology professor, and he's managed to write a natural language parser that can actually decipher meaning, and mark the relevance of the content of the essay against the question.
Parent
Re:Structure (Score:5, Insightful)
Perversely, the worse a paper is, the more time it receives; it's more important, and more difficult, to motivate a failing grade than a good one. Also, to some extent all good papers (or assignments) are alike and can be spotted fairly easily; it's the bad ones that are (regrettably) unique and need individual attention.
Parent
Not the world's best plan (Score:5, Insightful)
Re:Not the world's best plan (Score:4, Insightful)
It's possible to train computer programs to translate text between languages by feeding examples of good and bad translations to pattern-recognition algorithms, which start with simple rules. Most of these models are similar to neural-net machines, which is in turn based on the fundamental theory of how animal brains (including human brains) operate. You don't design and code an algorithm, you train the machine by example, with some human-assisted trail-and-error.
This often works because that's how human judgement works: we learn just about everything by example and trial-and-error, and we're VERY good at it (look at what millions of years of evolution can accomplish!). This isn't to say that a trained neural net machine is "intelligent" or "conscious", just that solves problems by the same mechanism that a human brain does, albeit in a much more limited fashion.
Of course, the effectiveness of a trained machine is limited by how big a computer you have, and how well you train it. Re-creating the complexity of the human brain in software with present-day techniques and equipment would be impossible (neural net software is VERY memory intensive when it gets complex). This may change in the future, but that's another debate that I won't get into.
I'm not saying that this professor's software actually works or not--he could easily be full of shit. I'm also not saying that you can't game one of these machines the same way spammers game Bayesian anti-spam filters: use trial-and-error to figure out how to trick the machine consistently.
In fact, I'm assuming that a canny student could steal the software and do exactly that. After all, the human brain is a much more powerful learning machine than the program, and could probably outsmart it in the same way that people can outsmart rats.
But then again, this is a socialogy course, so his students probably won't think of it on their own.
Parent
Intresting (Score:5, Insightful)
Re:Intresting (Score:5, Insightful)
Parent
And talent may remain unfound (Score:5, Insightful)
But how would hidden talent and creativity be found? How will the teacher know if his students are actually trying hard to write their papers when all he does is check the thing with a computer program?
It's a really terrible idea and I think it's really cheezy. Ohh, he saved some time. So does that mean he now gets paid less? Does this automation get the students a discount? Yea, right.
If I'm going to put a lot of work into writing an interesting paper about something, I want someone to read it.
More importantly... (Score:5, Insightful)
Just as bad as plagarism (Score:4, Insightful)
This one is just nuts. Why on earth am I writing essays which are going to be marked automatically by a machine? It's bad enough that scantron cards have found their way into subjects where they're totally irrelevant (a multiple-choice test for a university level Shakespeare course?), this is just another reason why post-secondary education has become increasingly less complete.
If he's allowed to use a machine to save him the effort of reading an essay, I should be able to use a machine so I don't have to go through the effort of writing one. Trust me, as arduous as it is to read a 20 page essay on the relative merits of liquid rubber concrete compound fasteners, writing it takes a lot more effort, a lot more time, and it damn well deserves to be read by the professor who assigned it.
i don't see why his studenrs would be doing better (Score:4, Informative)
The article didn't say anything about what kind of feedback the program provides, but I can't imagine it's anywhere near as helpful as the paragraph-long evaluations of my logic, style, and structure, which I got back with every paper I ever turned in, and I'd be impressed but surprised if his program took each student's previous weaknesses into account in the course of the evaluation. In writing, practicing can only do so much - the real help is in constructive feedback, and I just can't imagine where these students are getting it if not from the human graders of their papers.
GMAT exam has been doing this for awhile now... (Score:5, Informative)
According to ETS [ets.org], the e-rater agrees with the human grader 98% of the time.
The program DOES NOT grade the essays! (Score:5, Informative)
"The final papers, which he does read, are usually much better as a result of Qualrus, too."
There you go! For the reading and comprehension impaired, here's a summary of what's actually happening, which even the reporter didn't get:
1. Students write a draft of their essay, which they then upload via a Web form to this program
2. The program gives them a score on various parts of their essay, giving them valuable feedback on what needs to be improved.
3. Students improve the pieces of their essay that the program suggests.
4. Students submit the final draft to the professor, who reads and grades each one by hand. Due to steps 1-3, the quality of the final draft is much higher.
This sounds like a great thing to me. Wish I had something similar for my students. I don't have the time to read through dozens of drafts for every student. Too bad I'm not in sociology.
Re:The program DOES NOT grade the essays! (Score:5, Informative)
From TFA:
The computer-generated scores count for about a third to a quarter of students' final grade for Brent's class.
There you go! Make sure you RTFA very carefully before accusing others of being reading and comprehension impaired.
Parent
Save $$$ on tuition now? (Score:5, Funny)
200 hours * $32.00 = $7200
He teaches about 84 students...
$7200 / 84 = $85.71 refund for each student. It's party time!
Use it for Moderating SLASHDOT? (Score:5, Funny)
A new excuse (Score:4, Funny)
Cheers,
IT
A While (Score:4, Interesting)
I would say a long time. A program that tries to understand natural language requires some sort of "intelligence," a quality that humans definetly possess and computers, up to now, definetly do not.
AI still mostly consists of certain hacks to trick other people into thinking the programs are intelligent - basically attempting to fool the Turing Test. This can often produce great results and can be very useful, but almost never replaces a human in complex tasks (such as natural language processing).
The difficulty arises because humans cannot easily (or perhaps possibly) comprehend their own intelligence. It seems so natural to read a sentence and make sense of it, but when it comes time to program a computer to do it, most people try to emulate the behavior of their own comprehension. This may trick some people, but the simple nature of the programs cannot possibly be as powerful as an actual human.
The best solution, in my opinion, is a closer study of neuroscience and how it can be applied to silicon (or how new technologies need to arise to emulate the complex neural structure of the brain).
I know that people are starting to use computers to grade standardized essays, but there (currently) must always be a human checking the results because of the small number of unforseen cases that the hacked algorithms cannot do a good job. After all, the programs do not "understand" anything that is written. That is why I postulate it will be a long, long time before computers can truly emulate humans.
Re:Wouldn't want to be in his class. (Score:5, Interesting)
I go to the University of Missouri. I wouldn't want to be in his class either. Hmm, I don't have enough of the keywords in my paper? How about you actually read the paper you made me write?
a culty/Edward_Brent.html [missouri.edu]
http://sociology.missouri.edu/Faculty_and_Staff/F
Parent
So what? (Score:5, Insightful)
If I can write a program to automate a menial task so I don't have to do it, then by all means, I should do it. If grading undergrad papers is a menial task that can be automated, then it should be automated.
I mean, just because a freshman writes a bad paper doesn't mean a professor has to actually read it.
Parent
Re:"written using a word processor worth 50 points (Score:4, Funny)
What, his program can't read a DVI?
Tom
Parent