Every time students take a writing exercise on Quill.org–a writing instruction platform for schools–their responses are logged by computers and analyzed for patterns. Algorithms take account of every false word they type, every misplaced comma, every inappropriate conjunction, deepening a sense of where the nation’s kids are succeeding in sentence-construction and where they need extra help.
The algorithms substitute for human intervention. Instead of teachers having to correct errors late at night with a red pen, the system does it automatically, suggesting corrections and concepts on its own. The goal, says Peter Gault, who founded Quill three years ago, is to reach more students than traditional teaching methods, including those who need support the most. About 400,000 students in 2,000 schools have used the (mostly free) writing-instruction platform so far.
“Teachers just don’t have enough time in the day to offer feedback on everything students write, and that becomes a huge blocker to students moving forward,” Gault says in an interview. “Using machine learning to detect these patterns really unlocks a lot of options that allow us to bring this to thousands, or millions, of additional students in the coming years.”
The New York-based startup trains its algorithms with about 200 responses to each exercise, submitted by its programmers (it has about 300 exercises so far). As the students offer up thousands of their own responses, the code is then able to detect patterns without additional human intervention. When it prompts students to correct their sentences, it does so based on the collective trial-and-error of thousands of other users of the service.
A typical exercise asks students to connect a series of ideas into a sentence, like the following:
Jackie Robinson had a strong mother. She taught him to be proud. He did not give up. He faced racism.
A decent answer might be: “Jackie Robinson did not give up when he faced racism because he had a strong mother who taught him to be proud.” It combines the ideas and it shows their relationship–that is, that Robinson’s attitude was forged during his upbringing.
Students often use fragmentary or over-run sentences, or they’ll use “and” instead of more expressive conjunctions like “so,” or “but,” or “instead,” Gault says. Another exercise asks users to link up two phrases like “bats have wings” and “they can fly.” If they type “bats have wings and they can fly,” they’ll be told the sentence makes sense but that they can improve it with another word (“so” is a better choice). Then they’re asked to correct the punctuation (there should be a comma between the two clauses: “bats have wings, so they can fly”).
“A lot of schools don’t know how to teach writing,” Gault says, echoing what teachers themselves say. “With math, there is a clear process. You start with addition, subtraction, and multiplication, then you move on to algebra, geometry. In the writing world, we don’t see that. We often see [students] are taught in a haphazard manner.”
Gault, a wiry and energetic entrepreneur in his mid-twenties, says he initially imagined a startup that encouraged low-income students to debate social issues and thus improve their critical thinking. But he soon realized many, particularly low-income students, are struggling with the “basic building blocks of language” and that he’d have to start at a more fundamental level. He talks quickly and excitedly about Quill’s mission. Sentences are just the beginning, he says. He wants to build the platform out so it can help students write whole paragraphs, and even thesis papers and news stories.
“We’re at a very early stage of educational technology. What it looks like now is the equivalent of movies in the 1920s. It’s silent black and white films. We can do a lot more to get many more people writing well, ultimately improving their ability to think clearly. There are 30 million low-income kids in the United States, and we want to make sure every one is a strong writer.”