[리서치페이퍼=Fabian Rivera 기자] Professors at the University of Michigan have developed a writing-to-learn tool that will identify the strengths of a student's written submission.Some educators and students may be using the technology as early as fall 2017.
The technology is called M-Write and it uses automated text analysis (ATA) to help professors find out whether or not students are grasping the concepts of the course.ATA works by analyzing things like vocabulary or topic matching in an assignment.
It was initially developed by two professors to help students in increasing their conceptual learning skills in larger courses, as well as to aid in streamlining the grading process for professors, allowing them to accurately detect which students will need the most help.
The program is still new, so writing fellows should verify the tool's grading process to make sure the computer's assessment is correct before giving the assignment back to the student with the computer-generated revisions list. The student will then have the opportunity to revise their writing and resubmit it to the class.
"The verification to us is very interesting because it not only gives the human graders a moment to pause and reconsider their assessments but more importantly, it provides a direct feedback loop to the algorithm development and allows us to create a better one," said Chris Teplovs, the project's lead developer at the Digital Innovation Greenhouse.
According to the University of Michigan, M-Write has already been used in several classrooms with some success, and will be used again in a large statistics class in the fall.
Source: https://commons.wikimedia.org/wiki/File:University_of_Michigan_August_2013_096_(Palmer_Commons).jpg Author: Michael Barera[리서치페이퍼=Fabian Rivera 기자]