Washington, Jan 20 : Researchers at the University of Buffalo have designed a special software that not only reduces the time to grade children's handwritten essays, but may also help in enhancing students' comprehension skills.
The software has special relevance to the school systems and teachers involved in administering the standardized English Language Arts exams that are given every year, usually in January, by public school systems in every state.
"It surprised us that we were able to do as well as we did, especially since this was our first attempt," said Sargur N. Srihari, lead researcher and Distinguished Professor in the UB Department of Computer Science and Engineering .
The study focused on handwritten essays by eighth graders in the Buffalo Public Schools while answering the question from a New York State English Language Arts.
Against 300 essays scored by human examiners, 96 computer-scored essays were judged.
According to the researchers, in 70 percent of cases, the computer program graded the essays within one point of those assigned by human examiners.
"We wanted to see whether automated handwriting recognition capabilities can be used to read children's handwriting, which is essentially uncharted territory," he said.
"Then we took it one step further to see if we could get computers to score these essays like human examiners," he added.
The essays were first scanned into a computer where each line of text was broken down into individual words.
The system recognized the words using contextual information from the rest of the sample and once the majority of words were recognized, the essay was turned into a digital text file.
For the automated scoring step, the UB researchers used an artificial neural network approach.
"In this method, the system 'learns' from a set of answers that were scored already by humans, associating different values or scores with different features in the essays," explained Srihari.
The software program developed at UB was 'trained' to evaluate essays based on six specific writing traits: ideas, organization, word choice, sentence structure, voice and conventions like spelling, usage and punctuation.
James L. Collins, co-investigator and professor in the UB Department of earning and Instruction in the UB Graduate School of Education said that the software now under development could be used as an important teaching tool.
"We envision a program where a student would handwrite an essay, scan it into the computer, which would then 'read' it and analyze it for the specific traits we trained it to evaluate," he said.
"Once a handwritten essay has been 'read' by a computer, we can ask the computer to look for certain features of the writing so that we can spot general patterns and discover what kids are having trouble with," he added.
The UB team's preliminary results with the software are scheduled for publication in the February/March issue of Artificial Intelligence. The paper was published earlier in the online version of the journal.