Inferring Appropriate Feedback Timing from Answering Styles for Open-Ended Questions

Abstract

Among the possible forms of test, open-ended question has a non-replaceable role in assessing\r\nhigh-level thinking in science education. However, teachers usually hesitate to give\r\nthis type of tests because of the grading efforts involved unless the grading can be processed\r\nautomatically by the computer. Recently, there has been much research on automatic text\r\nprocessing in the area of language learning and writing [1] and science education [2]. The\r\nsystem in [2] was further customized into an intelligent tutoring system, called VIBRANT,\r\nthat can provide feedback to the students according to the answers that have been inputted\r\nso far [3]. In this system, the students were asked to answer an open-ended question in the\r\nform of ideation and explanation. When an idea or explanation is entered, appropriate\r\ncomments or feedbacks are provided automatically according to the established user model.\r\nHowever, this system requires a model of domain expert to compute the score for the students.\r\nIn addition, only the overall collection of answers counts without regard to the course\r\nof how they were inputted.