|Name: || Computerized Method of Assessing Open-ended Questions |
|Abstract || Many learning management systems such as Blackboard and Moodle allow users to create online exams. These online exams can be marked by the computer automatically as long as the items are true/false and multiple choice questions. In order to assess at higher levels of Bloom's (1956) taxonomy, it is necessary to include open-style questions in which the learner is given the task as well as the freedom to arrive at a response without the comfort of recall words and/or phrases. Some computerized assessment systems have been designed and developed to compare essays. These computerized systems mainly use statistical approach rather than semantic approach and need large human-marked essays as the corpus. The drawback of the statistical approach is that the difference between "the boy stepped on a spider" and "the spider stepped on a boy" cannot be told. This research takes the word meanings into consideration, and combines both of statistical and semantic approaches to design an efficient and accurate assessment method. The designed method doesn't require large human-marked answers as database, and uses open source APIs and components to implement the experiment system.
This research project takes the word meanings into consideration, and combines both of statistical approach and semantic methodology to design a more efficient and accurate assessment method. There are three goals:
1. Large human-marked essays are not required as corpus;
2. the method can understand the semantic meaning of the essay and/or open-question's answer while assessing the essay and/or the answer; and
3. the implementation of the method uses open source solutions.
This research proposes the design of a computerized assessment method which integrates different ground theories to assess semantic meaning of the text. The ground theories include Natural Language Processing, Information Retrieval, Information Extraction, and lexical and semantic relations of the words. |
|Start Date|| 2009-10-01 |
|End Date|| 2010-03-31 |
|Research Areas |
|artificial intelligence and education||computational models of learning analytics||data, skill, competency, and knowledge|
|e-education||knowledge representation and reasoning||natural language understanding|
|Source Name ||Amount |
Updated June 19 2017 by FST Technical Staff