Open AccessAutomatic Scoring system for evaluating Comprehensive Answers using key features (ASCA)
Author(s) -
N. Sivaranjani,
S. Amudha,
Mary Linda
Publication year - 2019
Publication title -
international journal of engineering and advanced technology
Language(s) - English
Resource type - Journals
ISSN - 2249-8958
DOI - 10.35940/ijeat.f1057.0886s219
Subject(s) - grading (engineering) , computer science , key (lock) , malpractice , test (biology) , similarity (geometry) , field (mathematics) , artificial intelligence , scoring system , natural language processing , machine learning , information retrieval , computer security , engineering , medicine , paleontology , civil engineering , mathematics , surgery , law , political science , pure mathematics , image (mathematics) , biology
Automatic evaluation of learner’s skills is the hot research area in the field of Machine learning. The key idea behind automatic scoring system for evaluating students answer is to reduce the time for instructors in evaluating the test paper and to make the scores consistent. This paper not only aims to evaluate the answer and also takes care of malpractice by implementing plagiarism and also redundant sentences. Redundant sentences may lead to erroneous grades. Experimental results show that our system shows better grading than the existing and also has higher match with the human judgment, especially for the answer that has higher similarity with answer key