International Journal of Computer Applications |
Foundation of Computer Science (FCS), NY, USA |
Volume 177 - Number 25 |
Year of Publication: 2019 |
Authors: A. E. E. Elalfi, A. F. Elgamal, N. A. Amasha |
10.5120/ijca2019919707 |
A. E. E. Elalfi, A. F. Elgamal, N. A. Amasha . Automated Essay Scoring using Word2vec and Support Vector Machine. International Journal of Computer Applications. 177, 25 ( Dec 2019), 20-29. DOI=10.5120/ijca2019919707
Essay scoring is one of the most important tools for evaluating and assessing the level of achievement of educational goals. It aims to innovate performance, arrange, integrate ideas, and connect them by using the vocabulary of the particular subjects. Human essay scoring consumes a lot of time and effort, this leads to mistakes. Automated Essay Scoring (AES) solve to great extent problems. A new approach for AES is presented. It is based on Natural Language Processing (NLP) which is used to unify linguistic answers, word2vec model which converts words into features and synonyms in semantic space, Support Vector Machine(SVM) is used to classify students answers and estimate score levels. The system stages consist of preprocessing, feature extraction, classification and similarity algorithm. The results of proposed method reaches high precision (94%) relative to human resident scores.