Title of article :
AUTOMATED ASSESSMENT OF STUDENTS ARABIC FREE-TEXT ANSWERS
Author/Authors :
Refaat, M. M. Mansoura University - Faculty of Specific Education - Computer Teacher Preparation Department, Egypt , Ewees, A. A. Mansoura University - Faculty of Specific Education - Computer Teacher Preparation Department, Egypt , Eisa, M. M. Port-Said University - Computer Science Department, Egypt , Sallam, Ab. A. Port-Said University - Faculty of Engineering - Electrical Engineering Department, Egypt
Abstract :
Essay questions are an important assessment way, they could not be dispensed it with objective questions, but essay questions need a long time to be evaluated properly. So, much research has focused on the assessment of essay questions automatically. In this paper, a method to assess Arabic free text answer (essay) automatically based on Latent Semantic Analysis (LSA) technique is proposed. It improves LSA by processing the entered text, unifying the form of letters, deleting the formatting, replacing synonyms, stemming and deleting Stop Words to produce a matrix that represents texts better than the traditional form of LSA matrix. The proposed method concerns mainly with decreasing the deleted stop words keeping its correlation with the human assessor at a desired and satisfied level
Keywords :
Automated Arabic essay assessment , Latent Semantic Analysis , Automatic free , text Grading
Journal title :
International Journal of Intelligent Computing and Information Sciences
Journal title :
International Journal of Intelligent Computing and Information Sciences
