Automated Arabic Essay Scoring (AAES) Using Vectors Space Model (VSM) and Latent Semantics Indexing (LSI)

Abstract

Automated EssaysScoring (AES) stands for the ability of computer technologiesto evaluate electronic essays written by learner according topreviously determined essay. All the previous works andresearches were applied to essays written in English language and they were applied to essays written inBahasa, Hebrew, Malay, Chinese, Japanese, and Swedish. The research paper suggests an Automated Arabic EssaysScoring (AAES) system onweb-based learning context based on Vectors Space Model (VSM) and Latent Semantics Indexing (LSI). The proposed system consists of two main processes. The firstprocess, deals with applying informationretrieval mechanics to retrieve the significant information from electronic essays. Inthe secondprocess,VSM and LSI areapplying to find out the similarity degree between thepreviously written essays by the instructorand the essay written by the learner.The experiments of ourresults reveal that the proposed system provides an electronic assessment closer to instructors’ traditional judgment, leading toimprove thelearning’sefficiency, performance and to overcome.