الفهرس 
Abstract
Problem definitionOnly 14 pages are availabe for public view
Abstract
E-Learning plays an important role in education today, it began decades ago with the introduction of televisions and overhead projectors in classrooms and has advanced to include interactive computer programs, 3D simulations, and real-time online discussion groups comprised of students from all over the world. E-learning environment does not provide good support as compared to the traditional teaching environment because of their inability to adapt to the learner’s profile. It is considered as an integral part of instruction-based learning methods researchers in the e-learning domain are looking to bring in intelligence in their environments so that they can adapt to changes with respect to an individual user’s needs. Intelligent software agent can develop a user’s/learner’s profile and use it to perform tasks for the learner. Intelligent software agents can adapt to different levels, which include user interface adjustment based on user’s demands and habits and adaptation of Knowledge level that presented to user depending on user’s needs and previous knowledge. Intelligent Tutoring Systems (ITSs) are good example of using intelligent software agents in e-learning. It provides an individual tutoring system and it is considered as a virtual training assistant to develop student’s knowledge without instructors. Assessment is a method of evaluating student knowledge based on specific learning objectives. There are a multiple kind of questions, the written essay and assessment, the most complex of all of them. ITS of free-text answer (essays) has received a great deal of work during the last years due to the necessity of evaluating the deep understanding of the lessons concepts that according to most educators and researchers. The main objective of this work was employ summarization which it is a process to select important information and creating a short version of from a source text, to propose a framework for student answer assessment by utilizing natural language processing algorithm and tools and merges semantic relations between words, for improving the accuracy of automatic summary evaluation. The semantic similarity is computed using information from a lexical database. In this thesis, a framework proposed to evaluate students essay answers based on a linguistic knowledge. The obtained results from implementing our proposed system in evaluating our simulation results indicated a high accuracy in its performance when compared with the other techniques. The efficiency of this framework measured using Pearson’s correlation coefficient (PCC) and Root Mean Square Error (RMSE) based on a student answers evaluation obtained from North Texas University dataset, which is available online.