Although the manual evaluation of essays is a time-consuming process, writing essays has a significant role in assessing learning outcomes. Therefore, automated essay evaluation represents a solution, especially for schools, universities, and testing companies. Moreover, the existence of such systems overcomes some factors that influence manual evaluation such as the evaluator’s mental state, the disparity between evaluators, and others. In this paper, we propose an Arabic essay evaluation system based on a support vector regression (SVR) model along with a wide range of features including morphological, syntactic, semantic, and discourse features. The system evaluates essays according to five criteria: spelling, essay structure, coherence level, style, and punctuation marks, without the need for domain-representative essays (a model essay). A specific model is developed for each criterion; thus, the overall evaluation of the essay is a combination of the previous criteria results. We develop our dataset based on essays written by university students and journalists whose native language is Arabic. The dataset is then evaluated by experts. The experimental results show that 96% of our dataset is correctly evaluated in the overall score and the correlation between the system and the experts’ evaluation is 0.87. Additionally, the system shows variant results in evaluating criteria separately.