An Expert System for Automated Essay Scoring (AES) in Computing Using Shallow NLP Techniques for Inferencing

Date Added: Aug 2012
Format: PDF

In this paper, the authors present the report of the development of an Expert System (ES) that; acquires the knowledge of Subject Matter Experts (SMEs) in a specific computing field, "Software Engineering", uses a built-in inference engine designed with shallow natural language processing techniques (Information extraction using tokenization, statistical keyword analysis and domain-specific dictionary) and a fuzzy-scoring model to assess students' free-text answers to open-ended questions and hence, computes the correctness of students' answers with respect to lecturers' underlying model answers or templates. The newly developed ES was adapted to an academic course in the university system and its performance was evaluated using certain statistical metrics.