SISTEM PENILAIAN OTOMATIS JAWABAN ESSAY MENGGUNAKAN ONTOLOGI PADA MOODLE

Abstract

This paper proposes a combination technique that called hybrid algorithm to be applied into automated scoring for essay e-learning system. This algorithm consists of two main processes: synonym comparison based on WordNet-based semantic similarity measurement and scoring process based on ontology structure. The process for searching a synonym will produce some outputs on different levels. This difference will stimulate a difference calculation of score due to every level reflects to a different similarity of degree. The matching process from input with key answer will generate an accurate matching process. In addition it also added with investigation of ontology class relationship. A different relationship will cause a different score. The last step is integrating this hybrid algorithm and ontology concept into Moodle e-learning system. The evaluation process will evaluate whether the hybrid algorithm can run very well inside ontology system that has been built. Besides that, it is expected that the integration process of hybrid algorithm into Moodle system can support the performance of Moodle e-learning system from essay auto grading perspective.