Automated Short Essay Scoring System Using Normalized Simpson Methods

The emergence of various methods in making measurement of similarity of short sentences triggered the development of the development of automatic short scoring system. The measurement of similarity of the automatic short scoring system is a brief description that compares the similarity of meanings between student answer and reference answer. The process of similarity measurement between student answer and reference answer is slightly different from measuring the similarity of meaning between two sentences. This difference lies in the process of justifying the similarity. This is because the measurement of reference answer and student answer is only based on the detection of keywords that appear in both, so that sentences that have additional information arc only considered as supplementary information from keywords. This paper proposes a method that can be used to reduce words that are considered less important so that they can be used to improve the measurement of similarity between the reference answer and the student answer. The result shows that the proposed method is able to provide a smaller RMSE value of 1.2 compared with other methods used as a comparison.