K-Means Clustering for Answer Categorization on Latent Semantic Analysis Automatic Japanese Short Essay Grading System

This paper discusses about the development of an automatic essay grading system for Japanese short essay answer by applying the K-Means Clustering to group each question’s topic and Latent Semantic Analysis to make the assessment. The system is developed to help facilitate the examination of essay answers that are currently still being done manually. The development of the system itself is done by using Python programming language. The test scenarios were carried out by varying the types of hiragana and romaji input also the process of stopwords elimination. From the results obtained and the analysis carried out, the form or type of text input used and the use of parameter such as stopwords affect the accuracy of the assessment. The developed automatic essay grading system was able to obtain the highest accuracy rate of 89% by using input in the form of romaji letters and without the stopwords elimination process.