Classification of Indonesian Tale Categories using Support Vector Machine and FastText Feature Extraction

Abstract

The purpose of this work is to develop a model to classify the various kinds of Indonesian folktales and to assess how well the support vector machine (SVM) approach and fastText feature extraction perform. The first phase of the study process is the gathering of data, namely the fairy tale dataset that has been annotated with categorizations for each genre of fairy tale. Following the collection of data, the pre-processing step is conducted. The purpose of the pre-processing step is to prepare the data for further processing in the subsequent stage. Following the completion of the preprocessing step, the training data and testing data are segregated. The subsequent step involves doing feature extraction using fastText. Moreover, the classification process is conducted using the Support Vector Machine (SVM) approach in order to get the ultimate outcome of the modeling process. The last phase involves assessing the performance of the constructed model. The categorization model for Indonesian fairy tales has a commendable accuracy rate of 85%, indicating its effectiveness. The aforementioned findings are substantiated by an accuracy metric of 85%, a recall metric of 85%, and an F1-score of 86%, indicating favorable outcomes.
Previous researchs have not conducted any studies on the categorization of types of Indonesian fairy tales.