Analisa Kinerja Chatgpt Dalam Menghasilkan Teks Bahasa Indonesia Menggunakan Metode Support Vector Machines (SVM)

The development of natural language processing technology has opened opportunities for creating language models such as ChatGPT, which can generate text in various languages, including Indonesian. This study focuses on evaluating the performance of ChatGPT in generating Indonesian-language text using the Support Vector Machines (SVM) approach. The dataset used consists of [number of data entries] text entries across various categories, namely "Semantic," "Syntactic," and "Not Similar." The data undergoes several preprocessing stages, including tokenization, normalization, stopword removal, and stemming, before further analysis. The findings reveal that the implementation of the SVM model on text generated by ChatGPT demonstrates good performance, with high precision, recall, and F1-scores across all categories. For the "Semantic" category, the model achieved a precision of 0.89, recall of 0.91, and an F1-score of 0.90. In the "Syntactic" category, precision was 0.85, recall was 0.83, and the F1-score was 0.84. For the "Not Similar" category, the model achieved a precision of 0.91, recall of 0.92, and an F1-score of 0.91. This research makes a significant contribution to the development and understanding of natural language processing technology, particularly in the context of the Indonesian language. However, several limitations were identified, such as the relatively small dataset size and the preprocessing methods, which could be further enhanced. Future research is recommended to use larger datasets and apply alternative machine learning techniques to improve the model's performance. Keywords: ChatGPT, Natural Language Processing, Support Vector Machines, Indonesian Language, Text Analysis.