Claim Missing Document
Check
Articles

Found 2 Documents
Search

Application of the Finite State Automata (FSA) Method in Indonesian Stemming using the Nazief & Adriani Algorithm fitriana, lady agustin; Mustopa, Ali; Firdaus, Muhammad Rifqi; Dahlia, Rizka
Sistemasi: Jurnal Sistem Informasi Vol 13, No 3 (2024): Sistemasi: Jurnal Sistem Informasi
Publisher : Program Studi Sistem Informasi Fakultas Teknik dan Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v13i3.4038

Abstract

Language is a communication tool commonly used in everyday life. Each country has a different language with predetermined rules. For instance, in the Indonesian language, there are approximately 35 official affixes mentioned in the Big Indonesian Dictionary. These affixes include prefixes (prefixes), infixes (insertions), suffixes (suffixes), and confixes (a combination of prefixes and suffixes). In Information Retrieval, there is a stemming process, which is the process of converting a word form into a base word or the process of transforming variant words into their base form. The theory of language and automata is the foundation of the computer science field that provides the basis for ideas and models of computer systems. In the implementation of the research, several stages were carried out, such as explaining the Nazief & Adriani stemming algorithm, finite state automata, creating pseudocode, and testing using a web-based system, resulting in affixed words becoming the correct base words with 20 affixed words. The results obtained from reading this web-based system, the base word "cinta" (love) used as a test yielded accurate results in accordance with the concept of the Nazief & Adriani stemming algorithm. There are some weaknesses in stemming from suffixes, and the solution is to perform stemming from the prefix position (Prefix).
Penerapan Machine Learning untuk Analisis Sentimen Agoda dengan Algoritma KNN, Naive Bayes, dan SVM Rindiani, Popi; Fatmawati, Jeni; Wira Hadi, Sofian; Fazriansyah, Agung; Fitriana, Lady Agustin
Jurnal Manajemen Informatika, Sistem Informasi dan Teknologi Komputer (JUMISTIK) Vol 4 No 2 (2025): Jurnal Manajemen Informatika, Sistem Informasi dan Teknologi Komputer (JUMISTIK)
Publisher : STMIK Amika Soppeng

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70247/jumistik.v4i2.232

Abstract

The rapid advancement of digital technology has significantly transformed the tourism industry, particularly in online hotel booking services such as Agoda. The large volume of user reviews available on this platform serves as a valuable data source for analyzing customer satisfaction and perceptions. This study aims to conduct sentiment analysis on 5,000 Indonesian-language user reviews from the Agoda mobile application by comparing the performance of three machine learning algorithms: K-Nearest Neighbors (KNN), Naïve Bayes, and Support Vector Machine (SVM). Data were collected using a web scraping technique from Google Play Store and processed through several preprocessing stages, including cleaning, case folding, tokenization, word normalization, stopword removal, and stemming. Text representation was performed using the CountVectorizer method, with an 80:20 ratio of training and testing datasets. The experimental results show that the SVM algorithm achieved the highest performance with an accuracy of 84.1%, outperforming Naïve Bayes (65.3%) and KNN (61.7%). These findings indicate that SVM demonstrates superior capability in classifying positive, negative, and neutral sentiments in Indonesian text. The results of this research are expected to contribute to the development of sentiment analysis models and support service quality improvement based on user feedback.