ANALISIS SENTIMEN MASYARAKAT TENTANG BANK SYARIAH DI PLATFORM X MENGGUNAKAN ALGORITMA MACHINE LEARNING

The advancement of digital technology has encouraged people to actively express their
opinions through social media, including in response to Islamic banking services. This study
aims to analyze public sentiment toward Islamic banks on platform X (formerly Twitter) using
a machine learning approach. The dataset consists of 1,843 tweets collected through a crawling
technique using the keyword "bank syariah" from 2019 to 2024. Sentiments are classified into
four categories: positive, negative, neutral, and others.
This study compares the performance of five classification algorithms, namely Support
Vector Machine (SVM), Naïve Bayes, Logistic Regression, Random Forest, and Long Short
Term Memory (LSTM). Prior to model training, the data underwent preprocessing steps
including cleansing, tokenization, stopword removal, and stemming. Text features were
extracted using the TF-IDF and Bag-of-Words (BoW) methods, while word embedding was
used for the LSTM model. Data balancing was performed using the Synthetic Minority Over
sampling Technique (SMOTE) to address class imbalance.
Model evaluation was conducted using accuracy, precision, recall, and F1-score
metrics. The results show that the SVM algorithm with the RBF kernel achieved the best
performance in classifying public sentiment toward Islamic banks. The application of SMOTE
also proved effective in improving model performance for minority classes. These findings are
expected to contribute to a deeper understanding of public perception and serve as a reference
for developing sentiment analysis systems in the Islamic banking sector.