Claim Missing Document
Check
Articles

Found 3 Documents
Search

Flagging clickbait in Indonesian online news websites using fine-tuned transformers Muhammad Noor Fakhruzzaman; Sa'idah Zahrotul Jannah; Ratih Ardiati Ningrum; Indah Fahmiyah
International Journal of Electrical and Computer Engineering (IJECE) Vol 13, No 3: June 2023
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v13i3.pp2921-2930

Abstract

Click counts are related to the amount of money that online advertisers paid to news sites. Such business models forced some news sites to employ a dirty trick of click-baiting, i.e., using hyperbolic and interesting words, sometimes unfinished sentences in a headline to purposefully tease the readers. Some Indonesian online news sites also joined the party of clickbait, which indirectly degrade other established news sites' credibility. A neural network with a pre-trained language model multilingual bidirectional encoder representations from transformers (BERT) that acted as an embedding layer is then combined with a 100 node-hidden layer and topped with a sigmoid classifier was trained to detect clickbait headlines. With a total of 6,632 headlines as a training dataset, the classifier performed remarkably well. Evaluated with 5-fold cross-validation, it has an accuracy score of 0.914, an F1-score of 0.914, a precision score of 0.916, and a receiver operating characteristic-area under curve (ROC-AUC) of 0.92. The usage of multilingual BERT in the Indonesian text classification task was tested and is possible to be enhanced further. Future possibilities, societal impact, and limitations of clickbait detection are discussed.
IndoPolicyStats: sentiment analyzer for public policy issues Fakhruzzaman, Muhammad Noor; Jannah, Sa'idah Zahrotul; Gunawan, Sie Wildan; Pratama, Angga Iryanto; Ardanty, Denise Arne
Bulletin of Electrical Engineering and Informatics Vol 13, No 1: February 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v13i1.5263

Abstract

The government requires some vaccination for public health. This has led to a debate in recent years, especially during the Covid-19 pandemic. This research aims to analyze the two sentiments of the public regarding the vaccination policy. This would be helpful to ensure the acceptance of the government campaign about vaccination. The data used was text data obtained from Twitter when Indonesia was facing the second wave of the Covid-19 pandemic. The data were pre-processed by removing noise data, case folding, stemming, and tokenizing. Then, the data were classified with random forest, Naïve Bayes, and XGBoost. The results showed that all classifiers exhibit satisfying performance but XGBoost performs slightly better in accuracy value. This method can be deployed to be an automatic sentiment analyzer to help the government understand public feedback about its policies. This would be given by proper pre-processing and enough datasets.
MODELING HOUSE SELLING PRICES IN JAKARTA AND SOUTH TANGERANG USING MACHINE LEARNING PREDICTION ANALYSIS Maula, Sugha Faiz Al; Setiawan, Nicoletta Almira Dyah; Pusporani, Elly; Jannah, Sa'idah Zahrotul
BAREKENG: Jurnal Ilmu Matematika dan Terapan Vol 19 No 1 (2025): BAREKENG: Journal of Mathematics and Its Application
Publisher : PATTIMURA UNIVERSITY

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/barekengvol19iss1pp107-118

Abstract

The increasing demand for housing in urban agglomerations, particularly in areas like Jakarta, has made homeownership a significant challenge for many, especially first-time buyers and the lower-middle class. Post-pandemic shifts have further influenced housing preferences, driving interest towards suburban areas with green spaces. Despite government efforts through mortgage subsidy programs, affordability remains a concern, particularly in peripheral regions. This study aims to analyze housing prices in various Jakarta regions using machine learning models, including Multiple Linear Regression (MLR), Support Vector Regression (SVR), Light Gradient Boosting Machine (LGBM), and Random Forest. A dataset of 554 house prices from West Jakarta, South Jakarta, Central Jakarta, and South Tangerang was used. The analysis focused on key predictors like land area, building area, bedrooms, and carports, with R² and Mean Squared Error (MSE) metrics evaluating model performance. Results showed that LGBM and Random Forest outperformed others with 0.8 R2 and low MSE, with building and land area as the most significant factors influencing prices. The study concludes that property size is a primary determinant of house prices, and there is a need for policy interventions to make housing more affordable. Additionally, apartment rentals offer a viable alternative, especially in central urban areas, where proximity to economic activities and facilities is crucial. The findings suggest that enhancing marketplace features with predictive tools could further assist buyers in making informed decisions.