The increasing use of social media not only provides various benefits but also contributes to the spread of cyberbullying. Detecting cyberbullying on social media is challenging because users frequently communicate in Indonesian, English, or a combination of both languages. In addition, previous studies have generally focused on detecting cyberbullying in a single language, limiting their ability to accommodate the characteristics of bilingual text. This limitation may lead to failures in detecting cyberbullying comments accurately and promptly, potentially causing psychological harm to victims. Therefore, an automated detection system capable of understanding the characteristics of bilingual text is needed. This study aims to develop a BiLSTM model for detecting cyberbullying in Indonesian and English texts. A bilingual dataset consisting of 21,308 Indonesian and English text samples was used to train the BiLSTM model. The experimental results show that the choice of optimizer affects model performance, with RMSProp outperforming Adam and SGD, achieving an accuracy of 96.01%, a precision of 96.03%, a recall of 96.01%, and an F1-score of 96.01%. These results demonstrate that the BiLSTM model with the RMSProp optimizer is effective for detecting cyberbullying in bilingual Indonesian and English texts.
Bitcoin is a highly liquid yet volatile crypto asset, making reliable next-day price forecasting challenging. This study develops a Support Vector Regression (SVR) model for predicting the next-day Bitcoin closing price and compares Grid Search tuning with the Whale Optimization Algorithm (WOA) using weighted Time Series Cross-Validation. The dataset comprised 2,620 daily observations from 10 March 2019 to 11 May 2026. Because the final row had no next-day target, it was excluded from scaling, validation, and model selection and retained only for one-step forecasting, leaving 2,619 modelled observations. An 80:20 chronological split produced 2,095 training observations and 524 independent test samples. Grid Search identified C=100, gamma=0.01, and epsilon=0.001 in 8.54 seconds, whereas warm-started WOA identified C=74.21, gamma=0.0075, and epsilon=0.0004 in 220.48 seconds. On the test set, SVR-WOA numerically reduced MAE from USD 1,612.09 to USD 1,551.35, RMSE from USD 2,161.85 to USD 2,112.09, and MAPE from 1.72% to 1.67%, while R² increased from 0.9803 to 0.9812. These differences correspond to improvements of 3.77%, 2.30%, and 3.05%, respectively, but WOA required approximately 25.8 times longer optimization. Because WOA was executed once and evaluated on a single chronological test split, the observed gains should be interpreted as numerical improvements rather than statistically established superiority. The findings therefore demonstrate a trade-off between slightly lower test errors and substantially greater optimization cost.
Wahyudi Wahyudi, Rizky Parlika, Yisti Vita Via· bit-Tech· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
