Cyberbullying on social media platforms, particularly X (formerly Twitter), has become a serious issue that negatively affects users' mental health and well-being. Automatic cyberbullying detection in Indonesian remains challenging due to the widespread use of informal language, slang, abbreviations, and highly imbalanced class distributions. This study proposes a hybrid deep learning model that integrates IndoBERTweet with a Bidirectional Gated Recurrent Unit (BiGRU) to improve cyberbullying detection performance on Indonesian tweets. A dataset of Indonesian tweets was collected from X and annotated using a multi-stage dual large language model (LLM) labeling strategy to reduce the time and effort required for manual annotation while maintaining label consistency. To address class imbalance, this study investigates the effectiveness of Focal Loss and label distribution modification through multiple experimental scenarios. The proposed approach was evaluated using accuracy, precision, recall, and F1-score. The best performance was achieved by combining Focal Loss with a modified four-class label configuration consisting of Rude and Vulgar Words, Sexual Harassment, Body Shaming and Hate Speech, and Non-Cyberbullying. This configuration obtained an accuracy of 0.93, precision of 0.90, recall of 0.90, and F1-score of 0.90. These findings demonstrate that integrating contextual language representations with sequential modeling, supported by an efficient LLM-assisted labeling strategy and class imbalance handling, provides an effective approach for Indonesian cyberbullying detection and offers a practical solution for large-scale social media content moderation.
F. Nafiah, Aviolla Terza Damaliana, K. M. Hindrayani· JOURNAL OF APPLIED INFORMATI...· 0 citations
Forecasting the number of train passengers is an important component in transportation system management to support operational planning and decision-making. Kediri Station, as a regional transit hub, exhibits highly dynamic daily passenger patterns with frequent fluctuations. The passenger time series data from this station shows occasional extreme spikes, particularly during holidays, long weekends, and promotional periods. These spikes can be characterized as Additive Outliers (AO), which may distort the underlying data structure and reduce the reliability of forecasting models if not properly addressed. This study aims to improve short-term forecasting accuracy of daily train passengers at Kediri Station by applying the Seasonal Autoregressive Integrated Moving Average (SARIMA) model with Additive Outlier (AO) handling. The analysis uses secondary daily passenger data from January 2024 to September 2025. AO effects are incorporated into the SARIMA framework to reduce bias caused by extreme observations. The results show that the SARIMA-AO model yields improved forecasting performance compared to the standard SARIMA model. The SARIMA-AO model achieves a Mean Squared Error (MSE) of 30,913 and a Mean Absolute Percentage Error (MAPE) of 13%, while the standard SARIMA model produces an MSE of 33,965 and a MAPE of 14%. Although the improvement is relatively modest, the results indicate that explicit handling of additive outliers can enhance forecast accuracy for daily passenger demand at Kediri Station. This approach provides preliminary evidence that AO-aware SARIMA modeling may be useful for supporting short-term operational planning in railway services.
K. M. Hindrayani, Nabila Lintang Ardani, Shindi Shella May Wara· bit-Tech· 0 citations
Aircraft accident investigation reports contain important information regarding the chronology of events, findings, contributing factors, and safety recommendations that can be used to understand accident patterns. However, this information is generally presented in the form of unstructured text, making manual analysis less efficient. This research aims to apply BERTopic to identify latent themes in aviation accident investigation reports published by the National Transportation Safety Committee (KNKT). A total of 182 investigation reports classified as Final Reports were processed through text extraction, corpus formation, and preprocessing, resulting in 172 documents used for topic modelling. BERTopic was implemented using sentence embedding, UMAP dimensionality reduction, HDBSCAN clustering, and c-TF-IDF-based topic representation. The modelling results yielded ten main topics reflecting various aspects of aviation safety, including technical, operational, and human factors. Evaluation showed that BERTopic achieved a topic coherence (Cv) value of 0.6111 and generated more specific keywords compared to Latent Dirichlet Allocation (LDA). The research results indicate that BERTopic is capable of effectively extracting latent themes from KNKT investigation reports and has the potential to support the analysis of aviation accident patterns and serve as a foundation for the development of domain knowledge-based research in the field of aviation safety.
Adelia Ramadhina Azzahra, K. M. Hindrayani, Andri Fauzan Adziima· ICEETE Conference Series· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
