Volume 5 Issue 3: September 2026 (In Progress)

The social networking sites have transformed digital communication but have simultaneously enabled the escalation of harmful online behaviors, particularly cyberbullying. This recurring form of digital aggression can lead to serious emotional and psychological harm, including anxiety, depression, and in severe cases, self-inflicted injury or suicidal behavior. The timely identification and prevention of cyberbullying have become an essential focus of current research. Although numerous machine learning techniques have been applied to detect abusive content, many continue to face challenges such as inefficient kernel tuning, extended training durations, and reduced predictive accuracy. To address these limitations, this study presents a hybrid deep learning architecture that integrates a Bidirectional Long Short-Term Memory (BiLSTM) network with the Extreme Gradient Boosting (XGBoost) algorithm to improve contextual awareness and classification accuracy. The proposed framework was trained and evaluated on datasets collected from Facebook and X (formerly Twitter), capturing diverse linguistic and behavioral characteristics of user interactions. Experimental results indicate that the BiLSTM–XGBoost hybrid model outperforms conventional classifiers by effectively managing context representation, adaptive learning, and class imbalance. The model achieved 97% accuracy, 95% precision, 92% recall, and an F1-score of 96%, confirming its robustness and efficiency for cyberbullying detection in dynamic social media environments. The study helps educational institutions, online platforms and legal frameworks provide insights into how to better identify cyberbullying in real-world scenarios. The study’s high recall ensures that cyberbullies are easily identified and it enhances the understanding of how combining multiple models can lead to better performance in cyberbullying detection.

• View PDF

This study uses bibliometric analysis of journal papers published between 2001 and 2025 to investigate the state of the research on technology-related foreign language anxiety (FLA). 224 articles that were indexed in the Scopus database were included in the data. This study used the Bibliometrix package in R to examine publishing patterns, top journals, authors, and institutions, records of international collaboration, and the thematic structure of the field using bibliometric performance indicators and scientific mapping approaches. The findings indicate a consistent and incredibly rapid rise in publications during the past ten years. The majority of the research field's progress is published by a small number of writers and institutions in a limited number of journals. Although China now accounts for the majority of articles geographically, extensive international collaborative networks are still limited and in the early stages of development. Research focus has clearly changed throughout time, as seen by thematic and keyword analysis. While computer-assisted language learning and technology-enhanced learning environments have historically been the focus of education technology research, more recent literature shows a growing interest in artificial intelligence, immersive technologies, and data-informed digital learning contexts. Foreign language anxiety is the subject of an increasing amount of study, which typically places it in positive psychological contexts and focuses on its relationship to motivation, self-efficacy, and communication willingness. These findings will help better understand the origins of technology FLA research and how it is evolving. They can also provide references for upcoming investigations into the potential effects of digital technologies on language learners' emotions.

• View PDF