The increased use of social media among digitally anonymous users, sharing their thoughts and opinions, can facilitate participation and collaboration. However, this anonymity feature which gives users freedom of speech and allows them to conduct activities without being judged by others can also encourage cyberbullying and hate speech. Predators can hide their identity and reach a wide range of audience anytime and anywhere. According to the detrimental effect of cyberbullying, there is a growing need for cyberbullying detection approaches. In this survey paper, a comparative analysis of the automated cyberbullying techniques from different perspectives is discussed including data annotation, data preprocessing, and feature engineering. In addition, the importance of emojis in expressing emotions as well as their influence on sentiment classification and text comprehension leads us to discuss the role of incorporating emojis in the process of cyberbullying detection and their influence on the detection performance. Furthermore, the different domains for using self-supervised learning (SSL) as an annotation technique for cyberbullying detection are explored.

The phenomenal growth and subsequent increasing use of Information and Communication Technology (ICT) innovations has led to an increase in their use in higher education over the past decade. Past research has criticised e-learning (compared to traditional face-to-face lecturing) for its failure to engage students in their learning. However, King Abdulaziz University (KAU) has only limited seats available for its traditional face-to-face programmes and therefore was determined to provide a viable alternative in the form of an e-learning programme, the first in Saudi Arabia. One of the requirements of this programme was that it should fit current sociocultural customs, enabling students from the K-12 Saudi educational system who are not skilled in independent learning or discovery to construct their own knowledge. The university created a programme that underwent rigorous course development and quality control to engage students more actively through asynchronous technologies — virtual classrooms for every face-to-face hour of every course — with synchronous components, using a learning management system developed in-house to integrate with all other university systems. The virtual classrooms enable students and instructors to communicate synchronously using audio, video, interactive whiteboard, application sharing, instant polling, text chat, and other features as though they were standing face to face in a regular classroom. All instructor activities and interactions with students are monitored within the LMS and virtual classroom. Instructors and departments are provided with detailed reports on instructor performance and continuous assessments of their interactions with students. Due to their distinct methods of delivery, it is difficult to make exact comparisons between face-to-face and e-learning models of learning; to allow for the most accurate comparisons, the performance of students in face-to-face courses was compared to that of students in scheduled virtual classrooms who were taught by the same instructors. The overall results show that for most courses, there were no significant differences in the performance of online and face-to-face students assigned to the same course and taught by the same instructor.

The objective of this research was to recognize the hand gestures of Arabic Sign Language (ArSL) words using two depth sensors. The researchers developed a model to examine 143 signs gestured by 10 users for 5 ArSL words (the dataset). The sensors captured depth images of the upper human body, from which 235 angles (features) were extracted for each joint and between each pair of bones. The dataset was divided into a training set (109 observations) and a testing set (34 observations). The support vector machine (SVM) classifier was set using different parameters on the gestured words’ dataset to produce four SVM models, with linear kernel (SVMLD and SVMLT) and radial kernel (SVMRD and SVMRT) functions. The overall identification accuracy for the corresponding words in the training set for the SVMLD, SVMLT, SVMRD, and SVMRT models was 88.92%, 88.92%, 90.88%, and 90.884%, respectively. The accuracy from the testing set for SVMLD, SVMLT, SVMRD, and SVMRT was 97.059%, 97.059%, 94.118%, and 97.059%, respectively. Therefore, since the two kernels in the models were close in performance, it is far more efficient to use the less complex model (linear kernel) set with a default parameter.

E-commerce web content is dynamic and diverse, necessitating continuous monitoring and adaptation. This presents researchers with the challenge of discovering methods to improve delivered services. Hence, integrating natural language processing (NLP), Machine Learning (ML), Deep Learning (DL), and sentiment analysis (SA) provides businesses with robust frameworks to utilize customer feedback and enhance decision-making. Therefore, we introduce a novel dataset collection methodology that captures the dynamic relationships between e-commerce web content and consumer sentiment. Additionally, we introduce a novel, real-consumer-based quality metric on product content through FG-CSrP, extending SA into a new Fine-Grained Consumer Sentiment related to the Product. We evaluated our dataset using baseline models: Deep Neural Network (DNN), Long Short-Term Memory (LSTM), DistilBERT, and twelve automatically optimized models created by AutoGluon-Tabular across three scenarios, each with varying feature inputs (numerical, textual, and both). We then applied Explainable Artificial Intelligence (XAI) to the DNN model to explain feature importance in prediction. Our findings showed that LightGBMXT outperformed the other models in two out of three scenarios, and XAI interpretations highlighted the significant role of vendor-provided web content details in consumer sentiment. Overall, our approach provides actionable insights that can help vendors improve e-commerce strategies and strengthen customer engagement.

The increasing reliance on e-commerce services has generated extensive product-related information and customer opinions, enabling analysis of product-page evolution and consumer sentiment. However, repeated product-page observations do not directly represent temporal changes without extracting differences between snapshots. This study proposes a difference-based dynamic feature extraction methodology using time-normalized numerical differences and TF-IDF cosine distance. The extracted features were integrated with original product-related features and evaluated using tuned LightGBM to predict the dominant Fine-Grained Consumer Sentiment related to the Product (FG-CSrP) class at later observations of previously observed products. Performance was assessed through expanding temporal validation windows and an independent temporal holdout. LightGBM gain-based and group-level permutation importance were further used to examine feature contributions. On the final holdout, Baseline and Original + Dynamic settings achieved Macro-F1 scores of 0.8710 and 0.8616, respectively, showing no clear improvement from dynamic features. Additional benchmark and robustness analyses highlighted temporal stability, limited generalization to unseen products, and superior Macro-F1 performance of LightGBM compared with regularized logistic regression. LightGBM gain-based and group-level permutation importance analyses showed that original product-related features contributed most to the predictive performance. Overall, difference-based features explicitly represent changes in evolving e-commerce content, although these features did not demonstrate additional predictive gains.