An Automated Toxicity Classification on Social Media Using LSTM and Word Embedding.

The automated identification of toxicity in texts is a crucial area in text analysis since the social media world is replete with unfiltered content that ranges from mildly abusive to downright hateful. Researchers have found an unintended bias and unfairness caused by training datasets, which caused an inaccurate classification of toxic words in context. In this paper, several approaches for locating toxicity in texts are assessed and presented aiming to enhance the overall quality of text classification. General unsupervised methods were used depending on the state-of-art models and external embeddings to improve the accuracy while relieving bias and enhancing F1-score. Suggested approaches used a combination of long short-term memory (LSTM) deep learning model with Glove word embeddings and LSTM with word embeddings generated by the Bidirectional Encoder Representations from Transformers (BERT), respectively. These models were trained and tested on large secondary qualitative data containing a large number of comments classified as toxic or not. Results found that acceptable accuracy of 94% and an F1-score of 0.89 were achieved using LSTM with BERT word embeddings in the binary classification of comments (toxic and nontoxic). A combination of LSTM and BERT performed better than both LSTM unaccompanied and LSTM with Glove word embedding. This paper tries to solve the problem of classifying comments with high accuracy by pertaining models with larger corpora of text (high-quality word embedding) rather than the training data solely.

Cognitive IoT-Based e-Learning System: Enabling Context-Aware Remote Schooling during the Pandemic.

The 2019-2020 coronavirus pandemic had far-reaching consequences beyond the spread of the disease and efforts to cure it. Today, it is obvious that the pandemic devastated key sectors ranging from health to economy, culture, and education. As far as education is concerned, one direct result of the spread of the pandemic was the resort to suspending traditional in-person classroom courses and relying on remote learning and homeschooling instead, by exploiting e-learning technologies, but many challenges are faced by these technologies. Most of these challenges are centered around the efficiency of these delivery methods, interactivity, and knowledge testing. These issues raise the need to develop an advanced smart educational system that assists home-schooled students, provides teachers with a range of smart new tools, and enable a dynamic and interactive e-learning experience. Technologies like the Internet of things (IoT) and artificial intelligence (AI), including cognitive models and context-awareness, can be a driving force in the future of e-learning, opening many opportunities to overcome the limitation of the existing remote learning systems and provide an efficient reliable augmented learning experience. Furthermore, virtual reality (VR) and augmented reality (AR), introduced in education as a way for asynchronous learning, can be a second driving force of future synchronous learning. The teacher and students can see each other in a virtual class even if they are geographically spread in a city, a country, or the globe. The main goal of this work is to design and provide a model supporting intelligent teaching assisting and engaging e-learning activity. This paper presents a new model, ViRICTA, an intelligent system, proposing an end-to-end solution with a stack technology integrating the Internet of things and artificial intelligence. The designed system aims to enable a valuable learning experience, providing an efficient, interactive, and proactive context-aware learning smart services.