Cyberbullying (CB) has become increasingly prevalent in social media platforms. With the popularity and widespread use of social media by individuals of all ages, it is vital to make social media platforms safer from cyberbullying. This paper presents a hybrid deep learning model, called DEA-RNN, to detect CB on Twitter social media network. The proposed DEA-RNN model combines Elman type Recurrent Neural Networks (RNN) with an optimized Dolphin Echolocation Algorithm (DEA) for fine-tuning the Elman RNN’s parameters and reducing training time. We evaluated DEA-RNN thoroughly utilizing a dataset of 10000 tweets and compared its performance to those of state-of-the-art algorithms such as Bi-directional long short term memory (Bi-LSTM), RNN, SVM, Multinomial Naive Bayes (MNB), Random Forests (RF). The experimental results show that DEA-RNN was found to be superior in all the scenarios. It outperformed the considered existing approaches in detecting CB on Twitter platform. DEA-RNN was more efficient in scenario 3, where it has achieved an average of 90.45% accuracy, 89.52% precision, 88.98% recall, 89.25% F1-score, and 90.94% specificity.

With the emergence of microblogging platforms and social media applications, large amounts of user-generated data in the form of comments, reviews, and brief text messages are produced every day. Microblog data is typically of poor quality; hence improving the quality of the data is a significant scientific and practical challenge. In spite of the relevance of the problem, there has been not much work so far, especially in regard to microblog data quality for Short-Text Topic Modelling (STTM) purposes. This paper addresses this problem and proposes an approach called the social media data cleansing model (SMDCM) to improve data quality for STTM. We evaluate SMDCM using six topic modelling methods, namely the Latent Dirichlet Allocation (LDA), Word-Network Topic Model (WNTM), Pseudo-document-based Topic Modelling (PTM), Biterm Topic Model (BTM), Global and Local word embedding-based Topic Modeling (GLTM), and Fuzzy Topic modelling (FTM). We used the Real-world Cyberbullying Twitter (RW-CB-Twitter) and the Cyberbullying Mendeley (CB-MNDLY) datasets in the evaluation. The results proved the efficiency of the GLTM and WNTM over the other STTM models when applying the SMDCM techniques, which achieved optimum topic coherence and high accuracy values on RW-CB-Twitter and CB-MNDLY datasets.

This paper conducts a comprehensive review of various word and sentence semantic similarity techniques proposed in the literature. Corpus-based, Knowledge-based, and Feature-based are categorized under word semantic similarity techniques. String and set-based, Word Order-based Similarity, POSbased, Syntactic dependency-based are categorized as sentence semantic similarity techniques. Using these techniques, we propose a model for computing the overall accuracy of the twitter dataset. The proposed model has been tested on the following four measures: Atish’s measure, Li’s measure, Mihalcea’s measure with path similarity, and Mihalcea’s measure with Wu and Palmer’s (WuP) similarity. Finally, we evaluate the proposed method on three real-world twitter datasets. The proposed model based on Atish’s measure seems to offer good results in all datasets when compared with the proposed model based on other sentence similarity measures.