Improving classifier training efficiency for automatic cyberbullying detection with Feature Density

Identification of cyber harassment and intention of target users on social media platforms

Due to Coronavirus diseases in 2020, all the countries departed into lockdown to combat the spread of the pandemic situation. Schools and institutions remain closed and students' screen time surged. The classes for the students are moved to the digital platform which leads to an increase in social media usage. Many children had become sufferers of cyber harassment which includes threatening comments on young students, sexual torture through a digital platform, people insulting one another, and the use of fake accounts to harass others. The rising effort on automated cyber harassment detection utilizes many AI-related components Natural language processing techniques and machine learning approaches. Though machine learning models using different algorithms fail to converge with higher accuracy, it is much more important to use significant natural language processes and efficient classifiers to detect cyberbullying comments on social media. In this proposed work, the lexical meaning of the text is analysed by the conventional scheme and the word order of the text is performed by the Fast Text model to improve the computational efficacy of the model. The intention of the text is analysed by various feature extraction methods. The score for intention detection is calculated using the frequency of words with a bully-victim participation score. Finally, the proposed model's performance is measured by different evaluation metrics which illustrate that the accuracy of the model is higher than many other existing classification methods. The error rate is lesser for the detection model.

Correlational study on cyberbullying and social abilities in intercultural teenagers

This article analyzes the relationship between cyberbullying profile by racist reasons and social abilities in a group of intercultural teenagers living in Spain (N = 1478). The study includes participants aged between 12 and 16 years old (M = 13.99; SD = 1.352). Of these, 738 were male (49.9%) and 740 were female (50.1%). A correlational study was carried out using online tools with suitable psychometrics parameters (content-construct validity and reliability). The first one was a scale that measured social abilities, and the second one evaluated racist or xenophobic cyberbullying, differentiating the victim and aggressor profiles. The results indicated five main findings: (1) generally, the participants analyzed present all their social abilities; (2) for the most part, these participants do not normally experience cyberbullying; (3) a positive correlation exists between the majority of social abilities analyzed and the cybervictim profile. It was also observed a negative correlation between the social ability associated with the ability of making requests and this profile; (4) there is a positive correlation among the six social abilities analyzed and the cyberaggressor profile; (5) the racist or xenophobic cyberbullying are driven not only by the absence of social abilities, but in some cases, they are also driven by socio-demographic variables (i.e., age and gender). Likewise, this work shows how the absence of some social abilities in some participants involve racist or xenophobic experiences as victims and as aggressors, which may be of interest for the analysis of teenagers' behavior in intercultural contexts, as well as according to age and gender. More transcultural research need to be carried out to know the global perspective of the link between social abilities and the different profiles of racist and xenophobic cyberbullying, framed in the context of social psychology and studies of mass communication.

The design, construction and evaluation of annotated Arabic cyberbullying corpus

Cyberbullying (CB) is classified as one of the severe misconducts on social media. Many CB detection systems have been developed for many natural languages to face this phenomenon. However, Arabic is one of the under-resourced languages suffering from the lack of quality datasets in many computational research areas. This paper discusses the design, construction, and evaluation of a multi-dialect, annotated Arabic Cyberbullying Corpus (ArCybC), a valuable resource for Arabic CB detection and motivation for future research directions in Arabic Natural Language Processing (NLP). The study describes the phases of ArCybC compilation. By way of illustration, it explores the corpus to discover strategies used in rendering Arabic CB tweets pulled from four Twitter groups, including gaming, sports, news, and celebrities. Based on thorough analysis, we discovered that these groups were the most susceptible to harassment and cyberbullying. The collected tweets were filtered based on a compiled harassment lexicon, which contains a list of multi-dialectical profane words in Arabic compiled from four categories: sexual, racial, physical appearance, and intelligence. To annotate ArCybC, we asked five annotators to classify 4,505 tweets into two classes manually: Offensive/non-Offensive and CB/non-CB. We conducted a rigorous comparison of different machine learning approaches applied on ArCybC to detect Arabic CB using two language models: bag-of-words (BoW) and word embedding. The experiments showed that Support Vector Machine (SVM) with word embedding achieved an accuracy rate of 86.3% and an F1-score rate of 85%. The main challenges encountered during the ArCybC construction were the scarcity of freely available Arabic CB texts and the deficiency of annotating the texts.