Deep Learning Approaches for Cyberbullying Detection and Classification on Social Media

Abstract

As a result of the ease with which the internet and cell phones can be accessed, online social networks (OSN) and social media have seen a significant increase in popularity in recent years. Security and privacy, on the other hand, are the key concerns in online social networks and other social media platforms. On the other hand, cyberbullying (CB) is a serious problem that needs to be addressed on social media platforms. Known as cyberbullying (CB), it is defined as a repetitive, purposeful, and aggressive reaction performed by individuals through the use of information and communication technology (ICT) platforms such as social media platforms, the internet, and cell phones. It is made up of hate messages that are sent by e-mail, chat rooms, and social media platforms, which are accessed through computers and mobile phones. The detection and categorization of CB using deep learning (DL) models in social networks are, therefore, crucial in order to combat this trend. Feature subset selection with deep learning-based CB detection and categorization (FSSDL-CBDC) is a novel approach for social networks that combines deep learning with feature subset selection. The suggested FSSDL-CBDC technique consists of a number of phases, including preprocessing, feature selection, and classification, among others. Additionally, a binary coyote optimization (BCO)-based feature subset selection (BCO-FSS) technique is employed to select a subset of features that will increase classification performance by using the BCO algorithm. Additionally, the salp swarm algorithm (SSA) is used in conjunction with a deep belief network (DBN), which is known to as the SSA-DBN model, to detect and characterize cyberbullying in social media networks and other online environments. The development of the BCO-FSS and SSA-DBN models for the detection and classification of cyberbullying highlights the originality of the research. A large number of simulations were carried out to illustrate the superior classification performance of the proposed FSSDL-CBDC technique. The SSA-DBN model has exhibited superior accuracy to the other algorithms, with a 99.983 % accuracy rate. Overall, the experimental results revealed that the FSSDL-CBDC technique beats the other strategies in a number of different aspects.

Improved African Buffalo Optimization-Based Energy Efficient Clustering Wireless Sensor Networks using Metaheuristic Routing Technique

“…In this section, a wide-ranging comparison study of the model is carried out under varying numbers of sensor nodes (SNs). Table 1 provides detailed results of the MHCRT-EEWSN model with existing models in terms of end-to-end delay (ETED), packet delivery ratio (PDR), and packet loss rate (PLR) [21][22][23][24][25]. SNs, the MHCRT-EEWSN model has attained effectual outcomes with minimal ETED of 1.36ms whereas the LEACH, HEED, MBC, FRLDG, and F-GWO models have obtained maximum ETED of 6.15ms, 5.18ms, 4.09ms, 3.39ms, and 2.14ms respectively.…”

An explainable deep learning model for prediction of early‐stage chronic kidney disease

“…Local surrogate models are interpretable models. Individual predictions of black box machine learning algorithms are explained using local surrogate models 35,36 . LIME, or local interpretable model‐agnostic explanations, explains the predictions of any classifier or regressor locally with an interpretable model.…”

“…Individual predictions of black box machine learning algorithms are explained using local surrogate models. 35,36 The training data, single test instance, and DNN-CKD predictions are fed as input to the explainable technique. LIME tweaks the feature values in a single CKD data sample to see how they affect the results.…”

Balanced Iterative Reduction and Clustering Using Hierarchies (BIRCH) methods to Prioritize and reduce Test Suites

“…In an effort to decrease the number of test instances, coverage criteria and searches are employed in all of the cited publications. Wotawa et al [23] developed an alternate test suite reduction strategy employing glue sequences to join small trial cases in a test suite and minimize overall assesement suite. Because of this, they can speed up test execution, especially in circumstances when the start-up procedure takes more time than the entire system itself.…”