The Detection of Sexual Harassment and Chat Predators Using Artificial Neural Network

Hamzah, Noor Amer; Dhannoon, Ban N.

doi:10.33640/2405-609x.3157

Cited by 11 publications

(7 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The preprocessing technique reduces unnecessary data and makes it more classifiable. Certainly, there are many pre-processing operations done by different researchers to clean the datasets (special characters, punctuation, white spaces, contractions, and stop words), convert all characters to lowercase, as well as return the words to their root using stemming or lemmatization [32][33][34]. Feature Extraction: A PC can utilize advanced information.…”

Section: Methodsmentioning

confidence: 99%

“…Sentences are represented as dense word vectors via word embedding, hence the term "embedding" refers to obtaining more data with fewer dimensions. [32]. The embedding process translates semantic meaning into geometric meaning, Word2Vec [8,23,25], Global vectors (GloVe) for word representation [18], n-grams [11,26], word-embedding [12], BOW [7] are the pioneers of word representativeness approaches.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A Review of the Past Decade's Research Outcomes on Classifying Cyberbullying

Haider Ameen,

Saad Al-Mukhtar,

Qahtan Ahmed

et al. 2024

ANJS

View full text Add to dashboard Cite

Cyberbullying is a new form of online violence that has emerged as a result of the social media industry's explosive expansion since it allows for indirect communication. Despite the usefulness of digital media, it has been used by weak people to threaten and bully others online. In the last ten years, research has shown that children and teenagers are increasingly experiencing cyberbullying as a concern. This paper examines the research conducted during the previous ten years, categorizes it, and presents statistical analyses of the data collected during that time. A table is used to present various data, including the dataset that was used, its size (number of samples, posts, or messages), the methods that were employed, and the metrics that were gathered from the examined research that was taken from the publications that were looked into. This survey will be helpful to everyone who wants to advance their understanding of how machine learning may be used to identify cyberbullying, and it may help create a social media environment that is safe and relatively healthy by automatically identifying bullying communications.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

A Review of the Past Decade's Research Outcomes on Classifying Cyberbullying

Haider Ameen,

Saad Al-Mukhtar,

Qahtan Ahmed

et al. 2024

ANJS

View full text Add to dashboard Cite

show abstract

“…GloVe is used to represent words using an embedding matrix containing many words. Each of these words corresponds to several numerical values, representing the vectors embedding this word, which are then employed as the input layer for neural networks of deep learning classifiers [13], [14]. Recurrent neural network (RNN) is one type of deep learning classifier based on keeping the output of a certain layer and feeding it back to the input to predict the layer's output, but it suffers from the problem of vanishing and exploding gradients.…”

Section: Preliminariesmentioning

confidence: 99%

Word embedding for detecting cyberbullying based on recurrent neural networks

Shaker,

Dhannoon

2024

IJ-AI

View full text Add to dashboard Cite

<span lang="EN-US">The phenomenon of cyberbullying has spread and has become one of the biggest problems facing users of social media sites and generated significant adverse effects on society and the victim in particular. Finding appropriate solutions to detect and reduce cyberbullying has become necessary to mitigate its negative impacts on society and the victim. Twitter comments on two datasets are used to detect cyberbullying, the first dataset was the Arabic cyberbullying dataset, and the second was the English cyberbullying dataset. Three different pre-trained global vectors (GloVe) corpora with different dimensions were used on the original and preprocessed datasets to represent the words. Recurrent neural networks (RNN), long short-term memory (LSTM), Bidirectional LSTM (BiLSTM), gated recurrent unit (GRU), and Bidirectional GRU (BiGRU) classifiers utilized, evaluated and compared. The GRU outperform other classifiers on both datasets; its accuracy on the Arabic cyberbullying dataset using the Arabic GloVe corpus of dimension equal to 256D is 87.83%, while the accuracy on the English datasets using 100 D pre-trained GloVe corpus is 93.38%.</span>

show abstract

“…• Dropout: Dropout lowers overfitting and raises the generalizability of the model. Depending on their likelihood of being in the chosen hidden layers, this technique ignores hidden neurons [17]. A neural network's dropout is depicted in Fig.…”

Section: B Data Augmentationmentioning

confidence: 99%

Improved Model for Skin Illnesses Classification Utilizing Gray-Level Co-occurrence Matrix and Convolution Neural Network

Hussein,

Maki

et al. 2023

JAIT

View full text Add to dashboard Cite

Skin conditions are more common than other illnesses. Skin issues can be brought on by viruses, bacteria, allergies, fungi, etc. The detection of skin diseases has been made better by lasers and photonics since it is now quicker and more precise. However, such a diagnosis is pricey. A system for automated dermatology screening is built with the use of computer vision. Using the Gray Level Co-occurrence Matrix (GLCM) and Convolution Neural Network (CNN) provides an improved model for accurately diagnosing skin disorders. In order to classify skin photos, CNN is used by the model to extract features from the images using GLCM. The high-level features utilizing the statistical features were retrieved via GLCM separately because the photos utilized in the research are for skin conditions. Once merged, these features created a high-accuracy categorization. Two distinct classification processes are used to categorize photos into 13 diseases: First, the Deep Neural Network (DNN) classifier obtains 96.69% accuracy, 96.2% recall, 96.2% precision, and 96.2% F1-score in terms of performance evaluation measures. Second, accuracy, recall, precision, and F1-score are the performance evaluation metrics for the Multiple Support Vector Machine (MSVM) classifiers. The model outperforms other cutting-edge models in terms of accuracy and effectiveness when compared to them. This work thus indicates the capability of GLCM and CNN for the classification of skin diseases and their prospective uses in the healthcare sector.

show abstract

The Detection of Sexual Harassment and Chat Predators Using Artificial Neural Network

Cited by 11 publications

References 0 publications

A Review of the Past Decade's Research Outcomes on Classifying Cyberbullying

A Review of the Past Decade's Research Outcomes on Classifying Cyberbullying

Word embedding for detecting cyberbullying based on recurrent neural networks

Improved Model for Skin Illnesses Classification Utilizing Gray-Level Co-occurrence Matrix and Convolution Neural Network

Contact Info

Product

Resources

About