A systematic literature review on spam content detection and classification

Kaddoura, Sanaa; Chandrasekaran, Ganesh; Popescu, Daniela; Hemanth, D. Jude

doi:10.7717/peerj-cs.830

Cited by 57 publications

(24 citation statements)

References 76 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared to the traditional mail spam and web spam, twitter went beyond phishing, fraudulent, and scam. It creates new avenues for profanity, insulting, spreading hate speech, and bullying [1]- [3], [13], [24]. Researchers have investigated wide range of approaches to accommodate such divergence.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Modified Genetic Algorithm for Feature Selection and Hyper Parameter Optimization: Case of XGBoost in Spam Prediction

2022

View full text Add to dashboard Cite

Recently, spam on online social networks has attracted attention in the research and business world. Twitter has become the preferred medium to spread spam content. Many research efforts attempted to encounter social networks spam. Twitter brought extra challenges represented by the feature space size, and imbalanced data distributions. Usually, the related research works focus on part of these main challenges or produce black-box models. In this paper, we propose a modified genetic algorithm for simultaneous dimensionality reduction and hyper parameter optimization over imbalanced datasets. The algorithm initialized an eXtreme Gradient Boosting classifier and reduced the features space of tweets dataset; to generate a spam prediction model. The model is validated using a 50 times repeated 10-fold stratified cross-validation, and analyzed using nonparametric statistical tests. The resulted prediction model attains on average 82.32% and 92.67% in terms of geometric mean and accuracy respectively, utilizing less than 10% of the total feature space. The empirical results show that the modified genetic algorithm outperforms Chi 2 and P CA feature selection methods. In addition, eXtreme Gradient Boosting outperforms many machine learning algorithms, including BERT-based deep learning model, in spam prediction. Furthermore, the proposed approach is applied to SMS spam modeling and compared to related works.

show abstract

Section: Related Workmentioning

confidence: 99%

“…One of the major issues in spam text research is the limited availability of labeled text datasets with high quality [13], [14]. For example the well known benchmark datasets are few, and many researchers use tools to collect domain specific datasets.…”

Section: Introductionmentioning

confidence: 99%

Modified Genetic Algorithm for Feature Selection and Hyper Parameter Optimization: Case of XGBoost in Spam Prediction

2022

View full text Add to dashboard Cite

show abstract

“…Analyse because CNNs function differently across object types. [19] Spam contains malicious links, programs, counterfeit accounts, false news, reviews, and rumors. Spam text detection and management increase social media security.…”

Section: Vertical Line Filtermentioning

confidence: 99%

“…This study looks at how to identify and categorize spam text on social media. Machine Learning, Deep Learning, and text-based spam detection and classification algorithms are discussed in this article [19].…”

Section: Vertical Line Filtermentioning

confidence: 99%

Deep Learning Image Classification for Fashion Design

Vijayaraj

Raj²,

Jebakumar

et al. 2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Fashion has always been an essential feature in our daily routine. It also plays a significant role in everyone’s lives. In this research, convolutional neural networks (CNN) were used to train images of different fashion styles, which were attempted to be predicted with a high success rate. Deep learning has been widely applied in a variety of fields recently. A CNN is a deep neural network that delivers the most accurate answers when tackling real-world situations. Apparel manufacturers have employed CNN to tackle various difficulties on their e-commerce sites, including clothing recognition, search, and suggestion. A set of photos from the Fashion-MNIST dataset is used to train a series of CNN-based deep learning architectures to distinguish between photographs. CNN design, batch normalization, and residual skip connections reduce the time it takes to learn. The CNN model’s findings are evaluated using the Fashion-MNIST datasets. In this paper, classification is done with a convolutional layer, filter size, and ultimately connected layers. Experiments are run with different activation functions, optimizers, learning rates, dropout rates, and batch sizes. The results showed that the choice of activation function, optimizer, and dropout rate impacts the correctness of the results.

show abstract

“…A well-known Python package called "regular expressions" can be used to divide the text into tokens, and it is widely used to carry out Natural Language Processing (NLP) activities. [36] It is the process of stripping a term down to its most basic form in order to decrease the number of different tokens in a text. By eliminating superfluous information, it helps in text cleaning.…”

Section: Spam Classification Techniquesmentioning

confidence: 99%

An Extensive Review on Contemporary Analysis of Comment Filtration of YouTube Videos Using Machine Learning Techniques

Sinhal¹,

Maheshwari²

2022

IJETAE

View full text Add to dashboard Cite

Recently, social media platforms like LinkedIn, Twitter, Facebook, YouTube, etc., are immensely popular, especially in the pandemic era. This is because they provide connection and interaction between people by posting images, comments, or videos.YouTube has become a very popular video-sharing platform, and because of this, it has also attracted several types of spammers or malicious users whose aim is to distribute viruses or promote their videos. Spammers also want to spread phishing, malware, or advertisements in the comment section of the videos. Spam is generally related to unsought content or irrelevant comments with low-grade information. They are usually found as images, texts, or videos, clogging the visualization of interesting content. Users spend a lot of time eradicating spam since it causes a variety of issues that could lead to traffic and financial losses. To filter spam, several techniques have been developed. Automatic comment spam filtering on YouTube is not a simple task even for well-known classification methods since comments are very short and often contain slang, symbols and abbreviations. However, typical machine learning classification algorithms have been confirmed to be fairly effective, but there is still space for improved accuracy with new methods. In this paper, we will evaluate several topperformance classification techniques (such as Naive Bayes, Random Forest, and Support Vector Machine) of Machine Learning classification algorithms to detect such comments as spam or ham with the help of text classification, feature extraction and text pre-processing. It will work after posting the comments. This paper provides a comparative analysis of various ML techniques implemented by various researchers and authors in their work. The dataset would be used with reference to the UCI machine learning repository for future implementations of this related work.

show abstract

A systematic literature review on spam content detection and classification

Cited by 57 publications

References 76 publications

Modified Genetic Algorithm for Feature Selection and Hyper Parameter Optimization: Case of XGBoost in Spam Prediction

Modified Genetic Algorithm for Feature Selection and Hyper Parameter Optimization: Case of XGBoost in Spam Prediction

Deep Learning Image Classification for Fashion Design

An Extensive Review on Contemporary Analysis of Comment Filtration of YouTube Videos Using Machine Learning Techniques

Contact Info

Product

Resources

About