Online reviews about the purchase of products or services provided have become the main source of users’ opinions. In order to gain profit or fame, usually spam reviews are written to promote or demote a few target products or services. This practice is known as review spamming. In the past few years, a variety of methods have been suggested in order to solve the issue of spam reviews. In this study, the researchers carry out a comprehensive review of existing studies on spam review detection using the Systematic Literature Review (SLR) approach. Overall, 76 existing studies are reviewed and analyzed. The researchers evaluated the studies based on how features are extracted from review datasets and different methods and techniques that are employed to solve the review spam detection problem. Moreover, this study analyzes different metrics that are used for the evaluation of the review spam detection methods. This literature review identified two major feature extraction techniques and two different approaches to review spam detection. In addition, this study has identified different performance metrics that are commonly used to evaluate the accuracy of the review spam detection models. Lastly, this work presents an overall discussion about different feature extraction approaches from review datasets, the proposed taxonomy of spam review detection approaches, evaluation measures, and publicly available review datasets. Research gaps and future directions in the domain of spam review detection are also presented. This research identified that success factors of any review spam detection method have interdependencies. The feature’s extraction depends upon the review dataset, and the accuracy of review spam detection methods is dependent upon the selection of the feature engineering approach. Therefore, for the successful implementation of the spam review detection model and to achieve better accuracy, these factors are required to be considered in accordance with each other. To the best of the researchers’ knowledge, this is the first comprehensive review of existing studies in the domain of spam review detection using SLR process.

Spam Review Detection Techniques: A Systematic Literature Review

COVID-19 X-ray images classification based on enhanced fractional-order cuckoo search optimizer using heavy-tailed distributions

Several techniques or methods may help in detecting diseases and cancer. Creating an effective method for extracting disease information is one of the major challenges in the classification of gene expression data as long as there is (in the presence) a massive amount of redundant data and noise. Bio-inspired algorithms are among the most effective when used for solving gene selection. Moth Flame Optimization Algorithm (MFOA) is computationally less expensive and can converge faster than other methods. In this paper, we propose a new extension of the MFOA called the modified Moth Flame Algorithm (mMFA), the mMFA is combined with Mutual Information Maximization (MIM) to solve gene selection in microarray data classification. Our approach Called Mutual Information Maximization – modified Moth Flame Algorithm (MIM-mMFA), the MIM based pre-filtering technique is used to measure the relevance and the redundancy of the genes, and the mMFA is used to evolve gene subsets and evaluated by the fitness function, which uses a Support Vector Machine (SVM) with Leave One Out Cross Validation (LOOCV) classifier and the number of selected genes. In order to test the performance of the proposed MIM-mMFA algorithm, we compared the MIM-mMFA algorithm with other recently published algorithms in the literature. The experiment results which have been conducted on sixteen benchmark datasets either binary-class or multi-class, confirm that MIM-mMFA algorithm provides a greater classification accuracy.

Gene selection and classification of microarray data method based on mutual information and moth flame algorithm.

The rapid growth of electronic documents are causing problems like unstructured data that need more time and effort to search a relevant document. Text Document Classification (TDC) has a great significance in information processing and retrieval where unstructured documents are organized into pre-defined classes. Urdu is the most favorite research language in South Asian languages because of its complex morphology, unique features, and lack of linguistic resources like standard datasets. As compared to short text, like sentiment analysis, long text classification needs more time and effort because of large vocabulary, more noise, and redundant information. Machine Learning (ML) and Deep Learning (DL) models have been widely used in text processing. Despite the major limitations of ML models, like learn directed features, these are the favorite methods for Urdu TDC. To the best of our knowledge, it is the first study of Urdu TDC using DL model. In this paper, we design a large multi-purpose and multi-format dataset that contain more than ten thousand documents organize into six classes. We use Single-layer Multisize Filters Convolutional Neural Network (SMFCNN) for classification and compare its performance with sixteen ML baseline models on three imbalanced datasets of various sizes. Further, we analyze the effects of preprocessing methods on SMFCNN performance. SMFCNN outperformed the baseline classifiers and achieved 95.4%, 91.8%, and 93.3% scores of accuracy on medium, large and small size dataset respectively. The designed dataset would be publically and freely available in different formats for future research in Urdu text processing.

/pdf/document-level-text-classification-using-single-layer-4l8lnycyh6.pdf

Document-Level Text Classification Using Single-Layer Multisize Filters Convolutional Neural Network

A comprehensive survey on recent metaheuristics for feature selection

Big multimedia data is heterogeneous in essence, that is, the data may be a mixture of video, audio, text, and images. This is due to the prevalence of novel applications in recent years, such as social media, video sharing, and location based services (LBS), etc. In many multimedia applications, for example, video/image tagging and multimedia recommendation, text classification techniques have been used extensively to facilitate multimedia data processing. In this paper, we give a comprehensive review on feature selection techniques for text classification. We begin by introducing some popular representation schemes for documents, and similarity measures used in text classification. Then, we review the most popular text classifiers, including Nearest Neighbor (NN) method, Naive Bayes (NB), Support Vector Machine (SVM), Decision Tree (DT), and Neural Networks. Next, we survey four feature selection models, namely the filter, wrapper, embedded and hybrid, discussing pros and cons of the state-of-the-art feature selection approaches. Finally, we conclude the paper and give a brief introduction to some interesting feature selection work that does not belong to the four models.

Feature selection for text classification: A review

Clustering by fast search and find of density peaks (CFSFDP) is a novel clustering algorithm proposed in recent years. The algorithm has the advantages of low computational complexity and high accuracy. However, the truncation distance dc needs to be determined according to user experience. Aiming to overcome these drawbacks, this paper proposes a new algorithm named Sparse learning based on clustering by fast search and find of density peaks (SL-CFSFDP). Compared to CFSFDP, the proposed algorithm can obtain dc automatically, and it uses sparse learning to determine the neighbors of each data point, removing irrelevant data points at the same time. SL-CFSFDP combines the local density and the distance δi to automatically determine cluster centers, after which the remaining data points are assigned to clusters according to the local density and distance δi. Extensive experimental results on both synthetic and benchmark datasets show that SL-CFSFDP is superior to DBSCAN and CFSFDP.

Sparse learning based on clustering by fast search and find of density peaks

Dimensionality reduction has been attracted extensive attention in machine learning. It usually includes two types: feature selection and subspace learning. Previously, many researchers have demonstrated that the dimensionality reduction is meaningful for real applications. Unfortunately, a large mass of these works utilize the feature selection and subspace learning independently. This paper explores a novel supervised feature selection algorithm by considering the subspace learning. Specifically, this paper employs an l
 2,1−norm and an l
 2,p
 −norm regularizers, respectively, to conduct sample denoising and feature selection via exploring the correlation structure of data. Then this paper uses two constraints (i.e. hypergraph and low-rank) to consider the local structure and the global structure among the data, respectively. Finally, this paper uses the optimizing framework to iteratively optimize each parameter while fixing the other parameter until the algorithm converges. A lot of experiments show that our new supervised feature selection method can get great results on the eighteen public data sets.

Xuelian Deng

Papers

Feature selection for text classification: A review

Sparse learning based on clustering by fast search and find of density peaks

Hypergraph expressing low-rank feature selection algorithm