ABSTRACT The rapid growth of online product reviews has made it increasingly challenging for consumers to make informed purchase decisions. However, the abundance of reviews, including fake or augmented and sarcastic reviews, poses a challenge for consumers. To address this challenge, this paper introduces the TOPS (Trusted Opinion analysis of Product reviewS) framework, a novel approach that leverages a hybrid deep learning‐based D2CL (Dual Deep leaning based cleaning) filter to enhance the reliability of online reviews. The proposed methodology employs the D2CL filter to identify and eliminate fake and sarcastic reviews, ensuring that the consolidated sentiment analysis provides users with trustworthy opinions. The framework is equipped with the R‐mGRU, a hybrid deep learning model specifically designed to tackle the nuances of product reviews. This model has demonstrated impressive accuracy rates, achieving 89%, 91%, and 94% for fake, sarcasm, and sentiment analysis tasks, respectively. The TOPS framework makes a significant contribution to improving the overall quality and authenticity of product reviews, empowering consumers with more reliable information for informed decision‐making in online shopping scenarios.

Abstract Lie detection is one of the major challenges that is being faced by the forensic sciences. Identification of lie on the basis of a person's mental behavior is a tedious task. Brain‐computer interface is one such medium which provides a solution to this problem by displaying visual stimuli and recording subject's brain responses. A P300 response is elicited whenever a person comes across a familiar stimuli in a series of rare stimuli. This P300 response is used for the lie detection method. In the proposed concealed information test, acquired signals are preprocessed to discard noise. Then, short‐time Fourier transform method is applied to extract features from the preprocessed electroencephalogram signals. To avoid the curse of dimensionality and to reduce computational overhead, binary bat algorithm is applied, which helps in choosing optimal subset of features. The obtained set of features is given as an input to the extreme learning machine classifier for training of guilty and innocent samples. The performance of the system is assessed using 10‐fold cross‐validation. The resultant accuracy obtained from the proposed lie detection system is 88.3%. The system has provided efficient results in contrast with most of the state‐of‐the‐art lie detection methods.

In the era of data, it is a challenging task to classify continuous data such as electroencephalographic data. The electroencephalographic signal maps several thoughts going in an individual's brain by connecting a device to the human brain. In this paper, we have proposed a deceit identification system using a test called “concealed information test.” The electroencephalographic data have been recorded when the concealed information test is performed for experimental analysis. To enhance the performance of the deceit identification system, the optimization of support vector machine (SVM) parameters and the selection of the EEG channels are performed. This paper implements a binary version of the BAT algorithm (binary BAT algorithm) and the conventional BAT algorithm on the electroencephalography (EEG) data. A novel cost function is also proposed, which utilizes the results of continuous BAT and binary BAT to enhance the system performance. In this synergistic approach, BAT is used for the SVM parameters optimization, and the binary BAT algorithm is applied for the EEG channel selection. The performance of the system is improved, and it is inferred that the channels placed at the occipital lobe of the brain consist of the artifacts. After removing the channels placed on the occipital lobe, i.e., O1, Oz, and O2, and using the optimized SVM parameters, the system's average accuracy increases from 94.11% to 96.8%.