A Novel Quantum Neural Network Approach to Combating Fake Reviews

Abstract

As e-commerce has grown gradually online item assessments have emerged as a key source of consumer data. That stated, there are problems with the consistency and fictitiousness of the evaluations because there are numerous fake or fraudulent ones. These misleading assessments are generated during the investigation in an attempt to mislead customers about the nature of a real advantage, compromising their ability to make a predetermined decision and damaging the reputations of businesses. A cutting-edge interrogation department revealed that quantum machine learning (QML) could manage a huge amount of machine-trained data and could convey almost emotional choices in the context of inaccurate checks. It is truly beneficial in obtaining reviews for things that are incorrect. Opinion, generating trends, interpersonal relationships, and assessing fatigue is merely a few of the attributes. Tests conducted utilizing the Amazon fraudulent review. The dataset demonstrates that QML tactics outperform conventional knowledge acquisition procedures in errands, including the place of fraudulent reviews. The delicacy and tolerance of incorrect review distinguishing evidence can be significantly advanced, although QML is still in its early stages of development. Both our proposed model and model pass rigorous conventional machine learning algorithms testing with a remarkable level of accuracy. An article introduces a unique approach to fraudulent review detection and brings in the QNN algorithm as a solution. A deep learning model, such as this one, has an 86% accuracy rate in quantum computer implementation, which is an impressive level of innovation, especially if it comes with successful results. Involvement in these cutting-edge technologies promises significant benefits in battling the problem of false identities on the Web. In our case, the experimental results demonstrate that our QNN algorithm, which can accurately identify fake reviews, will become a key weapon for suppressing various forms of fraudulence on emerging digital technology platforms.