INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2456-4184 | Impact factor: 8.76 | ESTD Year: 2016
Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.76 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
The escalating trend of online shopping has witnessed a significant surge, with a growing number of individuals preferring to procure products from virtual stores. Consequently, the utilization of the Internet and online marketing has attained widespread popularity. The online marketplace now offers an extensive array of millions of products and services, thereby generating a vast volume of information. Consequently, locating the most suitable services or products that align with specific requirements has become a daunting task. In such a vast landscape, customers heavily rely on reviews and opinions shared by others, which are based on their personal experiences, to make informed decisions. The spread of bogus reviews has emerged as a critical concern in today's world of intense competition. Companies are increasingly turning to employing people to create positive reviews for their own goods or services while writing unfairly critical comments about their rivals, which is a worrying trend. These dishonest actions have serious repercussions because they deceive prospective buyers who rely on these ratings to make wise purchasing decisions. A strong system that is capable of identifying and removing bogus reviews is thus urgently needed. In order to identify false reviews, this study will examine a variety of supervised, unsupervised, and semi-supervised machine learning algorithms. Multiple classifiers, including Support Vector Machine (SVM), Nave Bayes, and Random Forest Classifier, are used to assess each approach. Additionally, the study takes into consideration the effectiveness of n-gram techniques and linguistic models to enhance the evaluation process. The proposed methodology demonstrates a noteworthy accuracy rate of 87% in effectively identifying fake reviews.
Keywords:
Fake reviews detection, Machine learning Algorithms, Text Classification, Natural Language Processing, Bigrams, Term Frequency and Inverse Document Frequency.
Cite Article:
"Monitoring of Fake Online Reviews Through Machine Learning ", International Journal of Novel Research and Development (www.ijnrd.org), ISSN:2456-4184, Vol.8, Issue 5, page no.f577-f584, May-2023, Available :http://www.ijnrd.org/papers/IJNRD2305583.pdf
Downloads:
000118778
ISSN:
2456-4184 | IMPACT FACTOR: 8.76 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.76 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Facebook Twitter Instagram LinkedIn