• TEJASWINI DONKADA
• Dr.K.N.S.LAKSHMI

ABSTRACT: In the present day, online social media holds a dominant position in various aspects. There is a significant increase in the number of users utilizing social media platforms every day. The primary advantage of these platforms is the ease of connecting and communicating with people. However, this convenience has also opened doors to potential attacks such as fake identity and false information. A recent survey has revealed that the number of accounts on social media is considerably greater than the actual number of users, indicating a significant rise in fake accounts in recent years. The rise in fake accounts in recent years has presented a significant challenge for online social media providers, as identifying these accounts has proven to be difficult. The presence of fake accounts has led to a surge of false information and advertisements on social media platforms. Traditional methods for identifying fake accounts have become outdated due to the advancements in fake account creation. To combat this issue, new models have been developed using different approaches, such as automatic posts or comments, spreading false information, or spamming advertisements to identify fake accounts efficiently. The rise in fake account creation has led to the development of various algorithms with different attributes to combat the issue. Previous algorithms such as Naïve Bayes, Support Vector Machine, and Random Forest have become inefficient in detecting fake accounts. To address this problem, a new method was proposed in this research to identify fake accounts accurately. The approach involved the use of a gradient boosting algorithm with decision trees comprising three critical attributes: spam commenting, artificial activity, and engagement rate. By combining machine learning and data science, the proposed method provided an accurate prediction of fake accounts.

KEYWORDS: Data science, Fake account detection, Machine learning, online social media

"IDENTIFYING FAKE SOCIAL MEDIA PROFILES USING MACHINE LEARNING TECHNIQUES", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 6, page no.i634-i642, June-2023, Available :http://www.jetir.org/papers/JETIR2306868.pdf

"IDENTIFYING FAKE SOCIAL MEDIA PROFILES USING MACHINE LEARNING TECHNIQUES", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 6, page no. ppi634-i642, June-2023, Available at : http://www.jetir.org/papers/JETIR2306868.pdf