Survey of Developing a Model of Analysing and Detecting for Leaderboard Discrepancies of Mobile Application

Maria Varsha B¹, Kayalvizhi K², Hemalatha A³, Loganya K⁴

^1,2,3,4Student Scholar, Department of Information Technology, Karpagam Institute of Technology, Coimbatore.

Abstract

Recently, many number of research has resulted that the opinion sources as product reviews, forum posts, and blogs. Ranking the fraud mobile App with more ratings is a fraudulent or deceptive activities which have a intension to indicate that Apps in the popularity list. It becomes an added advantage for the App developers to increasing their Apps' sales or posting higher ratings, to commit ranking fraud. Though the importance of preventing ranking fraud has been already recognized, there is only limited research and work has been done in this area. The existing research focuses on classification and summarization of opinions using online analytical processing and data mining techniques. In this proposed system a holistic view of ranking fraud and propose a fraud detection system for mobile Apps. Specifically, we first propose to locate the ranking fraud by mining the leading sessions, of mobile Apps. We further investigate three types of evidences, i.e., ranking, rating and review, based on mobile Apps' ranking, rating and review behaviours. Based on these records and analysis, we can generate the report on fraud detection. To aggregate these reviews, OLAP data aggregation method is used. In the proposed system, user feedbacks can be collected. These feedbacks can contain both the positive and negative feedbacks. User can select the url of the mobile app. From the user click, user can identify the original or fake links. And also we can analyse the user behaviour or user interest by analysing the session history. From this analysis we can conclude, the most frequently used apps by users. K-means clustering algorithm is used to cluster the fake profile comments.

Keywords

• Mobile Apps, ranking fraud detection, evidence aggregation, historical ranking records, rating, review

Author's Profile

Author profile can be generated and linked through our partners World Book of Researchers. To include your profile online Click Here. After it is approved, please email to edlib @ asdf.res.in to create a link with all the papers.

• Maria Varsha B : Profile
• Kayalvizhi K : Profile
• Hemalatha A : Profile
• Loganya K : Profile

e-AID

Cite this Article as Follows

Maria Varsha B, Kayalvizhi K, Hemalatha A, Loganya K. "Survey of Developing a Model of Analysing and Detecting for Leaderboard Discrepancies of Mobile Application" International Conference on Systems, Science, Control, Communication, Engineering and Technology (2016): 509-511. Print.