Detecting Fraud Apps using Sentiment Analysis

Project Domain / Category

NLP/Information Retrieval

Abstract / Introduction

Nowadays, there are so many applications available on internet because of that user cannot always get correct or true reviews about the product on internet. In this project, we propose the system by developing web application which help to detect fraud apps using sentiment comments. We can check for user’s sentimental comments on multiple application. The reviews may be fake or genuine. But after comparing reviews of admin as well as user’s, we can get more clear idea. Hence, we can get higher probability of getting real reviews. So we are proposing a system to develop a web application that will take reviews from registered users for single product, and analyse them for positive negative rating. For every users reviews and comments will be fetched separately and analysed for positive negative rating. Then their rating/comments will be judged by the admin and it would be easy for admin to predict the application as Genuine or Fraud.

Functional Requirements:

        The system should be able to add applications to the system.

        The system should be able to allow user once to access the system, user can view Apps and can post review about the Apps.

        The system should be able to analyze the rating based on user comments.

        Modules:

The system comprises of 2 major modules with their sub-modules as follows:

        Admin

        Add New Application

        System allows Admin to add new applications and its details such as Name, Link, Description, Rating, Category, App Image, etc.

        Detect Fraud Applications:

        Admin will check the application details and also read the user comments.

        Admin will analyze the ratings and comments which will help him/her to decide whether the app is fraud or not.

        View Users:

        Can view the list of registered users with their details.

        View Feedback:

        Admin can view feedbacks received from the registered user’s. e. Review Monitoring (Opinion Mining):

Page 42 of 167