DETECTION AND PREVENTION OF MALICIOUS FEEDBACK RATING IN WEB SERVICE RECOMMENDATION SYSTEMS
Journal Title: Elysium Journal of Engineering Research and Management - Year 2015, Vol 2, Issue 3
Abstract
To facilitate a recommendation to users for selecting an appropriate or reputed web service from mass of services by avoiding dishonest recommendation. To prevent, avoid and detect the malicious feedback rating. Large scale feedback ratings are analyzed to validate the scalability of proposed approach. Service users provides feedback ratings, which used to calculate reputation of web service in the field of service computing. The malicious ratings and user’s preferences constitutes either positive bias or negative bias. A novel reputation measure for web services proposed in this paper. The proposed method works in two phases. They are malicious rating detection and rating adjustment. The two phases are used to enhance the reputation measure accuracy. The proposed system detects malicious feedback ratings by using cumulative sum method and reduces the effect of user feedback preferences by Pearson correlation coefficient. The proposed method is implemented on various experiments. Experimental results show that proposed method is effectively used to enhance the reliability of service selection. The exists of vulnerability of malicious feedback rating in the system of recommending reputed web services based on the feedback rating from users on each web service. Such vulnerability is detected, reduced and prevented using Cumulative Sum Control Chart, Pearson Correlation Coefficient, and Bloom filtering techniques respectively.
Authors and Affiliations
Deepika S, Kamala B.
AN EFFICIENT ALGORITHM FOR ESTIMATING THE HISTOGRAM USING SPATIO-TEMPORAL DATA
This paper spotlight on an influential query in methodical reproduction data analysis: the histogram estimation on spatial data. Histogram is nothing but an split up of datas into buckets for optimizing t...
EMPLOYMENT CHANCE PREDICTION BASED ON DECISION TREES AND NAIVE BAYES CLASSIFIER USING DATA MINING TECHNIQUES
Data Mining is the non-trivial extract information from a data set and transforms it into an understandable structure for further use. Data mining is the search for the relationship and global pattern that exi...
QR Code Authentication Based Goods Delivery System
This application is for, order checking between delivery boy and the customer. If the customer order some goods in a particular company/ industry means, the order information such as customer name, address, amount, numbe...
A SURVEY ON OPTIMIZED CLOUD INSTANCE MANAGEMENT STRATEGIES USING AMAZON EC2
Cloud computing has become more and more popular now a day. This is due to the fact that it is highly compatible to provide an effective and efficient service to customers on demand. This is due to...
AN INTEGRATED FRAMEWORK FOR PARALLEL TRAINING AND CLASSIFICATION OF ECG SIGNAL
Recently, various techniques are developed to analyze and classify the Electrocardiograph (ECG) signal to know the threaten results. Many real time development tools such as VLSI, DSP, etc., are availabl...