Indian Journal of Science and Technology
Year: 2015, Volume: 8, Issue: 34, Pages: 1-8
Department of Computer Science, AMBO University, Ethiopia; [email protected]
Objective: The main objective of this work is finding a fraudulent ranking behaviour of mobile apps where mobile app developers may generate fraudulent evidences for providing a top ranking for them. The primary goal of this work is to find out the fraudulent evidences present in the ranked mobile apps. This work attempts to improve the accuracy of detection of fraudulent ranking behaviour of mobile apps by performing concept vector based review evidence analysis. Method: Mobile app ranking fraudulent behaviour is the biggest issue in the mobile app development environment due to the degradation of mobile app’s important level. In the existing work, Leading Session Methodology based evidence aggregation (LSMEA) is introduced to leverage the fraudulent ranking activities. This LSM analysis the three types of evidences such as ranking based, rating based and review based and aggregates their output finally for detecting the fraudulent ranking behaviour of mobile apps. Among the above mentioned evidences, review based evidence is based on user opinion about the corresponding mobile app. LSM analysis the users review comments by using latent semantic approach which will find the important semantic terms from the user review comments. However this method failed to identify the concepts of semantic terms accurately which might lead to wrong assumption of fraudulent ranking behaviour. This problem is overcome in this work by introducing the Concept Vector based Review Evidence Analysis (CVREA) which is done by using WordNet tool. Word Net tool will retrieve the most important concepts present in each sentence of user review comments based on which fraud signature would be computed. Finally, result of these three evidences would be combined together to detect the fraudulent ranking behaviour of mobile apps. Application/ Improvements: This proposed research methodology would be more helpful in the mobile app markets where the number of apps developed for the specific purpose has been increased considerably. In this situation, it is required to provide truthful and most popular mobile apps to the users to increase the reputation level. This proposed research methodology provides a way for increasing the reputation level of the mobile owners by detecting and eliminating the fraudulent ranking behaviour of mobile apps.
Keywords: Mobile Apps, Fraudulent Behaviour, Ranking Evidences, Sematic Relation
Subscribe now for latest articles and news.