A NOVEL USER PROFILE-BASED FUZZY APPROACH FOR EVALUATING TRUST IN SEMANTIC WEB

ABSTRACT: As a developed World Wide Web architecture, the Semantic Web collects traditional web contents with a formal and understandable semantic using a machine. The main purpose of the Semantic Web is to increase automation, web information processing, and improve interactions and collaboration among information systems. The subject of trust is one of the main challenges in the semantic web. Since different tools and individuals exist in the semantic web, a certain measure of trust in an entity cannot be used and a central system is responsible for data collection and estimating the reliability. In this study, a fuzzy system is used to evaluate the trust measure in the semantic web. For this purpose, the user profile data including a list of pages, user sessions, and visited pages in each session, and the time of page viewings are used as semantic parameters. After determining the general framework of trust in the semantic web, the effectiveness of the above mentioned semantic parameters on the trust measure is investigated and effective parameters are used for evaluation in the fuzzy system. The experiment results show that the proposed fuzzy method with a mean absolute error of 2.5% and an average precision of 97.5% could achieve the right value of trust in the semantic web. ABSTRAK:  Sebagai senibina World Wide Web, Semantik Web mengumpul kandungan web tradisional bersama semantik formal dan mudah difahami menggunakan mesin. Tujuan utama Semantik Web adalah bagi meningkatkan automasi, pemprosesan maklumat web, dan meningkatkan interaksi dan kerjasama antara sistem maklumat. Kepercayaan adalah salah satu cabaran utama dalam web semantik. Disebabkan perbezaan alatan dan pelbagai individu wujud dalam web semantik, langkah tertentu sebagai entiti dipercayai tidak dapat digunakan dan sistem pusat adalah bertanggungjawab bagi pengumpulan data dan kebolehpercayaan anggaran. Dalam kajian ini, sistem rawak telah digunakan bagi menilai tahap kepercayaan dalam web semantik. Bagi tujuan ini, data profil pengguna termasuk senarai halaman, sesi pengguna, dan halaman yang dikunjungi dalam setiap sesi, dan masa paparan halaman telah digunakan sebagai parameter semantik. Selepas menentukan rangka umum kepercayaan dalam web semantik, keberkesanan parameter semantik yang dinyatakan di atas pada ukuran kepercayaan telah disiasat dan parameter yang berkesan telah digunakan bagi penilaian sistem rawak. Keputusan eksperimen menunjukkan bahawa kaedah rawak yang dicadangkan dengan ralat mutlak purata sebanyak 2.5% dan ketepatan purata sebanyak 97.5% dapat mencapai nilai kepercayaan yang benar dalam web semantik.

[1]  Saeedeh Shekarpour,et al.  Modeling and evaluation of trust with an extension in semantic web , 2010, J. Web Semant..

[2]  Chris Cornelis,et al.  Key figure impact in trust-enhanced recommender systems , 2008, AI Commun..

[3]  Shonali Krishnaswamy,et al.  A fuzzy model for reasoning about reputation in web services , 2006, SAC.

[4]  Li Wang,et al.  A Web Service trust evaluation model based on small-world networks , 2014, Knowl. Based Syst..

[5]  Mohsen Lesani,et al.  Applying and Inferring Fuzzy Trust in Semantic Web Social Networks , 2006, CSWWS.

[6]  Jose L. Muñoz,et al.  Optimal tag suppression for privacy protection in the semantic Web , 2012, Data Knowl. Eng..

[7]  Pern Hui Chia,et al.  Does Trust Matter for User Preferences? A Study on Epinions Ratings , 2010, IFIPTM.

[8]  E. Michael Maximilien,et al.  Multiagent System for Dynamic Web Services Selection , 2005 .

[9]  Mehran Mohsenzadeh,et al.  A new method of trust mirroring estimation based on social networks parameters by fuzzy system , 2018, Int. J. Mach. Learn. Cybern..

[10]  Yutaka Matsuo,et al.  Community gravity: measuring bidirectional effects by trust and rating on online social networks , 2009, WWW '09.

[11]  Barry Smyth,et al.  Mining Trust Values from Recommendation Errors , 2006, Int. J. Artif. Intell. Tools.

[12]  Mehran Mohsenzadeh,et al.  Trust estimation of the semantic web using semantic web clustering , 2017, J. Exp. Theor. Artif. Intell..

[13]  Yolanda Gil,et al.  A survey of trust in computer science and the Semantic Web , 2007, J. Web Semant..

[14]  Matthew Richardson,et al.  Trust Management for the Semantic Web , 2003, SEMWEB.

[15]  Hamdi Yahyaoui,et al.  A trust-based game theoretical model for Web services collaboration , 2012, Knowl. Based Syst..

[16]  Kiyana Zolfaghar,et al.  Evolution of trust networks in social web applications using supervised learning , 2011, WCIT.

[17]  Young Ae Kim,et al.  A trust prediction framework in rating-based experience sharing social networks without a Web of Trust , 2012, Inf. Sci..

[18]  Jian Yang,et al.  A Trust and Reputation Model Based on Bayesian Network for Web Services , 2010, 2010 IEEE International Conference on Web Services.