TY - GEN
T1 - A new fuzzy clustering approach for reputation management in OSNs
AU - Hamdi, Sana
AU - Gancarski, Alda Lopes
AU - Bouzeghoub, Amel
AU - Ben Yahia, Sadok
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/9/7
Y1 - 2017/9/7
N2 - Trust and reputation management is introduced tothe Online Social networks (OSNs) as a solution to promote ahealthy collaboration relationship among participants. Currently, most trust and reputation systems focus on evaluating thecredibility of the users. The reputation systems in OSNs have asobjective to help users to make difference between trustworthyand untrustworthy, and encourage honest users by rewardingthem with high trust values. Computing reputation of one userwithin a network requires knowledge of trust degrees betweenthe users. In this paper, we develop a new Fuzzy ClusteringReputation algorithm, called FCR, based on trusted network. This algorithm computes the membership degrees for each userand classifies the users of OSNs by their trust similarity suchthat most trustworthy users belong to the same cluster. Moreover, to satisfy the needs of OSNs' users by storing important trustdata in a well organized and easy to understand structure, wepropose to enrich the Friend of Friend (FOAF) vocabulary withthe reputation of users. Experimental results with data from thereal OSN, Twitter, show that our work generates high qualityresults.
AB - Trust and reputation management is introduced tothe Online Social networks (OSNs) as a solution to promote ahealthy collaboration relationship among participants. Currently, most trust and reputation systems focus on evaluating thecredibility of the users. The reputation systems in OSNs have asobjective to help users to make difference between trustworthyand untrustworthy, and encourage honest users by rewardingthem with high trust values. Computing reputation of one userwithin a network requires knowledge of trust degrees betweenthe users. In this paper, we develop a new Fuzzy ClusteringReputation algorithm, called FCR, based on trusted network. This algorithm computes the membership degrees for each userand classifies the users of OSNs by their trust similarity suchthat most trustworthy users belong to the same cluster. Moreover, to satisfy the needs of OSNs' users by storing important trustdata in a well organized and easy to understand structure, wepropose to enrich the Friend of Friend (FOAF) vocabulary withthe reputation of users. Experimental results with data from thereal OSN, Twitter, show that our work generates high qualityresults.
KW - Clustering
KW - Fuzzy trust
KW - Reputation
KW - Social networks
UR - https://www.scopus.com/pages/publications/85032333603
U2 - 10.1109/Trustcom/BigDataSE/ICESS.2017.288
DO - 10.1109/Trustcom/BigDataSE/ICESS.2017.288
M3 - Conference contribution
AN - SCOPUS:85032333603
T3 - Proceedings - 16th IEEE International Conference on Trust, Security and Privacy in Computing and Communications, 11th IEEE International Conference on Big Data Science and Engineering and 14th IEEE International Conference on Embedded Software and Systems, Trustcom/BigDataSE/ICESS 2017
SP - 586
EP - 593
BT - Proceedings - 16th IEEE International Conference on Trust, Security and Privacy in Computing and Communications, 11th IEEE International Conference on Big Data Science and Engineering and 14th IEEE International Conference on Embedded Software and Systems, Trustcom/BigDataSE/ICESS 2017
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 16th IEEE International Conference on Trust, Security and Privacy in Computing and Communications, 11th IEEE International Conference on Big Data Science and Engineering and 14th IEEE International Conference on Embedded Software and Systems, Trustcom/BigDataSE/ICESS 2017
Y2 - 1 August 2017 through 4 August 2017
ER -