%0 Conference Paper %B SERVICES %D 2011 %T Social Web Mashups Full Completion via Frequent Sequence Mining %A Maaradji, Abderrahmane %A Hacid, Hakim %A Skraba, Ryan %A Athena Vakali %K Mashups %K Sequence mining %K Social networks %K Web services %X

In this paper we address the problem of WebMashups full completion which consists of predicting themost suitable set of (combined) services that successfully meetthe goals of an end-user Mashup, given the current service(or composition of services) initially supplied. We model fullcompletion as a frequent sequence mining problem and weshow how existing algorithms can be applied in this context.To overcome some limitations of the frequent sequence miningalgorithms, e.g., efficiency and recommendation granularity,we propose FESMA, a new and efficient algorithm for computingfrequent sequences of services and recommending completions.FESMA also integrates a social dimension, extractedfrom the transformation of user ? service interactions intouser ? user interactions, building an implicit graph thathelps to better predict completions of services in a fashiontailored to individual users. Evaluations show that FESMAis more efficient outperforming the existing algorithms evenwith the consideration of the social dimension. Our proposalhas been implemented in a prototype, SoCo, developed at BellLabs.

%B SERVICES %I IEEE Computer Society %P 9-16 %@ 978-1-4577-0879-4 %G eng