The fields of computational intelligence and knowledge management have made significant advances over the past decades. The potential ability to create intelligence from the analysis of raw data has been successfully applied to diverse areas such as business, industry, sciences, social media etc. Online social networks and their combination with recommender systems created new opportunities for businesses that consider the social influence important for their product marketing, as well as the social networks that want to improve the user experience by personalizing the content that is provided to each user and enabling new connections. At the same time, these changes have created new challenges for researchers in the area of recommender systems and social network analysis. The large volume of social network interactions that expand the size of the social graph with increased velocity, the variety of information provided in the form of textual reviews, ratings or permanent and volatile relations, and the veracity of data expressed in the form of trust or distrust between users who become product reviewers or opinion influencers, are only some of the factors that make social networks and the associated recommender systems an ideal case of big-data research.

In this special issue we invite papers focusing on big data recommender systems that take advantage of the characteristics of the underlying social network and focus on the variety and volatility of social bonds, tackle the problems of size and speed of change of social graphs, test the scalability of traditional recommender systems and/or present solutions that can take recommender systems to the next level.

The issue will focus on technologies and solutions related (but not limited) to:

- Algorithms that exploit the diversity of big social graphs for improving recommendations
- Large-scale parallel and distributed implementations of recommender systems
- Incremental recommender solutions that can handle streaming data
- Real-time recommendations based on spatio-temporal features
- Innovative, concurrent, and scalable big data recommender systems
- Trust and reputation-aware social recommender systems
- Context-aware and privacy preserving social recommender systems

IMPORTANT DATES
Submission deadline: 20 June, 2016 (extended)
Notification to authors: 31 October, 2016
Submission of revised versions of manuscripts: 31 December, 2016
Final versions due: 31 January, 2017

PAPER SUBMISSION
Manuscripts must be submitted electronically through the journal web site (http://ees.elsevier.com/fgcs). Contributions must contain original unpublished work not concurrently submitted or under review anywhere else. Please select "SI: RecSysLSSN" when reaching the step of selecting article type name in submission process.

Paper length should be between 8 to 10 pages at the initial submission stage. After integration of reviewers' comments, the final length can be up to 12 pages.

GUEST EDITORS
Prof. Magdalini Eirinaki - San Jose State University
Prof. Jerry Gao - San Jose State University
Prof. Iraklis Varlamis - Harokopio University of Athens
Dr. Konstantinos Tserpes - Harokopio University of Athens