The present paper offers preliminary outcomes of a user study that investigated the acceptance of a recommender system that suggests future co-authors for scientific article writing. The recommendation approach is twofold: network information (betweenness centrality) and author (keyword) similarity are used to compute the utility of peers in a network of co-authors. Two sets of recommendations were provided to the participants: Set one focused on all candidate authors, including co-authors of a target user to strengthen current bonds and strive for acceptance of a certain research topic. Set two focused on solely new co-authors of a target user to foster creativity, excluding current co-authors. A small-scale evaluation suggests that the utilitybased recommendation approach is promising, but to maximise outcome, we need to (a) compensate for researchers' interests that change over time and (b) account for multi-person co-authored papers.Keywords: research; cooperation; network; similarity; recommender systems; utility-based; utility; betweenness centrality.Reference to this paper should be made as follows: Sie, R.L.L., Drachsler, H., Bitter-Rijpkema, M. and Sloep, P. (2012) 'To whom and why should I connect? Co-author recommendation based on powerful and similar peers', Int. J. Technology Enhanced Learning, Vol. 4, Nos. 1/2, pp.121-137.Bibliographical notes: Rory L.L. Sie is a PhD candidate in the Open Universiteit, The Netherlands. He served as chair and founder of the PhD council of the Open Universiteit in the Netherlands and chair of the PhD council of national research school SIKS. His main focus is on cooperation networks and how we can use social network analysis and game theoretic solution concepts to foster successful cooperation. In a more general sense, he is interested in how we can apply techniques from artificial intelligence (multiagent systems, intelligent virtual agents, semantic web) to education and learning.Hendrik Drachsler has more than 20 publications in the field of TechnologyEnhanced Learning and he serves as reviewer and programme committee member for international conferences, workshops, and journals. In his current 122 R.L.L. Sie et al.work, he focuses on the personalisation of information with information retrieval technologies and recommender systems. Furthermore, he is interested on research on educational datasets, linked data, learning networks, data mashups, data visualisations and learning analytics. Next to these activities he steers the Special Interest Group dataTEL of the European Association of TEL and organises an annual workshops series for relevant research topics like the SIRTEL08, SIRTEL09, RecSysTEL2010, dataTEL11.Marlies Bitter-Rijpkema works as Assistant Professor at CELSTEC/OUNL. Her research focuses on creative problem solving and knowledge building in virtual communities. Over the years, she worked in various roles in (inter)national (EU-FP7) projects (recently idSpace) and operated as liaison officer for the Dutch Digital University Consortium, accele...

By nature, learning is social. The interactions by which we learn from others inherently form a network of relationships among people, but also between people and resources. This paper gives an overview of the potential social network analysis (SNA) may have for social learning. It starts with an overview of the history of social learning and how SNA may be of value. The core of the paper outlines the state-of-art of SNA for technology-enhanced R.L.L. Sie et al.learning (TEL), by means of four possible types of SNA applications: visualisation, analysis, simulation, and interventions. In an outlook, future directions of SNA research for TEL are provided.

No abstract

Networked cooperation fails if the available partnerships remain opaque.A literature review and Delphi study uncovered the elements of a fruitful partnership. They relate to personality, diversity, cooperation, and management. Innovation networks and learning networks share the same cooperative intention, but they too often fail as members of the network do not know which partnerships are valuable. If one plans to build a support service that provides insight into the value of future cooperation, one first needs to know what contributes to effective and efficient cooperation. In addition to carrying out a literature review, we invoked the eDelphi method to answer this question. eDelphi is a method to solicit knowledge from experts anonymously and without geographical constraints. Observations from two eDelphi rounds are reported in this article. The first round focused on factor generation and determined which factors influence cooperation networks; it was conducted with two groups of six representative experts. Experts list open communication, a positive attitude, trust, keeping appointments, and personality as influential factors for cooperation networks. A team of four moderators categorised the factors in a second round, resulting in four core clusters: personal characteristics, diversity, effective cooperation, and managerial aspects. Interestingly the experts failed to list some factors that are mentioned in the literature. This finding is discussed.

This paper describes the experiments carried out in the context of the BEST-project, an interdisciplinary project with researchers from the Law faculty and the AI department of the VU University Amsterdam. The aim of the project is to provide laymen with information about their legal position in a liability case, based on retrieved case law. The process basically comes down to (1) analyzing the input of a layman in terms of a layman ontology, (2) mapping this ontology to a legal ontology, (3) retrieve relevant case law based, and finally (4) present the results in a comprehensible way to the layman. This paper describes the experiments undertaken regarding step 4, and in particular step 3.