Social network analysis has attracted much attention in recent years. Link prediction is a key research direction within this area. In this paper, we study link prediction as a supervised learning task. Along the way, we identify a set of features that are key to the performance under the supervised learning setup. The identified features are very easy to compute, and at the same time surprisingly effective in solving the link prediction problem. We also explain the effectiveness of the features from their class density distribution. Then we compare different classes of supervised learning algorithms in terms of their prediction performance using various performance metrics, such as accuracy, precision-recall, F-values, squared error etc. with a 5-fold cross validation. Our results on two practical social network datasets shows that most of the well-known classification algorithms (decision tree, k-NN, multilayer perceptron, SVM, RBF network) can predict links with comparable performances, but SVM outperforms all of them with narrow margin in all performance measures. Again, ranking of features with popular feature ranking algorithms shows that a small subset of features always plays a significant role in link prediction. 1

The term knowledge work has been used for decades, but to date there is not much understanding what knowledge workers do and how this work can be improved. This paper contributes to the development of our theoretical understanding of knowledge work by exploring use of weblogs for professional purposes: as personal knowledge repositories, learning journals or networking instruments. We draw on the results of a weblog adoption study to explore knowledge worker activities and to propose a framework for analysing knowledge work.

The growth of Web 2.0 and fundamental theoretical breakthroughs have led to an avalanche of interest in social networks. This paper focuses on the problem of modeling how social networks accomplish tasks through peer production style collaboration. We propose a general interaction model for the underlying social networks and then a specific model (iLink) for social search and message routing. A key contribution here is the development of a general learning framework for making such online peer production systems work at scale. The iLink model has been used to develop a system for FAQ generation in a social network (FAQtory), and experience with its application in the context of a full-scale learning-driven workflow application (CALO) is reported. We also discuss methods of adapting iLink technology for use in military knowledge sharing portals and a other message routing systems. Finally, the paper shows the connection of iLink to SQM, a theoretical model for social search that is a generalization of Markov Decision Processes and the popular Pagerank model.

This paper integrates the largely independent literatures on networks and teams. Our objective is twofold: (1) to understand what constitutes an effective organizational network when much of the work of the organization is done by teams; and (2) to examine what the internal and external social capital needs of teams are. We raise questions to guide future research, and point to potential managerial implications.

Abstract: In this paper we present the results of two studies aimed at understanding how employees find knowledge available in their organisation. Data about knowledge awareness and knowledge finding strategies were collected in two research organisations using interviews and on-line questionnaires. The results of the two studies demonstrate interesting patterns. First, we found that although people say that they are aware of knowledge in their organisation, they also indicate that the same knowledge is developed at different places in their organisations. Second, asking others and searching own mailbox and other own digital and paper archives – and not organisation-wide repositories – are most popular ways for finding in-house knowledge. The results are discussed in terms of implications from the perspective of employees and from the perspective of organisations.

Abstract—The vast majority of knowledge management initiatives fail because they do not take sufficiently into account the emotional, psychological and social needs of individuals. Only if users see real value for themselves will they actively use and contribute their own knowledge to the system, and engage with other users. Connection dynamics can make this easier, and even enjoyable, by connecting people and bringing them closer through shared experiences such as playing a game together. A higher connectedness of people to other people, and to relevant knowledge assets, will motivate them to participate more actively and increase system usage. In this paper, we describe the design of TENTube, a video-based connection tool we are developing to support competence development. TENTube integrates rich profiling and network visualization and navigation with agent-enhanced game-like connection dynamics. Index Terms—competence development, connection dynamics, connection games, intelligent social agents, knowledge management, learning networks, network visualization, virtual communities. I.

Virtual informal communication networks are widely recognized as an important part of corporate knowledge management (KM). Unfortunately, most practices of community-engineering are characterized by intuitive actions from KM managers rather than systematic network development based on detailed analysis. Therefore, as part of a larger research framework, this paper addresses topological structures as action variable of communityengineering. A dynamic computer-based simulation model is introduced and applied to real-life data from over 800 students and staff of the Economics and Business Administration Department at Frankfurt University, Germany. Several metrics of networks performance are developed and illustrated using different exemplary actions of community-engineering.

Despite the high availability of mobile phones and personal digital assistants with online capabilities, mobile computer supported cooperative workis still in its infancy. So far, only little is known about the distinct attributes of mobile cooperative work in comparison to its stationary counterpart. Across which dimensions does cooperation via mobile devices differ from traditional hard-onal settings and what implications have to be drawn for future research? To bring more light to this question, we conducted an experimental business-alk at Frankfurt University with 16 graduate students and analysed their collaborative behaviour across mobile and non-F:1kD channels of communication over a 5 weekperiod. We find that mobile messages differed from stationary messages in terms of size and that the use of mobile emails prevailed over stationary emails under conditions of stress. Finally, we found that the social structure of mobile communication corresponded with the structure of stationary communication. This indicates that mobile communication technologies support existing communication relations rather than creating new relations. From the perspective of system designers, these results may serve as practical insights into the user behaviour of mobile technologies and might support the future development of mobile computer supported cooperative workenvironments.

Knowledge Management (KM) is one of the key issues developing a creative development infrastructure for the increasing requirements of products, facing the challenges of time-competition and building a competitive organization. The problem in realization of the KM is that it more or less falls closer to Information Management. KM can be divided into sub types; managing of explicit and tacit knowledge, and managing knowledge as social activities, which is supported by technological facilities. The aim of research was to explore the social environment of product development personnel in companies of engineer-to-order type of business where control of tacit knowledge and use of knowledge from previous work is important. The focus is in conceptualization of knowledge intensive design work from perspectives of social infrastructure, technical tools and different artifacts mediating communication, in order to have a meaningful basis for designing and using new 3D-CAD based environments.

Abstract: We propose a sensor-based organisational design and engineering (ODE) approach that combines behavioural sensor data with other sources of information such as e-mail, surveys and performance data in order to design interventions aimed at improving organisational outcomes. We discuss relevant theory and technology backgrounds and describe the general requirements of a sensor-based organisational design and engineering system. We present an experimental platform that combines sensor measurements, pattern recognition algorithms, statistical analysis, social network analysis and feedback mechanisms to study the relationship between social signalling behaviour and face-to-face (f2f) interaction networks, with job attitudes and performance. We describe three case studies that we have conducted in several organisations using our experimental platform and the methodology that we have followed. The first study looks at e-mail and f2f networks in a marketing division of a bank. The second study analyses the effects of nurses ’ social behaviour on patients ’ length of stay in the post-anaesthesia care unit of a hospital. Finally, the third study analyses the effects of retail bank employees ’ social behaviour on sales performance.