In this book we provide two major case studies to demonstrate each of these opportunities. The first case study shows the possibilities of tracking a research community over the Web, combining the information obtained from the Web with other
data sources (publications, emails). The results are analyzed and correlated with performance measures, trying to predict what kind of social networks help researchers
succeed (Chapter 8). Social network mining from theWeb plays an impotant role in this case study for obtaining large scale, dynamic network data beyond the possibilities of survey methods. In turn semantic technology is the key to the representation and aggregation of information from multiple heterogeneous information sources (Chapters 4 and 5).
As the methods we are proposing are more generally applicable than the context of our scientometric study, most of this volume is spent on describing our methods rather than discussing the results. We summarize the possibilities for (re)using electronic data for network analysis in Chapter 3 and evaluate two methods of social network mining from theWeb in a separate study described in Chapter 7.We discuss semantic technology for social network data aggregation in Chapters 4 and 5. Lastly, we describe the implementation of our methods in the award-winning Flink system in Chapter 6. In fact these descriptions should not only allow the reader to reproduce
our work, but to apply our methods in a wide range of settings. This includes
adapting our methods to other social settings and other kinds of information sources, while preserving the advantages of a fully automated analysis process based on electronic data.
Our second study highlights the role of the social context in user-generated classifications of content, in particular in the tagging systems known as folksonomies
(Chapter 9). Tagging is widely applied in organizing the content in many Web 2.0
services, including the social bookmarking application del.icio.us and the photo sharing site Flickr. We consider folksonomies as lightweight semantic structures where
the semantics of tags emerges over time from the way tags are applied. We study
tagging systems using the concepts and methodology of network analysis. We establish
that folksonomies are indeed much richer in semantics than it might seem at
first and we show the dependence of semantics on the social context of application.
These results are particularly relevant for the development of the Semantic Web using
bottom-up, collaborative approaches. Putting the available knowledge in a social
context also opens the way to more personalized applications such as social search.
As the above descriptions show, both studies are characterized by an interdisciplinary
approach where we combine the concepts and methods of Artificial Intelligence with those of Social Network Analysis. However, we will not assume any particularly knowledge of these fields on the part of the reader and provide the necessary
introductions to both (Chapters 1 and 2). These introductions should allow access to our work for both social scientists with an interest in electronic data and for information scientists with an interest in social-semantic applications.
Our primary goal is not to teach any of these disciplines in detail but to provide an insight for both Social and Information Scientists into the concepts and methods from outside their respective fields. We show a glimpse of the benefits that this understanding could bring in addressing complex outstanding issues that are inherently
interdisciplinary in nature. Our hope is then to inspire further creative experimentation toward a better understanding of both online social interaction and the nature of human knowledge. Such understanding will be indispensable in a world where the border between these once far-flung disciplines is expected to shrink rapidly through more and more socially immersive online environments such as the virtual worlds of Second Life. Only when equipped with the proper understanding will we succeed in designing systems that show true intelligence in both reasoning and social capabilities and are thus able to guide us through an ever more complex online universe.
The Author would like to acknowledge the support of the Vrije Universiteit Research
School for Business Information Sciences (VUBIS) in conducting the research contained in this volume.
Download
Another Social Network Books
Another Semantic Web Books
No comments:
Post a Comment