Funded PhD position in Dynamic Network Analysis (Ireland)

The Unit for Information Mining and Retrieval (http://uimr.deri.ie) invites applications for a funded PhD Studentship as part of the Clique Research Cluster at DERI. At the Clique Research Cluster (http://www.cliquecluster.org), we are investigating and analysing how very large real-life social networks, on-line forums, biological networks and other networks of interest evolve. Some areas we are interested in include:

• Analysing how communities in these networks form and change with time;
• Analysing how information and innovation diffuses and formulating models to describe the observed diffusion behaviour;
• Analysing churn in online communities and mobile call networks.

The Candidate

We are seeking applications for a PhD candidature in dynamic graph analysis. The successful candidate will analyse how particular properties of the networks change, and use network changes to detect abnormal events or to predict how information diffusion is enhanced or hampered. The successful candidate should have a bachelors degree in computer science, maths, science or engineering, and have the pre-requisites for PhD studies at NUI Galway (http://www.nuigalway.ie).

The PhD studentship covers academic fees and includes a generous stipend for a four year period. In addition, desired, though not necessary, requirements are:

• Familiarity with basic graph theory (e.g., finding connected components, shortest paths);
• Familiarity with modelling and simulation;
• Familiarity with social network analysis;
• Familiarity with dynamic data analysis (e.g., data streaming algorithms, incremental algorithms);
• Familiarity with text mining, feature extraction and machine learning;
• Masters or equivalent degree in graph analysis, modelling or social network analysis.

The successful candidate will work with the PI Dr. Conor Hayes and Dr. Jeffrey Chan as part of the Clique Research Cluster at DERI, NUI Galway.


Application

Interested applicants should send an application with the subject header CLIQUE_PhD_09 to conor.hayes@deri.org. The application should contain a CV, a one page statement explaining how the candidate's background is compatible with the aims of the Clique Research Cluster and a list of references.


Vía Social Media Research Mail-list

The Future of Social Networks

Before Christmas, I wrote a post in my Spanish blog Sistemas Inteligentes (Intelligent Systems) containing some reflexions about the future of Social Networks. I try to resume the main idea and translate to English in this post, as I think Social Networks, and all Social Media are a really interesing field to KDD.

As stated by Wikipedia, "Emergence is the way complex systems and patterns arise out of a multiplicity of relatively simple interactions. Emergence is central to the theories of integrative levels and of complex systems". Some strong ideas in AI are connected with emergence, like Swarm Intelligence that "is a type of artificial intelligence based on the collective behavior of decentralized, self-organized systems. The expression was introduced by Gerardo Beni and Jing Wang in 1989, in the context of cellular robotic systems".


But now, what does emergence have in common with Social Networks? For me there is a clear similarity: both emergent systems and social networks present a group of individuals interacting among them to form something bigger. In emergent systems that group of, let's say stupid or limited, individuals are able to connect among themselves to create some kind of cooperative organism that is more intelligent than the union of the intelligences of the individuals. In today's Social Networks (refering to the Social Networks applications like Facebook or MySpace) we have a really better initial state, we have a group of intelligent individual cooperating among them, but the result is not the expected, because the global information is just the union (or even less, as some information may be duplicated) of the information generated by each user. But it's even worse, the global intelligence of the system is almost null, as today's Social Network systems are all about information and are not trying to create a superior layer of the system by processing all that information and creating real knowledge.

For me, it's clear that the future of Social Networks is about developing systems that generates added value to the users by processing all the information and connexions. Next years, Social Networks will need to use KDD techniques and I'me sure Social Media will become the next big application field for KDD and Machine Learning.

CFPS on Social Networks

In recent months, I've been developing software for my new company, a social network for videogamers, Wipley. That has awaken interests on all the stuff related to Social Network analysis. Last days, I've received a couple of call for papers related to this topic, that seems very interesting:

• Call for papers: 3rd International Conference on Weblogs and Social Media.
• Call for book chapters: Computational Social Network Analysis: Trends, Tools and Research Advance.