Last week, William Webberley of Cardiff University, gave a fascinating talk to the Agents and Intelligent Systems Group of the Department of Informatics at King’s on his research looking at retweets on Twitter. The audience comprised members of our Agents and Intelligent Systems Group and our Centre for Telecommunications Research.
Will gave an overview of his PhD research from his initial work on retweet behaviours and propagation characteristics through to studies of the properties exhibited by Twitter’s social graph and the effects that the interconnection of users have on message dissemination. He also outlined methods for identifying interesting content on Twitter and demonstrating its relative strengths and weaknesses, as validated by crowd-sourced assessments using Mechanical Turk. Part of his work involved the development of a multi-agent computational model, to simulate retweeting behaviours. The slides for his talk can be found here.
For me, a key question is this: Interesting tweets typically get retweeted, but are all retweeted tweets interesting? They may well be interesting to the connected group of people who retweet them, but are they interesting in general? Indeed, is anything “interesting in general”? And if the writers, readers, and retweeters of tweets are predominantly software agents, what does that say about interestingness? Do androids dream of electric sheep?
Big social data repository opened to everybody – Partnership between Department of Informatics at King’s College London and Affectv
Nowadays, we read more and more about big data and how they can be used by companies to their “business advantage”. For the last few years, companies gathered large datasets about their customers, employees, partners, etc. The challenge now is to analyze those data in a way that enables us to discover underlying patterns and trends, and from the business perspective to turn this knowledge into measurable profit.
It is not easy to mine meaningful information from an endless number of bits gathered in our computer systems. Things get even more complicated when we consider data that describes people and their activities as in such a case we have not only information about individuals but also their interactions with others. This means that we have to dig into a large graph that represents this web of connections.
Social targeting company Affectv is one of the businesses that understands the urgent need to look closer at the assets they have. Yes, data is an asset, a very valuable one. Thus, they decided to open up its aggregated social data for a limited period. The Open Graph Initiative kicks off with the Department of Informatics at King’s College London and will roll out to Edinburgh University and Indian Institute of Technology with the aim of sparking innovation within the social media interaction industry.
This partnership aims to help to uncover insights and trends in how social interaction across media platforms affects certain outcomes, for example:
• Can you identify interests based on someone’s social graph?
• Can you infer brand favourability through analysis of a person’s social graph?
• Can you predict purchase intent from social endorsement?
• What social signals reveal the strength of a social connection?
The Open Graph Initiative is organized in a form of challenge that is open to everybody who wants to be involved. It will consist of two open challenges per quarter. Each quarter, Affectv will release the results on its website. Credit will be cited for the relevant parties that uncover the most interesting insights on human behaviour on the social web and will receive press coverage.
So if you are interested in mining big social data – start now! Go to http://affectv.co.uk/opengraphinitiative or contact me (email@example.com)
Our very own Katarzyna Musial has a recent paper in the refereed academic journal, World Wide Web, which is now the most-downloaded paper in the journal (in the past 30 and the past 90 days). The paper, written with Przemysław Kazienko, is entitled, “Social networks on the Internet” (World Wide Web, in press, published online January 2012), and is available here.
The rapid development and expansion of the Internet and the social–based services comprised by the common Web 2.0 idea provokes the creation of the new area of research interests, i.e. social networks on the Internet called also virtual or online communities. Social networks can be either maintained and presented by social networking sites like MySpace, LinkedIn or indirectly extracted from the data about user interaction, activities or achievements such as emails, chats, blogs, homepages connected by hyperlinks, commented photos in multimedia sharing system, etc. A social network is the set of human beings or rather their digital representations that refer to the registered users who are linked by relationships extracted from the data about their activities, common communication or direct links gathered in the internet–based systems. Both digital representations named in the paper internet identities as well as their relationships can be characterized in many different ways. Such diversity yields for building a comprehensive and coherent view onto the concept of internet– based social networks. This survey provides in–depth analysis and classification of social networks existing on the Internet together with studies on selected examples of different virtual communities.
- Applications of computing
- Automated Trading
- Computer Industry
- Cyber security
- Department of Informatics
- Informatics Colloquia
- Informatics Distinguished Lectures
- Informatics Revolution
- Information Theory
- Logic Programming
- Network science
- Semantic Web
- Smart cities
- Social networking
- The Internet
- Theoretical Computer Science