Microblogging social media (mainly represented by Twitter) focuses on fast open real-time communication using short messages between users and their followers. These platforms generate large amounts of content and community finding techniques are an attractive alternative for organising it. However there is no clear agreement in the literature for a definition of user community for the microblogging use case, leading to unreliable ground-truth data and evaluation. In this work, we differentiate between functional and structural definitions of communities for microblogging. A functional community groups its users by a common independent social function, e.g. fans of the same football team, while in a structural community the members exclusively depend on their connectivity in a network, e.g. modularity. We build and characterise eight types of functional communities to be used as user-labelled ground-truth and five types of live user interactions networks from Twitter. We then evaluate thirteen popular structural community definitions using five different Twitter datasets, exploring their goodness and robustness for detecting the functional ground-truth under different perturbation strategies. Our results show that definitions based on internal connectivity, e.g. Triangle Participation Ratio, Fraction Over Median Degree or Conductance work best for the Twitter use case and are very robust. On the other hand, classic scores such as Modularity are limited and do not fit very well due to the sparsity and noise of microblogging.

Maintaining online communities is vital in order to increase and retain their economic and social value. That is why community managers look to gauge the success of their communities by measuring a variety of user behaviour, such as member activity, turnover and interaction. However, such communities vary widely in their purpose, implementation and user demographics, and although many success indicators have been proposed in the literature, we will show that there is no one-fits-all approach to community success: Different success criteria depend on different user behaviour. To demonstrate this, we put together a set of user behaviour features, including many that have been used in the literature as indicators of success, and then we define and predict community success in three different types of online communities: Questions & Answers (Q&A), Healthcare and Emotional Support (Life & Health), and Encyclopaedic Knowledge Creation. The results show that it is feasible to relate community success to specific user behaviour with an accuracy of 0.67--0.93 F1 score and 0.77--1.0 AUC.

The growth in the alternative digital publishing is widening the breadth of scholarly impact beyond the conventional bibliometric community. Thus, research is becoming more reachable both inside and outside of academic institutions and are found to be shared, downloaded and discussed in social media. In this study, we linked the scientific articles found in mainstream news, weblogs and Stack Overflow to the citation database of peer-reviewed literature called Scopus. We then explored how standard graph-based influence metrics can be used to measure the social impact of scientific articles. We also proposed the variant of Katz centrality metrics called EgoMet score to measure the local importance of scientific articles in its ego network. Later we evaluated these computed graph-based influence metrics by predicting absolute citations. Our results of the prediction model describe 34% variance to predict citations from blogs and mainstream news and 44% variance to predict citations from Stack Overflow.

The realization that scholarly publications are discussed and have influence on discourse outside scientific and academic domains has given rise to area of scientometrics called alternative metrics or “altmetrics”. Furthermore, researchers in this field tend to focus primarily on measuring scientific activity on social media platforms such as Twitter, however these count-based metrics are vulnerable to gaming because they tend to lack concrete justification or reference to the primary source. In this collaboration with Elsevier, we extend the conventional citation graph to a heterogeneous graph of publications, scientists, venues, organizations and more authoritative media sources such as mainstream news and weblogs. Our approach consists of two parts: one is integrating the bibliometric data with the social data such as blogs, mainstream news. The other involves understanding how standard graph-based metrics can be used to predict the academic impact. Our result showed the computed graph-based metrics can reasonably predict the academic impact of early stage researchers.

Sensor technology and sensor networks have evolved so rapidly that they are now considered a core driver of the Internet of Things (IoT), however data analytics on IoT streams is still in its infancy. This paper introduces an approach to sensor data analytics by using the OpenIoT1middleware; real time event processing and clustering algorithms have been used for this purpose. The OpenIoT platform has been extended to support stream processing and thus we demonstrate its flexibility in enabling real time on-demand application domain analytics. We use mobile crowd-sensed data, provided in real time from wearable sensors, to analyse and infer air quality conditions. This experimental evaluation has been implemented using the design principles and methods for IoT data interoperability specified by the OpenIoT project. We describe an event and clustering analytics server that acts as an interface for novel analytical IoT services. The approach presented in this paper also demonstrates how sensor data acquired from mobile devices can be integrated within IoT platforms to enable analytics on data streams. It can be regarded as a valuable tool to understand complex phenomena, e.g., air pollution dynamics and its impact on human health.

Automated topic labelling brings benefits for users aiming at analysing and understanding document collections, as well as for search engines targetting at the linkage between groups of words and their inherent topics. Current approaches to achieve this suffer in quality, but we argue their performances might be improved by setting the focus on the structure in the data. Building upon research for concept disambiguation and linking to DBpedia, we are taking a novel approach to topic labelling by making use of structured data exposed by DBpedia. We start from the hypothesis that words co-occuring in text likely refer to concepts that belong closely together in the DBpedia graph. Using graph centrality measures, we show that we are able to identify the concepts that best represent the topics. We comparatively evaluate our graph-based approach and the standard text-based approach, on topics extracted from three corpora, based on results gathered in a crowd-sourcing experiment. Our research shows that graph-based analysis of DBpedia can achieve better results for topic labelling in terms of both precision and topic coverage.

In recent years, companies have started to utilise online social communities as a means of communicating with and targeting their employees and customers, and such online communities include discussion fora. The conversational dynamics of users in fora can influence their neighbours in the underlying social network. We make use of such influence to target specific communities with information, i.e. post in them, because a post is generally shared with the community and not just with individual users. In short, we study information diffusion across communities and show that we can achieve high community (and user) spread using an efficient targeting strategy. In order to achieve this, we use a set of novel measures for cross-community influence and show that it outperforms other targeting strategies on two different data-sets: the largest Irish online discussion system, Boards.ie, and technical support fora, SAP SCN.

Twitter's list feature allows users to organize their followees into groups for easier information access and filtering. However, the percentage of users using lists is very small and most existing lists have only a few members. One reason for this may be that curating groups of Twitter users is a time consuming task. In this paper, we propose early and late fusion methods for automatically clustering followees using both graph structure and tweet content. We evaluate our approaches using ground-truth Twitter lists crawled via the Twitter API and show that the late fusion method outperforms both the baselines and the early fusion method.

We present a component-based, conceptual architecture for Semantic Web applications. It describes the high-level functionality that substantially differentiates Resource Description Framework (RDF)-supported applications from database-driven applications. We provide a strong empirical grounding for this architecture through a survey of Semantic Web applications over most of the past decade. Our empirical approach allows us to describe the current state of the art for the development and deployment of applications on the Web of Data. In addition, we determine how far the adoption of signature research topics of the Semantic Web, such as, data reuse, data integration, and reasoning, has progressed. We, then, discuss the main implementation challenges that developers using Semantic technologies are facing, as observed in the survey. We build on this in order to suggest future approaches to facilitate the standardization of components and the development of software engineering tools to increase the uptake of the Web of Data.

In this paper we describe our novel Twitter assistant called Tadvise. Tadvise helps users to know their Twitter communities better and also assists them to identify community hubs for propagating their community-related tweets. Tadvise video describes different parts of Tadvise and how it is used for propagating tweets in Twittersphere.

In recent years, the summarisation and decomposition of social networks has become increasingly popular, from community finding to role equivalence. However, these approaches concentrate on one type of model only. Generalised blockmodelling decomposes a network into independent, interpretable, labeled blocks, where the block labels summarise the relationship between two sets of users. Existing algorithms for fitting generalised blockmodels do not scale beyond networks of 100 vertices. In this paper, we introduce two new algorithms, one based on genetic algorithms and the other on simulated annealing, that is at least two orders of magnitude faster than existing algorithms and obtaining similar accuracy. Using synthetic and real datasets, we demonstrate their efficiency and accuracy and show how generalised blockmodelling and our new approaches enable tractable network summarisation and modelling of medium sized networks. 1

Search engines like Google.com use the link structure of the Web to determine whether Web pages are authoritative sources of information. However, the linking mechanism provided by HTML does not allow the Web author to express different types of links, such as positive or negative endorsements of page content. As a consequence, search engine algorithms cannot discriminate between sites that are highly linked and sites that are highly trusted. We demonstrate our claim by running PageRank on a real world data set containing positive and negative links. We conclude that simple semantic extensions to the link mechanism would provide a richer semantic network from which to mine more precise Web intelligence.