Real-time detection, tracking, and monitoring of automatically discovered events in social media

We introduce ReDites, a system for realtime event detection, tracking, monitoring and visualisation. It is designed to assist Information Analysts in understanding and exploring complex events as they unfold in the world. Events are automatically detected from the Twitter stream. Then those that are categorised as being security-relevant are tracked, geolocated, summarised and visualised for the end-user. Furthermore, the system tracks changes in emotions over events, signalling possible flashpoints or abatement. We demonstrate the capabilities of ReDites using an extended use case from the September 2013 Westgate shooting incident. Through an evaluation of system latencies, we also show that enriched events are made available for users to explore within seconds of that event occurring.

Ageing factor:a potential altmetric for observing events and attention spans in microblogs

We present an initial examination of the (alt)metric ageing factor to study posts in Twitter. Ageing factor was used to characterize a sample of tweets, which contained a variety of astronomical terms. It was found that ageing factor can detect topics that both cause people to retweet faster than baseline values, and topics that hold people’s attention for longer than baseline values.

A weakly-supervised Bayesian model for violence detection from social media

Social streams have proven to be the mostup-to-date and inclusive information on cur-rent events. In this paper we propose a novelprobabilistic modelling framework, called violence detection model (VDM), which enables the identification of text containing violent content and extraction of violence-related topics over social media data. The proposed VDM model does not require any labeled corpora for training, instead, it only needs the in-corporation of word prior knowledge which captures whether a word indicates violence or not. We propose a novel approach of deriving word prior knowledge using the relative entropy measurement of words based on the in-tuition that low entropy words are indicative of semantically coherent topics and therefore more informative, while high entropy words indicates words whose usage is more topical diverse and therefore less informative. Our proposed VDM model has been evaluated on the TREC Microblog 2011 dataset to identify topics related to violence. Experimental results show that deriving word priors using our proposed relative entropy method is more effective than the widely-used information gain method. Moreover, VDM gives higher violence classification results and produces more coherent violence-related topics compared toa few competitive baselines.

From icon to naturalised icon:a linguistic analysis of media representations of the BP Deepwater Horizon crisis

This research explores how news media reports construct representations of a business crisis through language. In an innovative approach to dealing with the vast pool of potentially relevant texts, media texts concerning the BP Deepwater Horizon oil spill are gathered from three different time points: immediately after the explosion in 2010, one year later in 2011 and again in 2012. The three sets of 'BP texts' are investigated using discourse analysis and semi-quantitative methods within a semiotic framework that gives an account of language at the semiotic levels of sign, code, mythical meaning and ideology. The research finds in the texts three discourses of representation concerning the crisis that show a movement from the ostensibly representational to the symbolic and conventional: a discourse of 'objective factuality', a discourse of 'positioning' and a discourse of 'redeployment'. This progression can be shown to have useful parallels with Peirce's sign classes of Icon, Index and Symbol, with their implied movement from a clear motivation by the Object (in this case the disaster events), to an arbitrary, socially-agreed connection. However, the naturalisation of signs, whereby ideologies are encoded in ways of speaking and writing that present them as 'taken for granted' is at its most complete when it is least discernible. The findings suggest that media coverage is likely to move on from symbolic representation to a new kind of iconicity, through a fourth discourse of 'naturalisation'. Here the representation turns back towards ostensible factuality or iconicity, to become the 'naturalised icon'. This work adds to the study of media representation a heuristic for understanding how the meaning-making of a news story progresses. It offers a detailed account of what the stages of this progression 'look like' linguistically, and suggests scope for future research into both language characteristics of phases and different news-reported phenomena.

Harnessing linked knowledge sources for topic classification in social media

Topic classification (TC) of short text messages offers an effective and fast way to reveal events happening around the world ranging from those related to Disaster (e.g. Sandy hurricane) to those related to Violence (e.g. Egypt revolution). Previous approaches to TC have mostly focused on exploiting individual knowledge sources (KS) (e.g. DBpedia or Freebase) without considering the graph structures that surround concepts present in KSs when detecting the topics of Tweets. In this paper we introduce a novel approach for harnessing such graph structures from multiple linked KSs, by: (i) building a conceptual representation of the KSs, (ii) leveraging contextual information about concepts by exploiting semantic concept graphs, and (iii) providing a principled way for the combination of KSs. Experiments evaluating our TC classifier in the context of Violence detection (VD) and Emergency Responses (ER) show promising results that significantly outperform various baseline models including an approach using a single KS without linked data and an approach using only Tweets. Copyright 2013 ACM.