Originator or propagator? Incorporating social role theory into topic models for twitter content analysis

A large number of studies have been devoted to modeling the contents and interactions between users on Twitter. In this paper, we propose a method inspired from Social Role Theory (SRT), which assumes that a user behaves differently in different roles in the generation process of Twitter content. We consider the two most distinctive social roles on Twitter: originator and propagator, who respectively posts original messages and retweets or forwards the messages from others. In addition, we also consider role-specific social interactions, especially implicit interactions between users who share some common interests. All the above elements are integrated into a novel regularized topic model. We evaluate the proposed method on real Twitter data. The results show that our method is more effective than the existing ones which do not distinguish social roles. Copyright 2013 ACM.

Automatic labelling of topic models learned from Twitter by summarisation

Latent topics derived by topic models such as Latent Dirichlet Allocation (LDA) are the result of hidden thematic structures which provide further insights into the data. The automatic labelling of such topics derived from social media poses however new challenges since topics may characterise novel events happening in the real world. Existing automatic topic labelling approaches which depend on external knowledge sources become less applicable here since relevant articles/concepts of the extracted topics may not exist in external sources. In this paper we propose to address the problem of automatic labelling of latent topics learned from Twitter as a summarisation problem. We introduce a framework which apply summarisation algorithms to generate topic labels. These algorithms are independent of external sources and only rely on the identification of dominant terms in documents related to the latent topic. We compare the efficiency of existing state of the art summarisation algorithms. Our results suggest that summarisation algorithms generate better topic labels which capture event-related context compared to the top-n terms returned by LDA. �� 2014 Association for Computational Linguistics.

Dynamic joint sentiment-topic model

Social media data are produced continuously by a large and uncontrolled number of users. The dynamic nature of such data requires the sentiment and topic analysis model to be also dynamically updated, capturing the most recent language use of sentiments and topics in text. We propose a dynamic Joint Sentiment-Topic model (dJST) which allows the detection and tracking of views of current and recurrent interests and shifts in topic and sentiment. Both topic and sentiment dynamics are captured by assuming that the current sentiment-topic-specific word distributions are generated according to the word distributions at previous epochs. We study three different ways of accounting for such dependency information: (1) Sliding window where the current sentiment-topic word distributions are dependent on the previous sentiment-topic-specific word distributions in the last S epochs; (2) skip model where history sentiment topic word distributions are considered by skipping some epochs in between; and (3) multiscale model where previous long- and shorttimescale distributions are taken into consideration. We derive efficient online inference procedures to sequentially update the model with newly arrived data and show the effectiveness of our proposed model on the Mozilla add-on reviews crawled between 2007 and 2011. �� 2013 ACM 2157-6904/2013/12-ART5 $ 15.00.

Incorporating social role theory into topic models for social media content analysis

In this paper, we explore the idea of social role theory (SRT) and propose a novel regularized topic model which incorporates SRT into the generative process of social media content. We assume that a user can play multiple social roles, and each social role serves to fulfil different duties and is associated with a role-driven distribution over latent topics. In particular, we focus on social roles corresponding to the most common social activities on social networks. Our model is instantiated on microblogs, i.e., Twitter and community question-answering (cQA), i.e., Yahoo! Answers, where social roles on Twitter include "originators" and "propagators", and roles on cQA are "askers" and "answerers". Both explicit and implicit interactions between users are taken into account and modeled as regularization factors. To evaluate the performance of our proposed method, we have conducted extensive experiments on two Twitter datasets and two cQA datasets. Furthermore, we also consider multi-role modeling for scientific papers where an author's research expertise area is considered as a social role. A novel application of detecting users' research interests through topical keyword labeling based on the results of our multi-role model has been presented. The evaluation results have shown the feasibility and effectiveness of our model.

Resource enclavity and corporate social responsibility in Sub-Saharan Africa:the case of oil production in Ghana

Why has Corporate Social Responsibility (CSR) yielded such disappointing outcomes in oil-rich sub-Saharan Africa? Over the past decades, a sizable body of literature has emerged which draws attention to the shortcomings of oil-related development and complementary CSR exercises in the region. Most critiques on the topic, however, assess specific interventions and/or policies but fail to evaluate the complex decision-making processes, dictated heavily by setting, which produce such actions altogether. This thesis attributes CSR outcomes in oil-rich sub-Saharan Africa to the unique context in which the decisions underpinning actions take place. In doing so, the analysis borrows ideas from a diverse body of literature spanning the international development, accounting, management and political science disciplines. To explore these ideas further, the thesis focuses on the case of Ghana. The most recent ���addition��� to sub-Saharan Africa���s oil club, Ghana provides a rare glimpse of how decisions underpinning CSR have been identified, evolved and reshaped from the outset. To provide a comprehensive picture of CSR in the sector and its impacts at the local level, interviews and focus groups were conducted with a range of stakeholder groups. As is the case throughout sub-Saharan Africa, in Ghana, oil production occurs in offshore ���enclaves���, which are disconnected geographically from local communities. This thesis argues that these dynamics have important implications for CSR. Findings point to companies also being disconnected ideologically from local development needs, which, in part explains the questionable CSR that has become such a contentious issue in the debate on oil and development in sub-Saharan Africa in recent years. The enclave-type setting in which oil production occurs appears to have stifled creativity and innovation in the area of CSR. This, along with institutional weaknesses, regulatory deficiencies and the Government of Ghana���s failure to adequately respond to local-level concerns, has produced these outcomes.

From Spanish paintings to murder:topic transitions in casual conversations between native and non-native speakers of English

This article explores some of the strategies used by international students of English to manage topic shifts in casual conversations with English-speaking peers. It therefore covers aspects of discourse which have been comparatively under-researched, and where research has also tended to focus on the problems rather than the communicative achievements of non-native speakers. A detailed analysis of the conversations under discussion, which were recorded by the participants themselves, showed that they all flowed smoothly, and this was in large measure due to the ways in which topic shifts were managed. The paper will focus on a very distinct type of topic shift, namely that of topic transitions, which enable a smooth flow from one topic to another, but which do not explicitly signal that a shift is taking place. It will examine how the non-native speakers achieved coherence in the topic transitions which they initiated, which strategies or procedures they employed, and show how their initiations were effective in enabling the proposed topic to be understood, taken up and developed. It therefore adds to our understanding of the interactional achievements of international speakers in informal, social contexts. �� 2013 Elsevier B.V.

Producing facial composite sketches in remote cognitive interviews:a preliminary investigation

Justice systems around the world are increasingly turning to videoconferencing as a means to reduce delays and reduce costs in legal processes. This preliminary research examined whether interviewing a witness remotely - without physical co-presence of the witness and interviewer - could facilitate the production of quality facial composite sketches of suspects. In Study 1, 42 adults briefly viewed a photograph of a face. The next day they participated in Cognitive Interviews with a forensic artist, conducted either face-to-face or remotely via videoconference. In Study 2, 20 adults participated in videoconferenced interviews, and we manipulated the method by which they viewed the developing sketch. In both studies, independent groups of volunteers rated the likeness of the composites to the original photographs. The data suggest that remote interviews elicited effective composites; however, in Study 1 these composites were considered poorer matches to the photographs than were those produced in face-to-face interviews. The differences were small, but significant. Participants perceived several disadvantages to remote interviewing, but also several advantages including less pressure and better concentration. The results of Study 2 suggested that different sketch presentation methods offered different benefits. We propose that remote interviewing could be a useful tool for investigators in certain circumstances. �� 2013 Taylor & Francis.

Linked knowledge sources for topic classification of microposts:a semantic graph-based approach

Short text messages a.k.a Microposts (e.g. Tweets) have proven to be an effective channel for revealing information about trends and events, ranging from those related to Disaster (e.g. hurricane Sandy) to those related to Violence (e.g. Egyptian revolution). Being informed about such events as they occur could be extremely important to authorities and emergency professionals by allowing such parties to immediately respond. In this work we study the problem of topic classification (TC) of Microposts, which aims to automatically classify short messages based on the subject(s) discussed in them. The accurate TC of Microposts however is a challenging task since the limited number of tokens in a post often implies a lack of sufficient contextual information. In order to provide contextual information to Microposts, we present and evaluate several graph structures surrounding concepts present in linked knowledge sources (KSs). Traditional TC techniques enrich the content of Microposts with features extracted only from the Microposts content. In contrast our approach relies on the generation of different weighted semantic meta-graphs extracted from linked KSs. We introduce a new semantic graph, called category meta-graph. This novel meta-graph provides a more fine grained categorisation of concepts providing a set of novel semantic features. Our findings show that such category meta-graph features effectively improve the performance of a topic classifier of Microposts. Furthermore our goal is also to understand which semantic feature contributes to the performance of a topic classifier. For this reason we propose an approach for automatic estimation of accuracy loss of a topic classifier on new, unseen Microposts. We introduce and evaluate novel topic similarity measures, which capture the similarity between the KS documents and Microposts at a conceptual level, considering the enriched representation of these documents. Extensive evaluation in the context of Emergency Response (ER) and Violence Detection (VD) revealed that our approach outperforms previous approaches using single KS without linked data and Twitter data only up to 31.4% in terms of F1 measure. Our main findings indicate that the new category graph contains useful information for TC and achieves comparable results to previously used semantic graphs. Furthermore our results also indicate that the accuracy of a topic classifier can be accurately predicted using the enhanced text representation, outperforming previous approaches considering content-based similarity measures. �� 2014 Elsevier B.V. All rights reserved.

How to Select a Topic for a Project

������������ ����������������-���������������� - �� �������������������� ������������ ���� ������������������ ������������ ���� �������� ������ ������������������������ ���� �������������� �� �������������������������� ���� �������������������� ��������������. ���������������� ���� ���������������� ���� ������������ ���� ��������. ������������������ ���� ���������������� �������� �� ������������������ ���� ��������������������, �������������������� �� ������������������������ �� ������������������������ �������������������� ���� ������������������, ���������� �� �������������� �������� �� ������������������������ ����������������.

The discursive construction of evidence in police interviews:case study of a rape suspect

This article presents an analysis of the discursive construction of evidence in an English police interview with a rape suspect. The analytic findings differ from previous research on police���suspect interview discourse, in that here the interviewers actively lead an interviewee to produce defence evidence. The article seeks to make the following contributions: (i) it demonstrates the interactional mechanisms through which the interviewers co-construct the interviewee���s own version of events, and highlights the potential legal ramifications by focusing on the construction of one key evidential aspect, namely, consent; (ii) it lends weight to the hypothesis that interviewer agendas are strongly determinative of interview outcomes in terms of the evidential account produced, while making the important new contribution of showing that this is not simply a case of police interviewers being inevitably prosecution-focused; and (iii) it aims to provoke further investigation into the significance of interviewer discursive influence in cases where consent is at issue, against a backdrop of increasing numbers of rape cases being discontinued by the police at this early stage of the criminal justice process.

Topic Segmentation: How Much Can We Do by Counting Words and Sequences of Words

In this paper, we present an innovative topic segmentation system based on a new informative similarity measure that takes into account word co-occurrence in order to avoid the accessibility to existing linguistic resources such as electronic dictionaries or lexico-semantic databases such as thesauri or ontology. Topic segmentation is the task of breaking documents into topically coherent multi-paragraph subparts. Topic segmentation has extensively been used in information retrieval and text summarization. In particular, our architecture proposes a language-independent topic segmentation system that solves three main problems evidenced by previous research: systems based uniquely on lexical repetition that show reliability problems, systems based on lexical cohesion using existing linguistic resources that are usually available only for dominating languages and as a consequence do not apply to less favored languages and finally systems that need previously existing harvesting training data. For that purpose, we only use statistics on words and sequences of words based on a set of texts. This solution provides a flexible solution that may narrow the gap between dominating languages and less favored languages thus allowing equivalent access to information.

A Statistical Approach for Multilingual Document Clustering and Topic Extraction from Clusters

2000 Mathematics Subject Classification: 62H30

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.

Exploring how social workers experience and cope with public perception of their profession

The public���s perception of the social work profession is a rarely considered perspective, and yet a topic that is a concern to front Thepublic���sperceptionofthesocialworkprofessionisararelyconsideredperspective and yet a topic that is a concern to front line professionals. This paper explores how social workers experience and attempt to cope with public perception of their profession. It highlights the impact of these concerns on social workers��� personal experiences and professional practice. Using semi-structured interviews with sixteen UK social workers, from local authorities and private organisations,we explore the experiences of this group.Thematic analysis of the data identified four concerns: the experience of public perception, drivers of public perception, coping with public perception, and mechanisms to raise the professions profile. Examining public perception through the eyes of social workers provides valuable insights into the lived experiences of these professionals, and offers practical implications at both the micro and macro levels. It reveals two key ways in which the profession can begin to address the prevailing negative perception considered to be emanating from the public: through developing a more co-operative relationship with external sources of public perception (e.g. government and the media) and by engaging in more pro-active self-promotion of the service.