Business intelligence in banking: A literature analysis from 2002 to 2013 using Text Mining and latent Dirichlet allocation

telligence applications for the banking industry. Searches were performed in relevant journals resulting in 219 articles published between 2002 and 2013. To analyze such a large number of manuscripts, text mining techniques were used in pursuit for relevant terms on both business intelligence and banking domains. Moreover, the latent Dirichlet allocation modeling was used in or- der to group articles in several relevant topics. The analysis was conducted using a dictionary of terms belonging to both banking and business intelli- gence domains. Such procedure allowed for the identification of relationships between terms and topics grouping articles, enabling to emerge hypotheses regarding research directions. To confirm such hypotheses, relevant articles were collected and scrutinized, allowing to validate the text mining proce- dure. The results show that credit in banking is clearly the main application trend, particularly predicting risk and thus supporting credit approval or de- nial. There is also a relevant interest in bankruptcy and fraud prediction. Customer retention seems to be associated, although weakly, with targeting, justifying bank offers to reduce churn. In addition, a large number of ar- ticles focused more on business intelligence techniques and its applications, using the banking industry just for evaluation, thus, not clearly acclaiming for benefits in the banking business. By identifying these current research topics, this study also highlights opportunities for future research.

Text mining na análise de sentimentos em contextos de big data

Dissertação de mestrado integrado em Engenharia e Gestão de Sistemas de Informação

Integration methods in dynamic analysis

"Series title: Springerbriefs in applied sciences and technology, ISSN 2191-530X"

Media(ted) discourse and society: rethinking the framework of critical discourse analysis

The analysis of journalistic discourse and its social embeddedness has known significant advances in the last two decades, especially due to the emergence and development of Critical Discourse Analysis. However, three important aspects remain under-researched: the time plane in discourse analysis, the discursive strategies of social actors, and the extra- and supra-textual effects of mediated discourse. Firstly, understanding the biography of public matters requires a longitudinal examination of mediated texts and their social contexts but most forms of analysis of journalistic discourse do not account for the time sequence of texts and its implications. Secondly, as the media representation of social issues is, to a large extent, a function of the discursive construction of events, problems and positions by social actors, the discursive strategies that they employ in a variety of arenas and channels ‘‘before’’ and ‘‘after’’ journalistic texts need to be examined. Thirdly, the fact that many of the modes of operation of discourse are extra- or supra-textual calls for a consideration of various social processes ‘‘outside’’ the text. This paper aims to produce a theoretical and methodological contribution to the integration of these issues in discourse analysis by proposing a framework that combines a textual dimension with a contextual one