Loading...
3 results
Search Results
Now showing 1 - 3 of 3
- A Novel Multi-View Ensemble Learning Architecture to Improve the Structured Text ClassificationPublication . Gonçalves, Carlos Adriano; Vieira, Adrián Seara; Talma Gonçalves, Célia; Camacho, Rui; Iglesias, Eva Lorenzo; Diz, Lourdes BorrajoMulti-view ensemble learning exploits the information of data views. To test its efficiency for full text classification, a technique has been implemented where the views correspond to the document sections. For classification and prediction, we use a stacking generalization based on the idea that different learning algorithms provide complementary explanations of the data. The present study implements the stacking approach using support vector machine algorithms as the baseline and a C4.5 implementation as the meta-learner. Views are created with OHSUMED biomedical full text documents. Experimental results lead to the sustained conclusion that the application of multi-view techniques to full texts significantly improves the task of text classification, providing a significant contribution for the biomedical text mining research. We also have evidence to conclude that enriched datasets with text from certain sections are better than using only titles and abstracts
- Developing integrated performance dashboards visualisations using power BI as a PlatformPublication . Gonçalves, Célia Talma; Gonçalves, Maria José Angélico; Campante, M.I.The rapid advance of business technologies in recent years has made knowledge an essential and strategic asset that determines the success or failure of an organisation. Access to the right information in real time and with high selectivity can be a competitive advantage in the business environment. Business intelligence systems help corporate executives, business managers, and other operational workers make better and more informed business decisions. This study aimed to assess the impact of using business intelligence tools on the decision-making process in organisations, specifically in sales marketing. The methodology applied to realise the study’s objective was the Vercellis methodology. A set of data available on the sales marketing website SuperDataScience was used to implement a set of pressing KPIs for the business decision-making process in the area. Using these data, a complete business intelligence system solution was implemented. A data warehouse was created using the ETL (extract–transform–load) process, and the data were then explored using a set of dynamics dashboards with a view of the business metrics. The results showed the use of business intelligence systems that allow the integration and transformation of data from various sources stored in data warehouses, where it is possible to implement KPIs and carry out quick, concise, easy-to-interpret graphical analyses. This paper contributes to a better understanding of the importance of data-integrated dashboard visualisation for the decision-making process.
- Business Intelligence como driver da Análise de Indicadores AcadémicosPublication . Dias, Bruno; Gonçalves, Célia Talma; Moreira Silva, ManuelO presente artigo aborda o Business Intelligence sob a perspetiva da sua utilidade enquanto driver para a análise de indicadores académicos. Sendo este um conceito de relevo no campo da análise de dados e do apoio ao processo de tomada de decisão, pretende-se demonstrar os benefícios da implementação de um sistema de Business Intelligence numa instituição académica. De forma a atingir esse objetivo principal, é realizada uma introdução de conceitos para estabelecer uma base de conhecimento para o leitor e clarificar o espectro de investigação que se pretende trabalhar. De seguida, é apresentada a metodologia utilizada na criação deste artigo, quais os resultados obtidos e qual a análise crítica que é feita da investigação produzida. Este artigo tem por base uma metodologia narrativa, assente num levantamento bibliográfico extenso, sendo em seguida selecionados vários autores relevantes para o tema segundo os critérios estabelecidos. Apresenta-se, depois, uma revisão de literatura a partir de uma perspetiva de abordagem inicial e não exaustiva, onde se expõem diferentes visões da aplicação do business intelligence, especificamente em contextos académicos. Verifica-se a existência de melhorias positivas nos casos em que estes modelos são aplicados e as conclusões daqui retiradas servirão de base para a construção e implementação de um sistema de Business Intelligence que ofereça suporte à gestão de um centro de investigação em contexto académico.