Cookies
O website necessita de alguns cookies e outros recursos semelhantes para funcionar. Caso o permita, o INESC TEC irá utilizar cookies para recolher dados sobre as suas visitas, contribuindo, assim, para estatísticas agregadas que permitem melhorar o nosso serviço. Ver mais
Aceitar Rejeitar
  • Menu
Publicações

Publicações por LIAAD

2016

Disabling and reoperation in patients with Crohn's disease subject to early surgery or immunosuppression: a Bayesian network prognostic model

Autores
Dias, CC; Magro, F; Rodrigues, PP;

Publicação
2016 IEEE 29TH INTERNATIONAL SYMPOSIUM ON COMPUTER-BASED MEDICAL SYSTEMS (CBMS)

Abstract
Crohn's disease is one type of inflammatory bowel disease whose incidence is currently increasing, subject to relapse and disabling, with unknown etiology, and usually diagnosed between the second and third decade of life. The aim of this work is to develop a Bayesian network tool to predict disabling and reoperation in patients with Crohn's disease subject to early surgery or immunosuppressors intake. Multi-centric study data from patients with surgery or immunosuppression in the first six months after diagnosis was used, focusing on the prognosis and the analysis of factors' interaction. Patients were grouped by the index episode: immunosuppressors intake, and surgery (stratified considering the use or not of immunosuppressors 6 months after surgery). Patient group was associated with disease behavior, upper gastrointestinal tract location (L4) and age at diagnosis, while disease extent was associated to perianal disease. For disabling, association between perianal disease and gender and location was also found. Association between gender and L4 was also found for reoperation. The cross-validated discriminative power of the models were high for both disabling (above 70%) and reoperation (above 80%). The generated models presented interesting insights on factor interaction and predictive ability for the prognosis, supporting their use in future clinical decision support systems.

2016

Effect of Incomplete Meta-dataset on Average Ranking Method

Autores
Abdulrahman, SM; Brazdil, P;

Publicação
Proceedings of the 2016 Workshop on Automatic Machine Learning, AutoML 2016, co-located with 33rd International Conference on Machine Learning (ICML 2016), New York City, NY, USA, June 24, 2016

Abstract

2016

Determining the Level of Clients' Dissatisfaction from Their Commentaries

Autores
Forte, AC; Brazdil, PB;

Publicação
COMPUTATIONAL PROCESSING OF THE PORTUGUESE LANGUAGE (PROPOR 2016)

Abstract
We present a study in the area of sentiment analysis of clients' commentaries transcribed by assistants of a help-desk service of one Portuguese telecommunications company. We have adopted a lexicon-based approach to determine the polarity of the sentiment of each commentary, based on the so called opinion words. This task was by no means easy, as not many tools are available for the Portuguese language. The initial results with the off-the-shelf solutions were rather poor. This has motivated us to carry out a number of enhancements, including, for instance, enriching the given lexicon with domain specific terms, formulating specific rules for negation and amplifiers. Automatic pruning of some of the lexicon terms has led to a significant improvement in performance. As our final system achieved a very good performance, our work should be of interest to others working on domain specific solutions for languages where ready-made solutions are not available.

2016

From offshore-provider to brand creator: fsQCA of footwear industry

Autores
Meneses, R; Brito, PQ; Gomes, PC;

Publicação
JOURNAL OF BUSINESS RESEARCH

Abstract
Portugal has become the second most expensive footwear brand manufacturer in the global market in just one decade. How does an offshore-outsourcing provider become a direct competitor with former clients? This study applies a fuzzy-set qualitative comparative analysis to 12 Portuguese footwear manufacturers and identifies the underlying factors of the managerial transition from an offshore-outsourcing provider to a direct brand manufacturer. The study finds that the transformation of external knowledge from the client into internal knowledge must occur first. But the decisive factor is the management's recognition that brand creation is a long-term investment and is less risky than remaining dependent on outsourcing. These findings contribute to the understanding of the transition to becoming a direct brand manufacturer.

2016

Assessing the impact of mystery client traits on service evaluation

Autores
Brito, PQ; Rambocas, M;

Publicação
JOURNAL OF SERVICES MARKETING

Abstract
Purpose - This study aims to investigate the reliability of a mystery client (MC) as a service evaluation technique taking into consideration personal differences of the MC agents. Design/methodology/approach - The ratings from 144 MCs from 355 evaluations of computer and electronic stores were cross analyzed with eight psychographic and demographic profile variables. Findings - MCs who were highly involved in the product category were more critical of service responsiveness with respect to product demonstrations and listening to customer requirements. On the other hand, MCs with stronger faith in intuition were more inclined to rate services higher on empathy with respect to employees making a conscientious effort to understand customers' needs. Practical implications - Depending on the service marketing goals, managers learn to define which aspects of MC profile they should consider or avoid during the recruitment as well as becoming more critical when they analyze the evaluation reports to avoid an interpretation bias. Originality/value - The usefulness of the MC tool relies on its reliability and credibility as a marketing research technique. It was identified that the MC personality traits are more likely associated with marketing service evaluation variability.

2016

Online brochures: relationship between message strategies and communicated attributes

Autores
Brito, PQ; Pratas, J;

Publicação
ANATOLIA-INTERNATIONAL JOURNAL OF TOURISM AND HOSPITALITY RESEARCH

Abstract
This paper develops a theoretical model to define tourism destination brand's online content. Message strategies and positioning attributes that brands want to communicate are the main inputs to develop communication content. However, the relationship between message strategies and attributes has not been studied in the literature. Our research examines this relationship, using 400 online brochures from around the world. Based on the positioning attributes and message strategies, a taxonomy is developed to analyse online brochures through content analysis. A comprehensive benchmark model was designed to assist tourism destination managers and advertisers while planning the concept and production of their online tourism brochures, and a new creative methodology based on several workable strategic alternatives are proposed.

  • 283
  • 503