Symbolic Data Analysis for the Assessment of User Satisfaction: An Application ...

• Author(s): Sousa, Áurea ; Tomás, Licínio Manuel Vicente ; Silva, Osvaldo ; Bacelar-Nicolau, Helena
• Date: 2013
• Persistent ID: http://hdl.handle.net/10400.3/2663
• Origin: Repositório da Universidade dos Açores
• Subject(s): Ascendent Hierarchical Cluster Analysis; Symbolic Data; Affinity Coefficient; VL Methodology
• Document Type: Article
• Language: English

Description

Special edition of the European Scientific Journal (ESJ): Conference proceedings: 1st Annual International Interdisciplinary Conference AIIC 2013, 24-26 April, Azores Islands, Portugal. This paper re-examines and deepens the study of a portion of the data collected within the context of a wider 2007 research project conducted in the Autonomous Region of Azores. The 2007 study aimed to understand users’ habits, attitudes and cultural practices, concerning reading and utilization of different library services, archives and museums. Based upon knowledge that only data analysis of a representative sample can supply, the study aimed to identify the aspects that should be prioritized in a process of restructuring the cultural services of leisure and reading to be implemented. This paper, utilizing data from the 2007 study, presents some results from the Ascendant Hierarchical Cluster Analysis (AHCA) of symbolic objects, according to the treatment to which they were submitted. These objects are described by different symbolic attributes pertaining to the latent variable ‘Degree of Satisfaction’. This variable was evaluated according to different dimensions of on-the-spot reading and consultation services. The aggregation criteria used in this study belong to a parametric family of methods and the similarity measure used is the weighted generalized affinity coefficient, for symbolic data. The validation of the clustering results is based on some validation measures.