Avaliação qualitativa da Consulta Espaço- Textual Top-k

Abstract

It is increasingly common to find large databases with textual and spatial (latitude and longitude) information. Therefore, there is great interest in new strategies to efficiently retrieve relevant information from these datasets. One solution, which has attracted the attention of the research community, is the use of the Top-k Spatial- Textual Query. This query returns the best k spatio-textual documents considering the spatial distance between the query location and the documents and the textual relevance between the query keywords and the text associated with the documents. This work, however, studies the Top-k Spatial-Textual Query from a qualitative perspective, proposing a methodology for creating test collections using metrics to evaluate the quality of the results of the two existing ranking functions, from a textual and spatial perspective. The generated collections have a great diversity of spatial-textual data, which is vital for a qualitative study. The gained knowledge in this research provides an important source for those interested in evaluating information retrievals systems with spatio-textual characteristics.