UNED @ Retrieving Diverse Social Images Task

This paper summarizes the participation of UNED at the 2014 Retrieving Diverse Social Images Task [3]. We propose a novel approach based on Formal Concept Analysis (FCA) to detect the latent topics related to the images and a later Hierarchical Agglomerative Clustering (HAC) to put together the images according to these latent topics. The diversification will be based on offering images from the different topics detected. In order to detect these latent topics, two kinds of data have been tested: only information related to the description of the images and all the textual information related to the images. The results show that our proposal is suitable for search result diversification, achieving similar results to those in the state of the art.