Can birds play a role as High Nature Value indicators of montado system?

Montados form a heterogeneous landscape of wooded matrix dominated by cork and/or holm oak with open areas characterized by fuzzy boundaries. Montado supports a high biological diversity associated to low intensity management and a landscape diversity provided by a continuous gradient of land cover. Among other features this permits the classification of montados as a High Nature Value (HNV) system. We assessed the role of birds as HNV indicators for montado, and tested several bird groups—farmland, edge, forest generalists and forest specialists species; and some universal indicators such as species conservation status, Shannon’s diversity index and species richness. Our study areas covered the North–South distribution of cork oak in Portugal, and we surveyed the breeding bird communities across 117 sampling sites. In addition to variables related to management and sanitary status, we considered variables that characterize the landscape heterogeneity inside the montado—trees and shrub density and richness of woody vegetation. Our results suggest that specific bird guilds can be used as HNV indicators of particular typologies of montado, and highlight the need to develop an indicator that could be transversally applied to all types of montado.

Age and Gender Identification using Stacking for Classification⋆ Notebook for PAN at CLEF 2016

This paper presents our approach of identifying the profile of an unknown user based on the activities of known users. The aim of author profiling task of PAN@CLEF 2016 is cross-genre identification of the gender and age of an unknown user. This means training the system using the behavior of different users from one social media platform and identifying the profile of other user on some different platform. Instead of using single classifier to build the system we used a combination of different classifiers, also known as stacking. This approach allowed us explore the strength of all the classifiers and minimize the bias or error enforced by a single classifier.