Identificación Automática del Idioma en Twitter: Adaptación de Identificadores del Estado del Arte al Contexto Ibérico

We describe here our partipation in TweetLID. After having studied the problem of language identification, the resources available, and designed a text conflation approach for this kind of tasks, we joined the competition with two systems: the first one was based in the guesser langdetect, re-trained and adapted in order to work with conflated text; the second one was an approach based on majority vote which used a set of re-trained and adapted classifiers. Results are analized both globally and at language and tweet-type levels.