Psychographic traits identification based on political ideology: An author analysis study on Spanish politicians’ tweets posted in 2020

In general, people are usually more reluctant to follow advice and directions from politicians who do not have their ideology. extreme cases, can be heavily biased in favour of a political party at the same time that they sharp disagreement with others, which may lead irrational decision making put people’s lives risk by ignoring certain recommendations authorities. Therefore, considering ideology as psychographic trait improve micro-targeting helping public authorities local governments adopt better communication policies during crises. this work, we explore reliability determining traits concerning Our contribution is twofold. On one hand, release PoliCorpus-2020, dataset composed Spanish politicians’ tweets posted 2020. other conduct two authorship analysis tasks aforementioned dataset: an author profiling task extract demographic traits, attribution determine anonymous text domain. Both experiments evaluated several neural network architectures grounded on explainable linguistic features, statistical state-of-the-art transformers. addition, test whether models transferred detect citizens. results indicate features good indicators for identifying fine-grained affiliation, boost performance when combined embedding-based preserve relevant information tested ordinary Besides, found lexical morphosyntactic effective profiling, whereas stylometric attribution. • PoliCorpus-2020 conducting released. Linguistic affiliation. Embeddings complementary analysis. Lexical profiling. Stylometric