There have been many attempts at au tomatically recognising author personal ity traits from text, typically incorporating linguistic features with conventional ma chine learning models, e.g. linear regres sion or Support Vector Machines. In this work, we propose to use deep-learning-based models with atomic features of text - the characters - to build hierarchical, vectorial word and sentence representa tions for the task of trait inference. On a corpus of tweets, this method shows state-of-the-art performance across five traits and three languages (English, Spanish and Italian) compared with prior work in au thor profiling. The results, supported by preliminary visualisation work, are en couraging for the ability to detect complex human traits.
展开▼