A Language-independent and Compositional Model for Personality Trait Recognition from Short Texts
This work addresses the problem of automated personality detection for applications like author profiling, but it is incremental as it builds on existing deep learning approaches.
The paper tackled personality trait recognition from short texts by using deep learning with character-level features to build hierarchical representations, achieving state-of-the-art performance across five traits and three languages on a tweet corpus.
Many methods have been used to recognize author personality traits from text, typically combining linguistic feature engineering with shallow learning models, e.g. linear regression or Support Vector Machines. This work uses deep-learning-based models and atomic features of text, the characters, to build hierarchical, vectorial word and sentence representations for trait inference. This method, applied to a corpus of tweets, shows state-of-the-art performance across five traits and three languages (English, Spanish and Italian) compared with prior work in author profiling. The results, supported by preliminary visualisation work, are encouraging for the ability to detect complex human traits.