A Language-independent and Compositional Model for Personality Trait Recognition from Short Texts

Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 754–764, Valencia, Spain, April 3-7, 2017. c⃝2017 Association for Computational Linguistics A Language-independent and Compositional Model for Personality Trait Recognition from Short Texts Fei Liu♠∗, Julien Perez♥ and Scott Nowson♣∗ ♠The University of Melbourne, Victoria, Australia ♥Xerox Research Centre Europe, Grenoble, France ♣Accenture Centre for Innovation, Dublin, Ireland fliu3@student.unimelb.edu.au julien.perez@xrce.xerox.com scott.nowson@accenture.com Abstract 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. 1 Introduction Deep-learning methods are becoming increasingly applied to problems in the area of Natural Lan- guage Processing (NLP) (Manning, 2016). Such techniques can be applied to tasks such as part- of-speech-tagging (Ling et al., 2015; Huang et al., 2015) and sentiment analysis (Socher et al., 2013; Kalchbrenner et al., 2014; Kim, 2014). At their core, these tasks can be seen as learning represen- tations of language at different levels. Our work reported here is no different, though we choose a less commonplace level of representation – rather than the text itself, we focus on the author be- hind the text. Automatically modelling individu- als from their language use is a task founded on the long-standing understanding that language use is influenced by sociodemographic characteristics ∗Work carried out at Xerox Research Centre Europe such as gender and personality (Tannen, 1990; Pennebaker et al., 2003). The study of personal- ity traits in particular is considered reliable as such traits are generally temporally stable (Matthews et al., 2003). As such, our ability to model our tar- get – the author – is enriched by the acquisition of more data over time. The volume of literature on computational per- sonality recognition, and its broader applications, has grown steadily over the last decade. There have also been a number of dedicated workshops (Celli et al., 2014; Tkalˇciˇc et al., 2014) and shared tasks (Rangel et al., 2015) on the topic occur- ring in recent years. A significant portion of this prior literature has used some variation of en- riched bag-of-words; e.g. the Open vocabulary approach (Schwartz et al., 2013). This is, theoret- ically speaking, entirely understandable as study of the relationship between word use and traits has delivered significant insight into human be- haviour (Pennebaker et al., 2003). Language has been represented at a number of different levels in this work such as syntactic, semantic, and cate- gorical …

Content truncated to 500 words