Unsupervised Personality Recognition from Text: advantages, disadvantages and applications

Speaker: Dr. Fabio Celli, post-doc, CLIC-CIMeC – University of Trento
Title: Unsupervised Personality Recognition from Text: advantages,
disadvantages and applications
When: Tuesday Oct 8, 12 pm
Where: Serraia room, via Sommarive 14, Povo
Abstract:
Personality recognition from text consists in the automatic classification of
authors’ personality traits from pieces of text they wrote. Classifier’s
predictions can be compared against gold standard labels, obtained by means of
personality assessments like the Big5 personality tests. Until recently, the
extraction of personality recognition was limited to blogs and offline texts,
while now there is a strong interest in the scientific community about the
extraction of personality from various sources, like status updates in online
social networks, speech and video.
Current approaches to Personality Recognition are based on supervised learning,
but this has several limitations, for example the cost of data annotation, the
lack of domain adaptability and multilinguality. We present an unsupervised
method for personality recognition from text and some of its applications in
Social network analysis as well as in NLP tasks.
References:
Celli F., Polonio L. (2013). Relationships between Personality and Interactions
in Facebook. In: Xin Ming Tu, Ann Marie White and Naiji Lu (Editors): Social
Networking: Recent Trends, Emerging Issues and Future Outlook. Nova Science
Publishers, Inc. pp. 31-43.
Celli F., Pianesi F., Stillwell D., Kosinski M. (2013) Workshop on Computational
Personality Recognition (Shared Task). In Proceedings of WCPR13, in conjunction
with ICWSM-13
Celli, F., Rossi, L. (2012) The role of Emotional Stability in Twitter
Conversations. In Proceedings of Workshop on Semantic Analysis in Social Media,
in conjunction with EACL 2012, Avignon.
Fornaciari T., Celli F., Poesio M. (2013) The Effect of Personality Type on
Deceptive Communication Style. In Workshop on Forensic Text Analytics, in
conjunction with the Intelligence and Security Informatics Conference (EISIC 2013).
Mairesse, F., Walker, M.A., Mehl, M.R., and Moore, R.K. (2007) Using Linguistic
Cues for the Automatic Recognition of Personality in Conversation and Text. In
Journal of Artificial intelligence Research, 30: 457–500.
Biography:
Fabio Celli, 1981, is a computational linguist and data miner. He got a degree
in communication studies at the University of Urbino, in linguistics at the
University of Bologna, and a PhD in cognitive science at the Center for Mind and
Brain Sciences (CIMeC), University of Trento. He is one of the organizers of the
Workshop on Computational Personality Recognition. His PhD thesis, Adaptive
Personality Recognition from Text, has been published by Lambert Academic
Publishing.