Abstract
In this work, we apply text mining algorithms on Twitter messages made available by PAN2015. In the first step, we applied IBM Watson algorithms to obtain the results of Big Five personality analysis, namely OCEAN: Openness, Conscientiousness, Extraversion, Agreeableness and Neuroticism. Then, we applied a Deep Learning algorithm on the resulted IBM Watson scores, in order to minimize the Root Mean Square Error. In this way, we achieved better results than using the IBM Watson algorithms alone. The dataset contains messages in English from 152 distinct authors.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
In short, to collect the ground truth data, when IBM was developing the tool, surveys were administered over large populations and, for each user, standard psychometric surveys were collected along with their Twitter posts.
References
Candel, A., Parmar, V., LeDell, E., Arora, A.: Deep Learning with H2O. H2O.ai, Inc., Mountain View (2015)
Celli, F.: Unsupervised personality recognition for social network sites. In: Proceedings of 6th International Conference on Digital Society. Citeseer (2012)
Álvarez-Carmona, M.A., et al.: INAOE’s participation at PAN’15: author profiling task–notebook for PAN at CLEF 2015. In: Cappellato, L., Ferro, N., Jones, G., Juan, E.S. (eds.) CLEF 2015 Evaluation Labs and Workshop - Working Notes Papers, Toulouse, France. CEUR-WS.org, 8–11 September 2015
Farnadi, G., Sitaraman, G., Sushmita, S.: User modeling and user-adapted interaction, vol. 26 (2016)
IBM: IBM Watson personality insights has a new model: support of shorter text and precision improvement. Technical report, IBM (2016)
IBM: Personality insight basics. Technical report, IBM (2016)
IBM: Personality models. Technical report, IBM (2016)
Mahmud, J.: IBM Watson personality insights: the science behind the service. Technical report, IBM (2016)
Werlen, L.M.: Statistical learning methods for profiling analysis-notebook for PAN at CLEF 2015. In: Cappellato, L., Ferro, N., Jones, G., Juan, E.S. (eds.) CLEF 2015 Evaluation Labs and Workshop - Working Notes Papers, Toulouse, France. CEUR-WS.org, 8–11 September 2015
Rangel, F., Celli, F., Rosso, P., Potthast, M., Stein, B., Daelemans, W.: Overview of the 3rd author profiling task at PAN 2015. In: Cappellato, L., Ferro, N., Jones, G., Juan, E.S. (eds.) CLEF 2015 Evaluation Labs and Workshop - Working Notes Papers, Toulouse, France. CEUR-WS.org, 8–11 September 2015
Ṣulea, O.-M., Dichiu, D.: Automatic profiling of Twitter users based on their tweets-notebook for PAN at CLEF 2015. In: Cappellato, L., Ferro, N., Jones, G., Juan, E.S. (eds.) CLEF 2015 Evaluation Labs and Workshop - Working Notes Papers, Toulouse, France. CEUR-WS.org, 8–11 September 2015
Tausczik, Y.R., Pennebaker, J.W.: The psychological meaning of words: LIWC and computerized text analysis methods. J. Lang. Soc. Psychol. 29(1), 24–54 (2010)
Acknowledgments
We are very grateful to the National Council for Scientific and Technological Development - CNPq (Brazil) for having subsidized the postdoctoral fellowship, and to Saman Daneshvar (University of Ottawa) for revising the paper.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Pereira Junior, R.A., Inkpen, D. (2017). Using Cognitive Computing to Get Insights on Personality Traits from Twitter Messages. In: Mouhoub, M., Langlais, P. (eds) Advances in Artificial Intelligence. Canadian AI 2017. Lecture Notes in Computer Science(), vol 10233. Springer, Cham. https://doi.org/10.1007/978-3-319-57351-9_32
Download citation
DOI: https://doi.org/10.1007/978-3-319-57351-9_32
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-57350-2
Online ISBN: 978-3-319-57351-9
eBook Packages: Computer ScienceComputer Science (R0)