Effect of Personality Traits on Classification of Political Orientation

Today, there is a large number of political transcripts available on the Web to be mined and used for statistical analysis, and product recommendations. As the online political resources are used for various purposes, automatically determining the political orientation on these transcripts becomes crucial. The methodologies used by machine learning algorithms to do an automatic classification are based on different features that are classified under categories such as Linguistic, Personality etc. Considering the ideological differences between Liberals and Conservatives, in this paper, the effect of Personality traits on political orientation classification is studied. The experiments in this study were based on the correlation between LIWC features and the BIG Five Personality traits. Several experiments were conducted using Convote U.S. Congressional- Speech dataset with seven benchmark classification algorithms. The different methodologies were applied on several LIWC feature sets that constituted by 8 to 64 varying number of features that are correlated to five personality traits. As results of experiments, Neuroticism trait was obtained to be the most differentiating personality trait for classification of political orientation. At the same time, it was observed that the personality trait based classification methodology gives better and comparable results with the related work.

Authors:

• Vesile Evrim
• Aliyu Awwal

Keywords:

• Politics
• personality traits
• LIWC
• machine learning.

References:

[1] K. Michael, P. Sobkowicz, and G. Bouchard, "Opinion Mining in Social
Media: Modeling, Simulating, andVisualizing Political Opinion
Formation in the Web," 2012.
[2] B. Liu, M. Hu, and J. Cheng, "Opinion observer: analyzing and
comparing opinions on the web," in WWW ’05: Proceedings of the 14th
international conference on World Wide Web, 2005, pp. 342–351.
[3] W. Yue and M. M. Tseng, "Customized products recommendation based
on probabilistic relevance model," Journal of Intelligent Manufacturing,
2013, vol. 24(5), pp. 951-960.
[4] M. Pennacchiotti and A.M. Popescu, "A Machine Learning Approach to
Twitter User Classification," ICWSM 11, 2011, pp. 281-288.
[5] M. Pennacchiotti and A.M. Popescu, "Democrats, republicans and
starbucksafficionados: user classification in twitter," in Proceedings of
the 17th ACM SIGKDD international conference on Knowledge
discovery and data mining, 2011.
[6] S. D. Gosling, P. J. Rentfrow, and W. B. Jr. Swann, "A very brief
measure of the Big Five personality domains," Journal of Research in
Personality, 2003, vol. 37, pp. 504–528.
[7] L. P. Naumann, S. Vazire, P. J. Rentfrow, and & S. D. Gosling,
"Personality judgments based on physical appearance," Personality and
Social Psychology Bulletin, 2009.
[8] R. Hogan, G. J. Curphy, and J. Hogan, "What we know about
leadership: Effectiveness and personality," American Psychologist,
1994, vol. 49 (6), pp. 493–504.
[9] W. T. Norman, "Toward an adequate taxonomy of personality attributes:
Replicated factor structure in peer nomination personality rating,"
Journal of Abnormal and Social Psychology, 1963, vol. 66, pp. 574–583.
[10] D. Watson and L. A. Clark, "On traits and temperament: General and
specific factors of emotional experience and their relation to the five
factor model," Journal of Personality, 1992, vol. 60 (2), pp. 441–76.
[11] R. E. Riggio, C. Salinas, and J. Tucker, "Personality and deception
ability," Personality and Individual Differences, 1988, vol. 9 (1), pp.
189–191.
[12] T. Yarkoni, "Personality in 100,000 Words: A Large-Scale Analysis of
Personality and Word Use among Bloggers," National Institute of Health
Public Access, 2010, pp. 1-23. [13] J. W. Pennebaker and L. A. King, "Linguistic styles: Language use as
an individual difference," Journal of Personality and Social Psychology,
1999, vol. 77, pp. 1296–1312.
[14] F. Mairesse, M. A. Walker, M. R. Mehl, and R. K. Moore, "Using
Linguistic Cues for the Automatic Recognition of Personality in
conversation and text", Journal of Artificial Intelligence Research, 2007,
pp. 457-500.
[15] S. Chris, "Predicting Dark Triad Personality traits From Twitter Usage
and A Linguistic Analysis of Tweets," in 11th International Conference
on Machine Learning and Applications (ICMLA), 2012, vol. 2.
[16] J. W. Pennebaker, M. E. Francis, and R. J. Booth, "Inquiry and Word
Count: LIWC 2001,” Mahwah, NJ, 2001.
[17] J. B. Hirsh and J. B. Peterson, "Personality and language use in selfnarratives,"
Journal of Research in Personality, 2009.
[18] A. J. Gill, S. Nowson, and J. Oberlander, "What are they blogging
about? Personality, topic and motivation in blogs," in Paper presented at
the The Third International AAAI Conference on Weblogs and Social
Media, San Jose, CA, 2009.
[19] F. Heylighen and J. M. Dewaele, "Variation in the contextuality of
language: an empirical measure," Context in Context: Special issue of
Foundations of Science, 2002, vol. 7 (3), pp. 293–340.
[20] S. Alan Gerber, A. Gregory Huber, David Doherty, and Conor M.
Dowling, "Personality and Political Attitudes: Relationships across Issue
Domains and Political Context," American Political Science Review,
2010, vol. 104(1), pp. 111-133.
[21] P. J. Rentfrow, J. T. Jost, S. D. Gosling, and J. Potter, "Statewide
differences in personality predict voting patterns in U.S. Presidential
elections, 1996–2004," in Social and psychological bases of ideology
and system justification. New York: Oxford University Press, 2009.
[22] R. McCrae and P. Costa, "Toward a new generation of personality
theories: Theoretical contexts for the five-factor model. ," in The five
factor model of personality: Theoretical perspectives. New York: JS
Wiggins, 1996, pp. 51-87.
[23] R. Carney Dana and etal, "The secret lives of liberals and conservatives:
Personality profiles, interaction styles, and the things they leave behind,"
Political Psychology, 2008, vol. 29(6), pp. 807-840.
[24] A. Furnham and J. Mitchell, "Personality, needs, social skills and
academic achievement: A longitudinal study," Personality and
Individual Differences, 1991, vol. 12, pp. 1067–1073.
[25] M. Komarraju and S. J. Karau, "The relationship between the Big Five
personality traits and academic motivation," Personality and Individual
Differences, 2005, vol. 39, pp. 557–567.
[26] G. Mishne, "Experiments with mood classification in blog posts," in
Proceedings of ACM SIGIR 2005 Workshop on Stylistic Analysis of
Text for Information Access, 2005.
[27] K. R. Scherer, "Vocal communication of emotion: A review of research
paradigms," Speech Communication, 2003, vol. 40 (1-2), pp. 227–256.
[28] E. Reiter and S. G. Sripada, "Contextual influences on near-synonym
choice," in Proceedings of the International Natural Language
Generation Conference, 2004, pp. 161– 170.
[29] J. Oberlander and S. Nowson, "Whose thumb is it anyway? Classifying
author personality from weblog text," 2006.
[30] L. Monroe Burt, Michael P. Colaresi, and Kevin M. Quinn,
"Fightin'words: Lexical Feature Selection And Evaluation For
Identifying The Content Of Political Conflict," Political Analysis, 2008,
vol. 16(4), pp. 372-403.
[31] M. Thomas, B. Pang, and L. Lee, "Get out the vote: Determining support
or opposition from congressional floor-debate transcripts," in
Proceedings of the 2006 Conference on Empirical Methods in Natural
Language Processing, Sydney, Australia, 2006, pp. 327–335.
[32] D. A. Allotey, "Sentiment analysis and classification of online reviews
using categorical proportional difference," 2011.
[33] J. W. Pennebaker, C. K. Chung, M. Ireland, A. Gonzales, and R. J.
Booth, "The Development and Psychometric Properties of LIWC2007,"
The University of Texas at Austin and The University of Auckland, New
Zealand, Austin, Texas 78703 USA, 2007.
[34] RapidMiner Inc. “RapidMiner Documentation”. (Online).
http://docs.rapidminer.com/studio/operators/, 2014.