Measuring Personal Values in Cross-Cultural User-Generated Content

There are several standard methods used to measure personal values, including the Schwartz Values Survey and the World Values Survey. While these tools are based on well-established questionnaires, they are expensive to administer at a large scale and rely on respondents to self-report their values rather than observing what people actually choose to write about. We employ a lexicon-based method that can computationally measure personal values on a large scale. Our approach is not limited to word-counting as we explore and evaluate several alternative approaches to quantifying the usage of value-related themes in a given document. We apply our methodology to a large blog dataset comprised of text written by users from different countries around the world in order to quantify cultural differences in the expression of person values on blogs. Additionally, we analyze the relationship between the value themes expressed in blog posts and the values measured for some of the same countries using the World Values Survey.

[1]  M. Kendall.  The treatment of ties in ranking problems. , 1945, Biometrika.

[2]  R. Gorsuch,et al.  Beliefs, attitudes, and values , 1968 .

[3]  M. Rokeach.  The Nature Of Human Values , 1974 .

[4]  M. Rokeach,et al.  The great American values test : influencing behavior and belief through television , 1986 .

[5]  S. Schwartz.  Universals in the Content and Structure of Values: Theoretical Advances and Empirical Tests in 20 Countries , 1992 .

[6]  Christiane Fellbaum,et al.  Building Semantic Concordances , 1998 .

[7]  M. Rohan.  A Rose by Any Name? The Values Construct , 2000 .

[8]  Christiane Fellbaum,et al.  Book Reviews: WordNet: An Electronic Lexical Database , 1999, CL.

[9]  Sandra L. Faulkner,et al.  Layers of Meaning: An Analysis of Definitions of Culture , 2006 .

[10]  Sandra L. Faulkner,et al.  Redefining Culture : Perspectives Across the Disciplines , 2006 .

[11]  G. Hofstede.  Dimensionalizing cultures: The Hofstede model in context , 2011 .

[12]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[13]  James W. Pennebaker,et al.  The Psychology of Word Use in Depression Forums in English and in Spanish: Texting Two Text Analytic Approaches , 2008, ICWSM.

[14]  Brian A. Nosek,et al.  Liberals and conservatives rely on different sets of moral foundations. , 2009, Journal of personality and social psychology.

[15]  A. Knafo,et al.  The Value of Values in Cross-Cultural Research: A Special Issue in Honor of Shalom Schwartz , 2011 .

[16]  Maite Taboada,et al.  Lexicon-Based Methods for Sentiment Analysis , 2011, CL.

[17]  S. Schwartz.  An Overview of the Schwartz Theory of Basic Values , 2012 .

[18]  Cindy K. Chung,et al.  Finding values in words: Using natural language to detect regional variations in personal concerns. , 2014 .

[19]  Ryan L. Boyd,et al.  The Development and Psychometric Properties of LIWC2015 , 2015 .

[20]  Rada Mihalcea,et al.  Values in Words: Using Language to Evaluate and Understand Personal Values , 2015, ICWSM.

[21]  Tomas Mikolov,et al.  Enriching Word Vectors with Subword Information , 2016, TACL.

[22]  Luke S. Zettlemoyer,et al.  Deep Contextualized Word Representations , 2018, NAACL.

[23]  Rada Mihalcea,et al.  Building and Validating Hierarchical Lexicons with a Case Study on Personal Values , 2018, SocInfo.

[24]  Morteza Dehghani,et al.  Dictionaries and distributions: Combining expert knowledge and large scale textual data content analysis , 2018, Behavior research methods.