Measuring Personal Values in Cross-Cultural User-Generated Content.

Yiting Shen, Steven Wilson, Rada Mihalcea

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

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.
Original languageEnglish
Title of host publicationInternational Conference on Social Informatics
Subtitle of host publication11th International Conference, SocInfo 2019
PublisherSpringer, Cham
Number of pages14
ISBN (Electronic)978-3-030-34971-4
ISBN (Print)978-3-030-34970-7
Publication statusPublished - 11 Nov 2019
Event11th International Conference on Social Informatics - Doha, Qatar
Duration: 18 Nov 201921 Nov 2019

Publication series

Name Lecture Notes in Computer Science (LNCS)
PublisherSpringer, Cham
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349


Conference11th International Conference on Social Informatics
Abbreviated titleSocInfo 2019
Internet address

Keywords / Materials (for Non-textual outputs)

  • Content analysis
  • Personal values
  • User-generated content


Dive into the research topics of 'Measuring Personal Values in Cross-Cultural User-Generated Content.'. Together they form a unique fingerprint.

Cite this