Disentangling Topic Models: A Cross-cultural Analysis of Personal Values through Words

Steven Wilson, Rada Mihalcea, Ryan Boyd, James Pennebaker

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

Abstract

We present a methodology based on topicmodeling that can be used to identify andquantify sociolinguistic differences betweengroups of people, and describe a regressionmethod that can disentangle the influences ofdifferent attributes of the people in the group(e.g., culture, gender, age). As an example,we explore the concept of personal values,and present a cross-cultural analysis of value-behavior relationships spanning writers fromthe United States and India.
Original languageEnglish
Title of host publicationProceedings of the EMNLP 2016 First Workshop on Natural Language Processing and Computational Social Science
Place of PublicationAustin, Texas
PublisherAssociation for Computational Linguistics
Pages143-152
Number of pages10
ISBN (Electronic)978-1-945626-26-5
DOIs
Publication statusPublished - 5 Nov 2016
Event2016 Conference on Empirical Methods in Natural Language Processing - Austin, United States
Duration: 1 Nov 20165 Nov 2016
https://www.aclweb.org/mirror/emnlp2016/

Conference

Conference2016 Conference on Empirical Methods in Natural Language Processing
Abbreviated titleEMNLP 2016
Country/TerritoryUnited States
CityAustin
Period1/11/165/11/16
Internet address

Fingerprint

Dive into the research topics of 'Disentangling Topic Models: A Cross-cultural Analysis of Personal Values through Words'. Together they form a unique fingerprint.

Cite this