Detecting Cross-cultural Differences Using a Multilingual Topic Model
Published
2016-02-19
E. D. Gutiérrez
,
Ekaterina Shutova
,
Patricia Lichtenstein
,
Gerard de Melo
,
Luca Gilardi
E. D. Gutiérrez
University of California, San Diego
Ekaterina Shutova
University of Cambridge, UK
Patricia Lichtenstein
University of California, Merced
USA
Gerard de Melo
Tsinghua University, China
Luca Gilardi
International Computer Science Institute, UC Berkeley, USA
Abstract
Understanding cross-cultural differences has important implications for world affairs and many aspects of the life of society. Yet, the majority of text-mining methods to date focus on the analysis of monolingual texts. In contrast, we present a statistical model that simultaneously learns a set of common topics from multilingual, non-parallel data and automatically discovers the differences in perspectives in these topics across linguistic communities. We perform a behavioural evaluation of a subset of the differences identified by our model in English and Spanish to investigate their psychological validity.
PDF (presented at ACL 2016)