SMAGA: A Text Mining Framework to Study Culture and Cultural Differences

SMAGA: A Text Mining Framework to Study Culture and Cultural Differences

Yuan Xue, Yilu Zhou
Copyright: © 2019 |Pages: 23
DOI: 10.4018/IJSMOC.2019070102
OnDemand:
(Individual Articles)
Available
$37.50
Current Special Offers
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

The study of national culture and cultural differences has immense value in today's business world. However, contemporary cross-cultural study instruments are subjective to many biases and intensive in terms of human labor. On the other hand, social media data offers tremendous opportunities for cross-cultural studies. However, it cannot be used directly as input for existing cross-cultural study applications in social science for being unstructured and noisy. In this work, the authors develop a text mining application called Social Media Associative Group Analysis (SMAGA). It effectively discovers information relevant to cultural values from social media data and represent such information using AGA verbal associations tuples. Experimental results show that the SMAGA framework can generate meaningful results in support of cross-cultural studies with much higher efficiency than traditional cross-cultural study instruments. This research underlines the emerging trend of developing text mining applications to automate cross-cultural and other types of social science studies.
Article Preview
Top

Literature Review

In this section, we first provide an overview of two mainstream survey instruments frequently used in contemporary cultural studies: VBS and AGA. This is followed by a discussion of their contributions and limitations in the context of cross-cultural studies. The prospects of using social media data analytics for cross-cultural studies are discussed in light of the limitations of VBS and AGA. We then present a major challenge in using social media data for cultural studies and propose our text mining-based framework, which effectively addresses this challenge.

Complete Article List

Search this Journal:
Reset
Volume 16: 1 Issue (2024)
Volume 15: 1 Issue (2023)
Volume 14: 2 Issues (2022)
Volume 13: 2 Issues (2021)
Volume 12: 2 Issues (2020)
Volume 11: 2 Issues (2019)
View Complete Journal Contents Listing