SMAGA

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.