Classification of Cross-cultural News Events
This work addresses the challenge of cross-cultural analysis in news events for researchers and analysts, but it is incremental as it applies existing cultural dimensions and classification techniques to a new dataset.
The authors tackled the problem of analyzing culture from text by developing a methodology to classify news events across 11 categories and 117 countries using Hofstede's cultural dimensions, achieving performance comparisons for different classification methods and feature sets.
We present a methodology to support the analysis of culture from text such as news events and demonstrate its usefulness on categorizing news events from different categories (society, business, health, recreation, science, shopping, sports, arts, computers, games and home) across different geographical locations (different places in 117 countries). We group countries based on the culture that they follow and then filter the news events based on their content category. The news events are automatically labelled with the help of Hofstedes cultural dimensions. We present combinations of events across different categories and check the performances of different classification methods. We also presents experimental comparison of different number of features in order to find a suitable set to represent the culture.