Exploring Cross-cultural Crowd Sentiments on Twitter

Twitter is frequently used to express personal opinions and sentiments. This work presents a novel crowd sentiment analysis of Twitter for exploring cross-cultural differences. We aim to find similar meanings but different sentiments between Twitter data collected over diverse geographic places. For this, we detect sentiments and topics of each tweet and assign sentiments to each topic based on the sentiments of the corresponding tweets. This permits finding interesting cross-cultural patterns. We demonstrate a visualization system that supports the interactive analysis of two countries: France and Italy.