A Twitter-Based Culture Visualization System by Analyzing Multilingual Geo-Tagged Tweets
This paper presents a novel multilingual analysis of Twitter for exploring cultural differences. For this, we developed a Twitter-based visualization system for food culture by analyzing the differences between locations and languages in geo-tagged tweets from European countries. A key feature of the proposed system is the ability to infer similarities in food preferences between different language users in different cities even when such preferences are not explicitly shown in existing tweets.
KeywordsMultilingual Twitter analysis Culture visualization
The work in this paper is partially supported by SCOPE of the Ministry of Internal Affairs and Communications of Japan (#171507010), JSPS KAKENHI Grant Numbers 16H01722, 17K12686 and 17H01822.
- 1.Hu, T., Song, R., Wang, Y., Xie, X., Luo, J.: Mining shopping patterns for divergent urban regions by incorporating mobility data. In: Proceedings of CIKM 2016, pp. 569–578 (2016)Google Scholar
- 2.Pla, F., Hurtado, L.F.: Language identification of multilingual posts from Twitter: a case study. Knowl. Inf. Syst. 1–25 (2016)Google Scholar
- 3.Raghavi, K.C., Chinnakotla, M.K., Shrivastava, M.: “answer ka type kya he?”: learning to classify questions in code-mixed language. In: Proceedings of WWW 2015 Companion, pp. 853–858 (2015)Google Scholar