City Link: Finding Similar Areas in Two Cities Using Twitter Data
Today in our increasingly globalized world, the number of people travelling overseas is increasing. A system that helps overseas travelers by providing information related to unfamiliar places has been earnestly sought. This study develops such a system by exploiting user-generated data over a popular social network platform: Twitter. We propose the use of natural language processing (NLP) as a method of estimating location similarity between areas in different cities. Finally, location similarity is visualized on a map. Our experiment is conducted at two popular sightseeing cities: Bangkok, Thailand and Kyoto, Japan. Our evaluation using crowd-sourcing-based 1,000 questionnaires empirically demonstrated that the proposed method can find similar places in the two cities. This result demonstrated the fundamental feasibility of our approach.
KeywordsCity similarity Crowd-sourcing Doc2Vec Map visualization Social media
This work was partly supported by MIC SCOPE #171507010, AMED under Grant Number JP16fk0108119, and JSPS KAKENHI Grant Numbers JP16K16057 and JP16H01722.
- 1.Lynch, K.: The Image of the City. MIT Press, Cambridge (1960)Google Scholar
- 2.Nold, C.: Greenwich Emotion Map. http://www.emotionmap.net/ (2005)
- 3.Quercia, D., Schifanella, R., Aiello, L.M.: The shortest path to happiness: recommending beautiful, quiet, and happy routes in the city. In: Proceedings of Conference on Hypertext and Social Media (HyperText) (2014)Google Scholar
- 4.Quercia, D., Schifanella, R., Aiello, L.M., McLean, K.: Smelly maps: the digital life of urban smellscapes. In: Proceedings of the Ninth International AAAI Conference on Web and Social Media, pp. 327–336 (2015)Google Scholar
- 6.Culotta, A.: Towards detecting influenza epidemics by analyzing Twitter messages. In: Proceedings of the First Workshop on Social Media Analytics, pp. 115–122 (2010)Google Scholar
- 7.Amador Diaz Lopez, J., Collignon-Delmar, S., Benoit, K., et al.: Predicting the Brexit vote by tracking and classifying public opinion using Twitter data. Stat. Polit. Policy 8(1), 85–104 (2017). Accessed 24 Aug 2018. https://doi.org/10.1515/spp-2017-0006
- 9.Tumasjan, A., Sprenger, T.O., Sandner, P.G., Welpe, I.M.: Predicting elections with Twitter: what 140 characters reveal about political sentiment. In: International AAAI Conference on Weblogs and Social Media, Washington, DC (2010)Google Scholar
- 10.Hahmann, S., Purves, R., Burghardt, D.: Twitter location (sometimes) matters: exploring the relationship between georeferenced tweet content and nearby feature classes. J. Spat. Inf. Sci. Number 9, 1–36 (2014)Google Scholar
- 11.Preotiuc-Pietro, D., Cranshaw, J., Yano, T.: Exploring venue-based city-to-city similarity measures. In: Proceedings of the Second ACM SIGKDD International Workshop on Urban Computing, Article No. 16 (2013)Google Scholar
- 12.Kato, M.P., Hiroaki, O., Oyama, S., Tanaka, K.: Search as if you were in your home town: geographic search by regional context and dynamic feature-space selection. In: Proceedings of the 19th ACM International Conference on Information and Knowledge Management, pp. 1541–1544 (2010)Google Scholar
- 13.Seth, R., Covell, M., Ravichandran, D., Sivakumar, D., Baluja, S.: A tale of two (similar) cities: inferring city similarity through geo-spatial query log analysis. In: Proceedings of the International Conference on Knowledge Discovery and Information Retrieval (2011)Google Scholar