Social media and mobility landscape: Uncovering spatial patterns of urban human mobility with multi source data
- 58 Downloads
In this paper, we present a three-step methodological framework, including location identification, bias modification, and out-of-sample validation, so as to promote human mobility analysis with social media data. More specifically, we propose ways of identifying personal activity-specific places and commuting patterns in Beijing, China, based on Weibo (China’s Twitter) check-in records, as well as modifying sample bias of check-in data with population synthesis technique. An independent citywide travel logistic survey is used as the benchmark for validating the results. Obvious differences are discerned from Weibo users’ and survey respondents’ activity-mobility patterns, while there is a large variation of population representativeness between data from the two sources. After bias modification, the similarity coefficient between commuting distance distributions of Weibo data and survey observations increases substantially from 23% to 63%. Synthetic data proves to be a satisfactory cost-effective alternative source of mobility information. The proposed framework can inform many applications related to human mobility, ranging from transportation, through urban planning to transport emission modeling.
KeywordsSocial media Human mobility Population bias Sample reconstruction Data integration
We would like to thank Fuzheng Zhang, Jianxun Lian, and Danyang Liu from Microsoft Research Asia for helping us crawl and manage Weibo check-in data.
- Beckman R J, Baggerly K A, Mckay M D (1996). Creating synthetic baseline populations. Transportation Research Part A: Policy and Practice, 30(6): 415–429Google Scholar
- Ghauche A (2010). Integrated transportation and energy activity-based model. Dissertation for the Master Degree. Cambridge: Massachusetts Institute of TechnologyGoogle Scholar
- Hasan S, Zhan X, Ukkusuri S V (2013). Understanding urban human activity and mobility patterns using large-scale location-based data from online social media. In: Proceedings of the 2nd ACM SIGKDD International Workshop on Urban Computing. New York: ACM, 6Google Scholar
- Hossain N, Hu T, White A M, Luo J, Kautz H (2016). Inferring finegrained details on user activities and home location from social media: Detecting drinking-while-tweeting patterns in communities. arXiv preprint arXiv, 1603.03181Google Scholar
- Kirk H (2013). Microsimulation Model User Guide (flexible modeling framework). Leeds: School of Geography, University of LeedsGoogle Scholar
- Müller K, Axhausen K W (2010). Population synthesis for microsimulation: State of the art. Arbeitsberichte Verkehrs- und Raumplanung, 638Google Scholar
- Rieser M, Dobler C, Dubernet T, Grether D, Horni A, Lammel G, Waraich, R, Zilske M, Axhausen K W, Nagel K (2014). MATSim User Guide. Zurich: MATSimGoogle Scholar
- Subbiah R, Lum K, Marathe A, Marathe M (2013). Activity based energy demand modeling for residential buildings. In: Innovative Smart Grid Technologies (ISGT), 2013 IEEE PES. Piscataway: IEEE, 1–6Google Scholar
- Wikipedia contributors (2017). Cosine similarity. Available online at https://doi.org/en.wikipedia.org/w/index.php?title=Cosine_similarity&oldid=767962382 (accessed March 7, 2017)
- Yuan N J, Wang Y, Zhang F, Xie X, Sun G (2013). Reconstructing individual mobility from smart card transactions: a space alignment approach. In: ICDM. Piscataway: IEEE, 877–886Google Scholar
- Zhang F, Yuan N J, Xie X (2012). Data from ‘LifeSpec: Learning the spectrum of urban lifestyles’. Available online at https://doi.org/www.microsoft.com/en-us/research/project/lifespec-learning-spectrum-urban-lifestyles-2/(accessed March 7, 2017)Google Scholar