%0 Conference Paper %1 Cheng:2010:YYT:1871437.1871535 %A Cheng, Zhiyuan %A Caverlee, James %A Lee, Kyumin %B Proceedings of the 19th ACM International Conference on Information and Knowledge Management %C New York, NY, USA %D 2010 %I ACM %K k3 language language-twitter location twitter %P 759--768 %R 10.1145/1871437.1871535 %T You Are Where You Tweet: A Content-based Approach to Geo-locating Twitter Users %U http://doi.acm.org/10.1145/1871437.1871535 %X We propose and evaluate a probabilistic framework for estimating a Twitter user's city-level location based purely on the content of the user's tweets, even in the absence of any other geospatial cues. By augmenting the massive human-powered sensing capabilities of Twitter and related microblogging services with content-derived location information, this framework can overcome the sparsity of geo-enabled features in these services and enable new location-based personalized information services, the targeting of regional advertisements, and so on. Three of the key features of the proposed approach are: (i) its reliance purely on tweet content, meaning no need for user IP information, private login information, or external knowledge bases; (ii) a classification component for automatically identifying words in tweets with a strong local geo-scope; and (iii) a lattice-based neighborhood smoothing model for refining a user's location estimate. The system estimates k possible locations for each user in descending order of confidence. On average we find that the location estimates converge quickly (needing just 100s of tweets), placing 51% of Twitter users within 100 miles of their actual location. %@ 978-1-4503-0099-5

@inproceedings{Cheng:2010:YYT:1871437.1871535, abstract = {We propose and evaluate a probabilistic framework for estimating a Twitter user's city-level location based purely on the content of the user's tweets, even in the absence of any other geospatial cues. By augmenting the massive human-powered sensing capabilities of Twitter and related microblogging services with content-derived location information, this framework can overcome the sparsity of geo-enabled features in these services and enable new location-based personalized information services, the targeting of regional advertisements, and so on. Three of the key features of the proposed approach are: (i) its reliance purely on tweet content, meaning no need for user IP information, private login information, or external knowledge bases; (ii) a classification component for automatically identifying words in tweets with a strong local geo-scope; and (iii) a lattice-based neighborhood smoothing model for refining a user's location estimate. The system estimates k possible locations for each user in descending order of confidence. On average we find that the location estimates converge quickly (needing just 100s of tweets), placing 51% of Twitter users within 100 miles of their actual location.}, acmid = {1871535}, added-at = {2015-03-14T21:38:37.000+0100}, address = {New York, NY, USA}, author = {Cheng, Zhiyuan and Caverlee, James and Lee, Kyumin}, biburl = {https://www.bibsonomy.org/bibtex/2fd6eed16cf052176704383aa7c03dbe1/asmelash}, booktitle = {Proceedings of the 19th ACM International Conference on Information and Knowledge Management}, description = {You are where you tweet}, doi = {10.1145/1871437.1871535}, interhash = {b993f878cb2f045ee7bb080c7d298720}, intrahash = {fd6eed16cf052176704383aa7c03dbe1}, isbn = {978-1-4503-0099-5}, keywords = {k3 language language-twitter location twitter}, location = {Toronto, ON, Canada}, numpages = {10}, pages = {759--768}, publisher = {ACM}, series = {CIKM '10}, timestamp = {2016-02-08T18:00:14.000+0100}, title = {You Are Where You Tweet: A Content-based Approach to Geo-locating Twitter Users}, url = {http://doi.acm.org/10.1145/1871437.1871535}, year = 2010 }