Durumeric Zakir, Wustrow Eric, and Halderman J. Inferring the location of twitter messages based on user relationships. Davis, Pappa Gisele L., Oliveira Diogo Rennó Rocha de, and Arcanjo Filipe de L. In Proceedings of the 9th ACM International Conference on Web Search and Data Mining. Improving IP geolocation using query logs. Dan Ovidiu, Parikh Vaibhav, and Davison Brian D. Geolocation of Internet hosts: Accuracy limits through Cramér–Rao lower bound. Ciavarrini Gloria, Greco Maria S., and Vecchio Alessio. In Proceedings of the 19th ACM International Conference on Information and Knowledge Management. You are where you tweet: A content-based approach to geo-locating twitter users. Cheng Zhiyuan, Caverlee James, and Lee Kyumin. In Proceedings of the 2012 International Conference on Advances in Social Networks Analysis and Mining (ASONAM’12). Phillies tweeting from Philly? Predicting Twitter user locations with spatial word usage. Chang Hau-wen, Lee Dongwon, Eltaher Mohammed, and Lee Jeongkyu. Department of Computer Science, Duke University. Alidade: IP Geolocation without Active Probing. Chandrasekaran Balakrishnan, Bai Mingru, Schoenfield Michael, Berger Arthur, Caruso Nicole, Economou George, Gilliss Stephen, Maggs Bruce, Moses Kyle, Duff David, et al. In 2011 IEEE 3rd International Conference on Privacy, Security, Risk and Trust (PASSAT’11) and 2011 IEEE 3rd International Conference on Social Computing (SocialCom’11). Estimating Twitter user location using social interactions–A content based approach. Chandra Swarup, Khan Latifur, and Muhaya Fahad Bin. Economic Development and Cultural Change 9, 4 ( 1961), 573– 588. City size distributions and economic development. Inferring and using location metadata to personalize web search. Bennett Paul N., Radlinski Filip, White Ryen W., and Yilmaz Emine. Find me if you can: Improving geographical prediction with social and spatial proximity. Backstrom Lars, Sun Eric, and Marlow Cameron. In Workshop on Geographic Information Retrieval (GIR’06), colocated with SIGIR. In Proceedings of the 27th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. Amitay Einat, Har’El Nadav, Sivan Ron, and Soffer Aya. Finally, we also demonstrate that our two approaches outperform the academic state of the art based on mining query logs. This second approach also outperforms the baselines by 7 and 17 percentage points, respectively, and has higher coverage than the first method. Second, we present an alternative method of assigning locations to URLs when IP location training data is not available, by instead extracting locations from the body of web documents. Our approach significantly outperforms two state-of-the-art commercial IP geolocation databases by 25 and 36 percentage points at a distance error of 10 kilometers, respectively. 
We demonstrate that we can further propagate these URL locations to IP addresses with unknown locations. First, we show that we can derive which URLs have local affinity by clustering clicks from IPs with known locations. In this work we present two novel approaches to improving IP geolocation by mining search engine click logs.
However, IP geolocation databases are often inaccurate. These databases are vital for a number of online services, including search engine personalization, content delivery, local ads, and fraud detection. They are used to determine the location of online users when their precise location is unavailable. IP geolocation databases map IP addresses to their physical locations.
0 kommentar(er)
