%0 Conference Paper %1 Bosnjak:2012:TDF:2187980.2188266 %A Bosnjak, Matko %A Oliveira, Eduardo %A Martins, José %A Mendes Rodrigues, Eduarda %A Sarmento, Lu\'ıs %B Proceedings of the 21st International Conference on World Wide Web %C New York, NY, USA %D 2012 %I ACM %K adaptiveCrawler focusedCrawler k3 twitter %P 1233--1240 %R 10.1145/2187980.2188266 %T TwitterEcho: A Distributed Focused Crawler to Support Open Research with Twitter Data %U http://doi.acm.org/10.1145/2187980.2188266 %X Modern social network analysis relies on vast quantities of data to infer new knowledge about human relations and communication. In this paper we describe TwitterEcho, an open source Twitter crawler for supporting this kind of research, which is characterized by a modular distributed architecture. Our crawler enables researchers to continuously collect data from particular user communities, while respecting Twitter's imposed limits. We present the core modules of the crawling server, some of which were specifically designed to focus the crawl on the Portuguese Twittosphere. Additional modules can be easily implemented, thus changing the focus to a different community. Our evaluation of the system shows high crawling performance and coverage. %@ 978-1-4503-1230-1

@inproceedings{Bosnjak:2012:TDF:2187980.2188266, abstract = {Modern social network analysis relies on vast quantities of data to infer new knowledge about human relations and communication. In this paper we describe TwitterEcho, an open source Twitter crawler for supporting this kind of research, which is characterized by a modular distributed architecture. Our crawler enables researchers to continuously collect data from particular user communities, while respecting Twitter's imposed limits. We present the core modules of the crawling server, some of which were specifically designed to focus the crawl on the Portuguese Twittosphere. Additional modules can be easily implemented, thus changing the focus to a different community. Our evaluation of the system shows high crawling performance and coverage.}, acmid = {2188266}, added-at = {2016-01-13T12:21:31.000+0100}, address = {New York, NY, USA}, author = {Bo\v{s}njak, Matko and Oliveira, Eduardo and Martins, Jos{\'e} and Mendes Rodrigues, Eduarda and Sarmento, Lu\'{\i}s}, biburl = {https://www.bibsonomy.org/bibtex/26ba449fd28a29943c8f37c1545dd8076/asmelash}, booktitle = {Proceedings of the 21st International Conference on World Wide Web}, description = {TwitterEcho}, doi = {10.1145/2187980.2188266}, interhash = {82c613065e7fb063cda8c5792377cb65}, intrahash = {6ba449fd28a29943c8f37c1545dd8076}, isbn = {978-1-4503-1230-1}, keywords = {adaptiveCrawler focusedCrawler k3 twitter}, location = {Lyon, France}, numpages = {8}, pages = {1233--1240}, publisher = {ACM}, series = {WWW '12 Companion}, timestamp = {2016-01-27T14:03:50.000+0100}, title = {TwitterEcho: A Distributed Focused Crawler to Support Open Research with Twitter Data}, url = {http://doi.acm.org/10.1145/2187980.2188266}, year = 2012 }