@inproceedings{fink2009geolocation,
  abstract = {Understanding the spatial distribution of people who author social media content is of growing interest for researchers and commerce. Blogging platforms depend on authors reporting their own location. However, not all authors report or reveal their location on their blog's home page. Automated geolocation strategies using IP address and domain name are not adequate for determining an author's location because most blogs are not self-hosted. In this paper we describe a method that uses the place name mentions in a blog to determine an author's location. We achieved an accuracy of 63% on a collection of 844 blogs with known locations.},
  author = {Fink, C. and Piatko, C. and Mayfield, J. and Chou, D. and Finin, T. and Martineau, J.},
  booktitle = {Proceedings of the International Conference on Computational Science and Engineering},
  doi = {10.1109/CSE.2009.584},
  interhash = {59b768c08026047c20d472ff93a4d513},
  intrahash = {70eddd59803db7efee4b8c840fe5a79b},
  month = aug,
  pages = {1088--1092},
  title = {The Geolocation of Web Logs from Textual Clues},
  url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5282996},
  volume = 4,
  year = 2009
}

@inproceedings{brooks2006improved,
  abstract = {Tags have recently become popular as a means of annotating and organizing Web pages and blog entries. Advocates of tagging argue that the use of tags produces a 'folksonomy', a system in which the meaning of a tag is determined by its use among the community as a whole. We analyze the effectiveness of tags for classifying blog entries by gathering the top 350 tags from Technorati and measuring the similarity of all articles that share a tag. We find that tags are useful for grouping articles into broad categories, but less effective in indicating the particular content of an article. We then show that automatically extracting words deemed to be highly relevant can produce a more focused categorization of articles. We also show that clustering algorithms can be used to reconstruct a topical hierarchy among tags, and suggest that these approaches may be used to address some of the weaknesses in current tagging systems.},
  address = {New York, NY, USA},
  author = {Brooks, Christopher H. and Montanez, Nancy},
  booktitle = {WWW '06: Proceedings of the 15th international conference on World Wide Web},
  file = {:brooks06-improved.pdf:PDF;brooks2006improved.pdf:brooks2006improved.pdf:PDF},
  groups = {public},
  interhash = {c88a665abf8d88c5a7ae95fa2783f837},
  intrahash = {5c9c83e89da2faa8906a5927fe7ca3ef},
  lastdatemodified = {2006-07-18},
  lastname = {Brooks},
  longnotes = {[[http://www2006.org/programme/files/pdf/583-slides.pdf slides]] Summary: - authors analyse the effectiveness of tags for classifying blog articles (technorati) - clustering of articles beloning to top 350 technorati tags * by tag * randomly * by related by Google News - results: * tags help to classify articles into broad categories (yet Google News performs better) * tags are not that descriptive for a specific topic of an article * automatically extracted tags (by TF/IDF) are much more descriptive for specific content - 2nd study: hierarchical clustering of articles (starting from tag clusters, i.e. all articles who share a tag) - resulting tag hierarchy comes close to e.g. Yahoo hand-built one},
  own = {own},
  pages = {625--632},
  pdf = {brooks06-improved.pdf},
  publisher = {ACM Press},
  read = {read},
  timestamp = {2009-09-29 16:23:07},
  title = {Improved annotation of the blogosphere via autotagging and hierarchical clustering},
  url = {http://www2006.org/programme/item.php?id=583},
  username = {dbenz},
  year = 2006
}

@article{kolari2006blog,
  author = {Kolari, P. and Java, A. and Finin, T. and Mayfield, J. and Joshi, A. and Martineau, J.},
  interhash = {22f376a3a5e2ee890908d81f409fc08c},
  intrahash = {e8d9c31822799d4d862a4bbcd885a4cf},
  journal = {TREC 2006 Blog Track Notebook},
  publisher = {Citeseer},
  title = {{Blog track open task: Spam blog classification}},
  url = {http://scholar.google.com/scholar.bib?q=info:BXvRJMPpbFUJ:scholar.google.com/&output=citation&hl=en&as_sdt=2000&as_vis=1&ct=citation&cd=10},
  year = 2006
}

@inproceedings{brooks2005analysis,
  abstract = {Tags have recently become popular as a means of annotating and organizing Web pages and blog entries. Advocates of tagging argue that the use of tags produces a 'folksonomy', a system in which the meaning of a tag is determined by its use among the community as a whole. We analyze the effectiveness of tags for classifying blog entries by gathering the top 350 tags from Technorati and measuring the similarity of all articles that share a tag. We find that tags are useful for grouping articles into broad categories, but less effective in indicating the particular content of an article. We then show that automatically extracting words deemed to be highly relevant can produce more focused categorization of articles. We also provide anecdotal evidence of some of tagging's weaknesses, and discuss future directions that could make tagging more effective as a tool for information organization and retrieval.},
  author = {Brooks, Christopher H. and Montanez, Nancy},
  booktitle = {AAAI Spring Symposium on Computational Approaches to Analyzing Weblogs},
  interhash = {71c1300be554e03e62db313f15fa1a27},
  intrahash = {e6c9ec01018cf315ca5c49461de86c51},
  month = mar,
  organization = {AAAI},
  title = {An analysis of the effectiveness of tagging in blogs},
  url = {http://www.aaai.org/Library/Symposia/Spring/2006/ss06-03-002.php},
  year = 2005
}

@inproceedings{1557077,
  abstract = {Tracking new topics, ideas, and "memes" across the Web has been an issue of considerable interest. Recent work has developed methods for tracking topic shifts over long time scales, as well as abrupt spikes in the appearance of particular named entities. However, these approaches are less well suited to the identification of content that spreads widely and then fades over time scales on the order of days - the time scale at which we perceive news and events. We develop a framework for tracking short, distinctive phrases that travel relatively intact through on-line text; developing scalable algorithms for clustering textual variants of such phrases, we identify a broad class of memes that exhibit wide spread and rich variation on a daily basis. As our principal domain of study, we show how such a meme-tracking approach can provide a coherent representation of the news cycle - the daily rhythms in the news media that have long been the subject of qualitative interpretation but have never been captured accurately enough to permit actual quantitative analysis. We tracked 1.6 million mainstream media sites and blogs over a period of three months with the total of 90 million articles and we find a set of novel and persistent temporal patterns in the news cycle. In particular, we observe a typical lag of 2.5 hours between the peaks of attention to a phrase in the news media and in blogs respectively, with divergent behavior around the overall peak and a "heartbeat"-like pattern in the handoff between news and blogs. We also develop and analyze a mathematical model for the kinds of temporal variation that the system exhibits.},
  address = {New York, NY, USA},
  author = {Leskovec, Jure and Backstrom, Lars and Kleinberg, Jon},
  booktitle = {KDD '09: Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining},
  doi = {http://doi.acm.org/10.1145/1557019.1557077},
  interhash = {f60a96f8adb340b62bacbc90fdb3e069},
  intrahash = {051df7b09db1d7806909cc22c1a362c8},
  isbn = {978-1-60558-495-9},
  location = {Paris, France},
  pages = {497--506},
  publisher = {ACM},
  title = {Meme-tracking and the dynamics of the news cycle},
  url = {http://portal.acm.org/citation.cfm?id=1557077},
  year = 2009
}