@inproceedings{marlow2006position,
  abstract = {In recent years, tagging systems have become increasingly popular. These systems enable users to add keywords (i.e., “tags”) to Internet resources (e.g., web pages, images, videos) without relying on a controlled vocabulary. Tagging systems have the potential to improve search, spam detection, reputation systems, and personal organization while introducing new modalities of social communication and opportunities for data mining. This potential is largely due to the social structure that underlies many of the current systems. Despite the rapid expansion of applications that support tagging of resources, tagging systems are still not well studied or understood. In this paper, we provide a short description of the academic related work to date. We offer a model of tagging systems, specifically in the context of web-based systems, to help us illustrate the possible benefits of these tools. Since many such systems already exist, we provide a taxonomy of tagging systems to help inform their analysis and design, and thus enable researchers to frame and compare evidence for the sustainability of such systems. We also provide a simple taxonomy of incentives and contribution models to inform potential evaluative frameworks. While this work does not present comprehensive empirical results, we present a preliminary study of the photosharing and tagging system Flickr to demonstrate our model and explore some of the issues in one sample system. This analysis helps us outline and motivate possible future directions of research in tagging systems.},
  author = {Marlow, Cameron and Naaman, Mor and Boyd, Danah and Davis, Marc},
  booktitle = {Collaborative Web Tagging Workshop at WWW2006},
  interhash = {7446351e0d902ee4f36fb750f82c50a5},
  intrahash = {8b100f88154692615b1e31e2e243e78c},
  location = {Edinburgh, Scotland},
  month = May,
  title = {{Position Paper, Tagging, Taxonomy, Flickr, Article, ToRead}},
  url = {http://www.danah.org/papers/WWW2006.pdf},
  year = 2006
}

@inproceedings{bozsak2002towards,
  author = {Bozsak, E. and Ehrig, Marc and Handschuh, Siegfried and Hotho, Andreas and Maedche, Alexander and Motik, Boris and Oberle, Daniel and Schmitz, Christoph and Staab, Steffen and Stojanovic, Ljiljana and Stojanovic, Nenad and Studer, Rudi and Stumme, Gerd and Sure, York and Tane, Julien and Volz, Raphael and Zacharias, Valentin},
  booktitle = {Proceedings of the Third International Conference on E-Commerce and Web Technologies (EC-Web 2002), Aix-en-Provence, France},
  editor = {Bauknecht, Kurt and Tjoa, A. Min and Quirchmayr, Gerald},
  interhash = {940750309ac472ea48a712e16b5d902a},
  intrahash = {d0aa1d2d01e378046e1693babc026836},
  pages = {304-313},
  publisher = {Springer},
  series = {LNCS},
  title = {KAON - Towards a large scale Semantic Web},
  url = {http://www.aifb.uni-karlsruhe.de/WBS/ysu/publications/2002_ecweb_kaon.pdf},
  volume = 2455,
  year = 2002
}

@inproceedings{weikum2011longitudinal,
  abstract = {Organizations like the Internet Archive have been capturing Web contents over decades, building up huge repositories of time-versioned pages. The timestamp annotations and the sheer volume of multi-modal content constitutes a gold mine for analysts of all sorts, across diff�erent application areas, from political analysts and marketing agencies to academic researchers and product developers. In contrast to traditional data analytics on click logs, the focus is on longitudinal studies over very long horizons. This longitudinal aspect affects and concerns all data and metadata, from the content itself, to the indices and the statistical metadata maintained for it. Moreover, advanced analysts prefer to deal with semantically rich entities like people, places, organizations, and ideally relationships such as company acquisitions, instead of, say, Web pages containing such references. For example, tracking and analyzing a politician's public appearances over a decade is much harder than mining frequently used query words or frequently clicked URLs for the last month. The huge size of Web archives adds to the complexity of this daunting task. This paper discusses key challenges, that we intend to take up, which are posed by this kind of longitudinal analytics: time-travel indexing and querying, entity detection and tracking along the time axis, algorithms for advanced analyses and knowledge discovery, and scalability and platform issues.},
  author = {Weikum, Gerhard and Ntarmos, Nikos and Spaniol, Marc and Triantafillou, Peter and Benczúr, András and Kirkpatrick, Scott and Rigaux, Philippe and Williamson, Mark},
  booktitle = {Proceedings of the 5th Biennial Conference on Innovative Data Systems Research},
  interhash = {2d84fdbf82a84bfc557056df3d0dcf11},
  intrahash = {6ffcc0d793bbe53bf6ed17f9d929846e},
  month = jan,
  pages = {199--202},
  title = {Longitudinal Analytics on Web Archive Data: It's About Time!},
  url = {http://www.cidrdb.org/cidr2011/Papers/CIDR11_Paper26.pdf},
  year = 2011
}