@inproceedings{brew2010using,
  abstract = {Tracking sentiment in the popular media has long been of interest to media analysts and pundits. With the availability of news content via online syndicated feeds, it is now possible to automate some aspects of this process. There is also great potential to crowdsource Crowdsourcing is a term, sometimes associated with Web 2.0 technologies, that describes outsourcing of tasks to a large often anonymous community. much of the annotation work that is required to train a machine learning system to perform sentiment scoring. We describe such a system for tracking economic sentiment in online media that has been deployed since August 2009. It uses annotations provided by a cohort of non-expert annotators to train a learning system to classify a large body of news items. We report on the design challenges addressed in managing the effort of the annotators and in making annotation an interesting experience.},
  acmid = {1860997},
  address = {Amsterdam, The Netherlands, The Netherlands},
  author = {Brew, Anthony and Greene, Derek and Cunningham, Pádraig},
  booktitle = {Proceedings of the 19th European Conference on Artificial Intelligence},
  editor = {Coelho, Helder and Studer, Rudi and Wooldridge, Michael},
  interhash = {90650749ea1084b729710d37b5865b72},
  intrahash = {9643e3c5729886b0b4e85cb3d3d704f5},
  isbn = {978-1-60750-605-8},
  numpages = {6},
  pages = {145--150},
  publisher = {IOS Press},
  series = {Frontiers in Artificial Intelligence and Applications},
  title = {Using Crowdsourcing and Active Learning to Track Sentiment in Online Media},
  url = {http://dl.acm.org/citation.cfm?id=1860967.1860997},
  volume = 215,
  year = 2010
}

@inproceedings{narayanan2008robust,
  abstract = {We present a new class of statistical de- anonymization attacks against high-dimensional micro-data, such as individual preferences, recommendations, transaction records and so on. Our techniques are robust to perturbation in the data and tolerate some mistakes in the adversary's background knowledge. We apply our de-anonymization methodology to the Netflix Prize dataset, which contains anonymous movie ratings of 500,000 subscribers of Netflix, the world's largest online movie rental service. We demonstrate that an adversary who knows only a little bit about an individual subscriber can easily identify this subscriber's record in the dataset. Using the Internet Movie Database as the source of background knowledge, we successfully identified the Netflix records of known users, uncovering their apparent political preferences and other potentially sensitive information.},
  author = {Narayanan, Arvind and Shmatikov, Vitaly},
  booktitle = {Proc. of the 29th IEEE Symposium on Security and Privacy},
  doi = {10.1109/SP.2008.33},
  interhash = {77c86be6c4bf7fc51b7faecfe85479fe},
  intrahash = {2748ba4684dbe09120aee56c6a0a9de9},
  issn = {1081-6011},
  month = may,
  pages = {111--125},
  publisher = {IEEE Computer Society},
  title = {Robust De-anonymization of Large Sparse Datasets},
  url = {http://www.cs.utexas.edu/~shmat/shmat_oak08netflix.pdf},
  year = 2008
}