@article{muniswamyreddy2010provenance,
  abstract = {Digital provenance is meta-data that describes the ancestry or history of a digital object. Most work on provenance focuses on how provenance increases the value of data to consumers. However, provenance is also valuable to storage providers. For example, provenance can provide hints on access patterns, detect anomalous behavior, and provide enhanced user search capabilities. As the next generation storage providers, cloud vendors are in the unique position to capitalize on this opportunity to incorporate provenance as a fundamental storage system primitive. To date, cloud offerings have not yet done so. We provide motivation for providers to treat provenance as first class data in the cloud and based on our experience with provenance in a local storage system, suggest a set of requirements that make provenance feasible and attractive.},
  acmid = {1713258},
  address = {New York, NY, USA},
  author = {Muniswamy-Reddy, Kiran-Kumar and Seltzer, Margo},
  doi = {10.1145/1713254.1713258},
  interhash = {6fb5af3426b91f7e460d99746b3358c2},
  intrahash = {1f9f6761cab2437739d30b9636ba5531},
  issn = {0163-5980},
  issue_date = {January 2010},
  journal = {SIGOPS Operating Systems Review},
  month = jan,
  number = 4,
  numpages = {6},
  pages = {11--16},
  publisher = {ACM},
  title = {Provenance as first class cloud data},
  url = {http://doi.acm.org/10.1145/1713254.1713258},
  volume = 43,
  year = 2010
}

@mastersthesis{flohr2011extraktion,
  abstract = {Informationen so aufzubereiten, dass sie für eine bestimmte Situation nützlich sind, ist eine große Herausforderung. In solchen Situationen soll ein Benutzer, wenn er sich an einem fremden Ort befindet, mit Hilfe des Android Smartphone interessante und wis- senswerte Informationen anzeigen lassen. Um dies bewerkstelligen zu können, muss es eine georeferenzierte Informationsquelle geben. Außerdem muss ein Konzept vor- handen sein, um diese Daten zu sammeln und so aufzubereiten, dass der Benutzer diese auch nützlich findet. Es muss eine Visualisierung dieser Daten geben, da der Platz zur Anzeige auf Smartphones sehr begrenzt ist. Als georeferenzierte Informationsquelle wird die Online-Enzyklopädie Wikipedia ge- nutzt, diese ist frei zugänglich und auch sehr umfassend. In dieser Arbeit wird das Konzept zur Sammlung und Aufbereitung von relevanten Daten behandelt. Zur In- formationsvisualisierung wird die Methode der Schlagwortwolke (engl. Tag-Cloud) verwendet.   It is a major challenge to prepare useful information for a particular situation. In this situation an Android smartphone user wants to display interesting and important facts about an unknown place. To manage this task existence of a geo-referenced source of information has to be ensured. In order to collect and prepare this data a creation of concept is needed. Due to limited display space, it is necessary to construct a suitable visualization of this data. Wikipedia is used as a geo-referenced information resource, because it has open-access and it offers global geo-referenced information. This thesis covers the concept of col- lecting and preparing relevant data. To visualize information a tag cloud is used.  },
  author = {Flohr, Oliver},
  interhash = {5d1f4da4964062ed6598fe8d8be8b591},
  intrahash = {a28959724af1907e7fc67a68e648c14c},
  month = aug,
  school = {Gottfried Wilhelm Leibniz Universität Hannover},
  title = {Extraktion und Visualisierung ortsbezogener Informationen mit Tag-Clouds},
  type = {bachelor thesis},
  url = {http://www.se.uni-hannover.de/pub/File/pdfpapers/Flohr2011a.pdf},
  year = 2011
}

@mastersthesis{olson2012cloud,
  abstract = {My thesis describes the design and implementation of systems that empower individuals to help their communities respond to critical situations and to participate in research that helps them understand and improve their environments. People want to help their communities respond to threats such as earthquakes, wildfires, mudslides and hurricanes, and they want to participate in research that helps them understand and improve their environment. “Citizen Science” projects that facilitate this interaction include projects that monitor climate change, water quality and animal habitats. My thesis explores the design and analysis of community-based sense and response systems that enable individuals to participate in critical community activities and scientific research that monitors their environments.},
  author = {Olson, Michael J.},
  interhash = {a9cdee464e76cd5210c13d7f66981e83},
  intrahash = {d9e22a1a5e9404a805aee5cb0fd406c4},
  school = {California Institute of Technology},
  title = {Cloud computing for citizen science},
  type = {Master's thesis},
  url = {http://resolver.caltech.edu/CaltechTHESIS:08232011-122341638},
  year = 2012
}

@article{dean2008mapreduce,
  abstract = {MapReduce is a programming model and an associated implementation for processing and generating large datasets that is amenable to a broad variety of real-world tasks. Users specify the computation in terms of a <i>map</i> and a <i>reduce</i> function, and the underlying runtime system automatically parallelizes the computation across large-scale clusters of machines, handles machine failures, and schedules inter-machine communication to make efficient use of the network and disks. Programmers find the system easy to use: more than ten thousand distinct MapReduce programs have been implemented internally at Google over the past four years, and an average of one hundred thousand MapReduce jobs are executed on Google's clusters every day, processing a total of more than twenty petabytes of data per day.},
  acmid = {1327492},
  address = {New York, NY, USA},
  author = {Dean, Jeffrey and Ghemawat, Sanjay},
  doi = {10.1145/1327452.1327492},
  interhash = {b8a00982bf087c8543855897b7362a04},
  intrahash = {bff539224836d703c2d21141985fa1a3},
  issn = {0001-0782},
  issue_date = {January 2008},
  journal = {Communications of the ACM},
  month = jan,
  number = 1,
  numpages = {7},
  pages = {107--113},
  publisher = {ACM},
  title = {MapReduce: simplified data processing on large clusters},
  url = {http://doi.acm.org/10.1145/1327452.1327492},
  volume = 51,
  year = 2008
}

@article{kaser2007tagcloud,
  abstract = {Tag clouds provide an aggregate of tag-usage statistics. They are typically sent as in-line HTML to browsers. However, display mechanisms suited for ordinary text are not ideal for tags, because font sizes may vary widely on a line. As well, the typical layout does not account for relationships that may be known between tags. This paper presents models and algorithms to improve the display of tag clouds that con- sist of in-line HTML, as well as algorithms that use nested tables to achieve a more general 2-dimensional layout in which tag relationships are considered. The first algorithms leverage prior work in typesetting and rectangle packing, whereas the second group of algorithms leverage prior work in Electronic Design Automation. Experiments show our algorithms can be efficiently implemented and perform well. },
  author = {Kaser, Owen and Lemire, Daniel},
  date = {2008-01-02},
  interhash = {cb6ed5e3340cf684ec55299adc65e1a9},
  intrahash = {56270d1311c066a3852bea23eeb8d484},
  journal = {CoRR},
  note = {informal publication},
  title = {Tag-Cloud Drawing: Algorithms for Cloud Visualization},
  url = {http://arxiv.org/abs/cs/0703109},
  volume = {abs/cs/0703109},
  year = 2007
}

@inproceedings{hassanmontero2006improving,
  address = {Merida, Spain},
  author = {Hassan-Montero, Y. and Herrero-Solana, V.},
  booktitle = {Proc. InSciT 2006},
  day = {25--28},
  interhash = {4458142370e3c6a4fe656af2f822a0dc},
  intrahash = {99ffb0c3a76afe508f5ff6b219f72515},
  month = Oct,
  title = {{Improving Tag-Clouds as Visual Information Retrieval Interfaces}},
  year = 2006
}