@article {newman_probabilistic_2006,
	title = {Probabilistic topic decomposition of an eighteenth-century American newspaper},
	journal = {Journal of the American Society for Information Science and Technology},
	volume = {57},
	number = {6},
	year = {2006},
	note = {00040},
	pages = {753{\textendash}767},
	abstract = {This article begins by identifying that, due to the exponential growth in web documents, there is a growing need for a system for characterizing, classifying, and indexing this data. In this paper, Newman and Block explore three types of topic decomposition models that are designed to achieve this organized information retrieval. Throughout the entirety of the article, Newman and Block use the Pennsylvania Gazette as their case study and through this data they illustrate the use of three different methodologies and compare their success in identifying and displaying topics from the newspaper. Newman and Block conclude that this style of textual analysis is important because it identifies hidden topics in the text rather than merely collating keywords.  },
	issn = {1532-2890},
	doi = {10.1002/asi.20342},
	url = {http://onlinelibrary.wiley.com/doi/10.1002/asi.20342/abstract},
	author = {Newman, David J. and Block, Sharon}
}