Automated classification of congressional legislation

Purpura, Stephen; Hillard, Dustin

doi:10.1145/1146598.1146660

Cited by 44 publications

(31 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A more recent approach to automation in this type of problem is supervised learning Wilkerson 2007, 2008;Kwon, Hovy, and Shulman 2007;Purpura and Hillard 2006). Hand coding is done to a subset of texts that will serve as training data and to another subset of texts that serve as evaluation data (sometimes called "test data").…”

Section: Categorizing Texts: Methods Assumptions and Costsmentioning

confidence: 99%

How to Analyze Political Attention with Minimal Assumptions and Costs

Quinn

Monroe

Colaresi

et al. 2009

American J Political Sci

524

411

View full text Add to dashboard Cite

Section: Categorizing Texts: Methods Assumptions and Costsmentioning

confidence: 99%

How to Analyze Political Attention with Minimal Assumptions and Costs

Quinn

Monroe

Colaresi

et al. 2009

American J Political Sci

524

411

View full text Add to dashboard Cite

“…Like previous work (Purpura & Hillard, 2006), the method developed by Hopkins and King begins with documents labeled by humans, and then statistically analyzes word features to generate an efficient, discriminative, multiclass classification. However, their approach of estimating proportions is not appropriate for the researchers interested in mixed-methods research requiring the ability to analyze documents within a class.…”

Section: Downloaded By [Laurentian University] At 23:59 18 September mentioning

confidence: 99%

Computer-Assisted Topic Classification for Mixed-Methods Social Science Research

Hillard

Purpura

Wilkerson

2008

Journal of Information Technology & Politics

Self Cite

106

View full text Add to dashboard Cite

Social scientists interested in mixed-methods research have traditionally turned to human annotators to classify the documents or events used in their analyses. The rapid growth of digitized government documents in recent years presents new opportunities for research but also new challenges. With more and more data coming online, relying on human annotators becomes prohibitively expensive for many tasks. For researchers interested in saving time and money while maintaining confidence in their results, we show how a particular supervised learning system can provide estimates of the class of each document (or event). This system maintains high classification accuracy and provides accurate estimates of document proportions, while achieving reliability levels associated with human efforts. We estimate that it lowers the costs of classifying large numbers of complex documents by 80% or more.

show abstract

“…Alternatively, patterns may be determined from a large body of pre-classified items in a method known as machine learning. Some have found the accuracy from the application of machine learning to be comparable to knowledge engineering techniques [10], [11].…”

Section: Background In Text Classificationmentioning

confidence: 99%

Creating and visualizing fuzzy document classification

Gelernter

Cao

et al. 2009

2009 IEEE International Conference on Systems, Man and Cybernetics

View full text Add to dashboard Cite

Abstract-Fuzzy classification ranks items by degree rather than assigning them either within or without of a category. The novelty of our work is in integrating fuzzy classification algorithms with an interface to visualize fuzzy results. An advantage of our algorithms' 'fuzziness' is that it provides additional information per retrieved result that helps in deciding whether to drill down to the document or skip it. An advantage of our interface is that it allows users to visualize those differences quickly. We have created a prototype that allows the retrieval of journal articles by content word or by ontologysupported browse categories that can be selected independently or in tandem. Journal articles in our digital library pertain to paleontology, but techniques demonstrated viable in indexing and ranking paleo-journal literature should apply to other knowledge domains with little modification.

show abstract

Automated classification of congressional legislation

Cited by 44 publications

References 18 publications

How to Analyze Political Attention with Minimal Assumptions and Costs

How to Analyze Political Attention with Minimal Assumptions and Costs

Computer-Assisted Topic Classification for Mixed-Methods Social Science Research

Creating and visualizing fuzzy document classification

Contact Info

Product

Resources

About