Law Commons^™

Active Learning For E-Rulemaking: Public Comment Categorization, Stephen Purpura, Claire Cardie, Jesse Simons

Cornell e-Rulemaking Initiative Publications

We address the e-rulemaking problem of reducing the manual labor required to analyze public comment sets. In current and previous work, for example, text categorization techniques have been used to speed up the comment analysis phase of e-rulemaking - by classifying sentences automatically, according to the rule-specific issues [2] or general topics that they address [7, 8]. Manually annotated data, however, is still required to train the supervised inductive learning algorithms that perform the categorization. This paper, therefore, investigates the application of active learning methods for public comment categorization: we develop two new, general-purpose, active learning techniques to selectively sample …

A Study In Rule-Specific Issue Categorization For E-Rulemaking, Claire Cardie, Cynthia R. Farina, Adil Aijaz, Matt Rawding, Stephen Purpura

Cornell e-Rulemaking Initiative Publications

We address the e-rulemaking problem of categorizing public comments according to the issues that they address. In contrast to previous text categorization research in e-rulemaking [5, 6], and in an attempt to more closely duplicate the comment analysis process in federal agencies, we employ a set of rule-specific categories, each of which corresponds to a significant issue raised in the comments. We describe the creation of a corpus to support this text categorization task and report interannotator agreement results for a group of six annotators. We outline those features of the task and of the e-rulemaking context that engender both …

Facilitating Issue Categorization & Analysis In Rulemaking, Thomas R. Bruce, Claire Cardie, Cynthia R. Farina, Stephen Purpura

Cornell e-Rulemaking Initiative Publications

One task common to all notice-and-comment rulemaking is identifying substantive claims and arguments made in the comments by stakeholders and other members of the public. Extracting and summarizing this material may be helpful to internal decisionmaking; to produce the legally required public explanation of the final rule, it is essential. When comments are lengthy or numerous, natural language processing and machine learning techniques can help the rulewriter work more quickly and comprehensively. Even when a smaller volume of comment material is received, the ability to annotate relevant portions and store information about them in a way that permits retrieval and …

An Erulemaking Corpus: Identifying Substantive Issues In Public Comments, Claire Cardie, Cynthia R. Farina, Matt Rawding, Adil Aijaz

Cornell e-Rulemaking Initiative Publications

We describe the creation of a corpus that supports a real-world hierarchical text categorization task in the domain of electronic rulemaking (eRulemaking). Features of the task and of the eRulemaking domain engender both a non-traditional text categorization corpus and a correspondingly difficult machine learning task. Interannotator agreement results are presented for a group of six annotators. We also briefly describe the results of experiments that apply standard and hierarchical text categorization techniques to the eRulemaking data sets. The corpus is the first in a series of related sentence-level text categorization corpora to be developed in the eRulemaking domain.

A Study In Rule-Specific Issue Categorization For E-Rulemaking, Claire Cardie, Cynthia R. Farina, Adil Aijaz, Matt Rawding, Stephen Purpura

Cornell Law Faculty Publications

We address the e-rulemaking problem of categorizing public comments according to the issues that they address. In contrast to previous text categorization research in e-rulemaking, and in an attempt to more closely duplicate the comment analysis process in federal agencies, we employ a set of rule-specific categories, each of which corresponds to a significant issue raised in the comments. We describe the creation of a corpus to support this text categorization task and report interannotator agreement results for a group of six annotators. We outline those features of the task and of the e-rulemaking context that engender both a non-traditional …

The State Attorney General And Preemption, Trevor W. Morrison

Cornell Law Faculty Publications

According to the National Association of Attorneys General, "the rise of preemption of state laws and regulations by federal administrative agencies, rather than directly by Congress" is "[p]erhaps the most significant development in federal preemption in the last several decades." This kind of preemption is typically claimed in an agency ruling or regulation declaring certain state laws or activities preempted, even though the underlying statute says nothing about preemption in those areas. That an association of state attorneys general would view "agency preemption" as particularly worrisome is hardly surprising: the main casualties are often state attorneys general, whose broad investigative …

Achieving The Potential: The Future Of Federal E-Rulemaking: A Report To Congress And The President, Committee On The Status And Future Of Federal E-Rulemaking (U.S.), Cynthia R. Farina

Cornell Law Faculty Publications

Federal regulations are among the most important and widely used tools for implementing the laws of the land – affecting the food we eat, the air we breathe, the safety of consumer products, the quality of the workplace, the soundness of our financial institutions, the smooth operation of our businesses, and much more. Despite the central role of rulemaking in executing public policy, both regulated entities (especially small businesses) and the general public find it extremely difficult to follow the regulatory process; actively participating in it is even harder.

E-rulemaking is the use of technology (particularly, computers and the World …