About | HeinOnline Law Journal Library | HeinOnline Law Journal Library | HeinOnline
LOG IN
LOG IN

92 U. Cin. L. Rev. 1108 (2023-2024)
Computationally Assessing Suspicion

handle is hein.journals/ucinlr92 and id is 1108 raw text is: COMPUTATIONALLY ASSESSING SUSPICION* Wesley M. Oliver, Morgan A. Gray, Jaromir Savelka & Kevin D. Ashley** CONTENTS INTRODUCTION................................................................................. 1109 I. REASONABLE SUSPICION CAN BE MODELED........................................ 1116 A. The Law of Drug Interdiction Stops.................................................... 1118 B. The Ill-Defi ned Reasonable Suspicion Standard................................. 1123 C. The Potential Benefits of an Automated Standard............................... 1125 II. IDENTIFYING LEGALLY RELEVANT FACTORS WITH LANGUAGE M ODELS ......................................................................... 1127 A. Developing a List of Suspicious Factors............................................. 1128 B. Annotating a Sample of 211 Cases ..................................................... 1139 C. Using Language Models to Identify Factors....................................... 1141 III. ASSESSING EXTENDED VEHICLE DETENTIONS BASED ON REASONABLE SUSPICION WITH MACHINE LEARNING ............................ 1147 A. Explaining the Machine Learning Models.......................................... 1149 1. Tree-Based Models ..................................................................... 1153 2. k-N earest N eighbors.................................................................... 1157 3. L inear M odels............................................................................. 1159 4. N eural N etw orks......................................................................... 1162 B. Minimizing Biased Decisions and Fruitless Searches......................... 1163 CONCLUSION .................................................................................... 1169 * The authors wish to thank Mike Livermore, Aileen Nielsen, Andrea Roth, Eric Talley, and participants at the Second Annual Fordham, University of Virginia, and ETH Zurich Data Science and Law Conference for very helpful comments on a previous draft of this Article. We also recognize the excellent research assistance of Rachel Schade. ** Wesley M. Oliver is Professor of Law, Thomas R. Kline School of Law of Duquesne University. Morgan A. Gray is a Ph.D. Candidate in Intelligent Systems, University of Pittsburgh School of Computing and Information. Jaromir Savelka is a Computer Science Associate Research Fellow, Carnegie Mellon University School of Computer Science. Kevin D. Ashley is Professor of Law and Intelligent Systems, University of Pittsburgh School of Law and School of Computing and Information. 1108

What Is HeinOnline?

HeinOnline is a subscription-based resource containing thousands of academic and legal journals from inception; complete coverage of government documents such as U.S. Statutes at Large, U.S. Code, Federal Register, Code of Federal Regulations, U.S. Reports, and much more. Documents are image-based, fully searchable PDFs with the authority of print combined with the accessibility of a user-friendly and powerful database. For more information, request a quote or trial for your organization below.



Short-term subscription options include 24 hours, 48 hours, or 1 week to HeinOnline.

Purchase Access

Contact us for annual subscription options:

Contact Us

Already a HeinOnline Subscriber?

Log In

profiles profiles most