國立高雄大學圖資館 |

Language: English

Back

Project Recon: A Computational Framework for and Analysis of the California Parole Hearing System.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Project Recon: A Computational Framework for and Analysis of the California Parole Hearing System.
Author:	Hong, Jenny.
Published:	Ann Arbor : ProQuest Dissertations & Theses, 2023
Description:	197 p.
Notes:	Source: Dissertations Abstracts International, Volume: 84-12, Section: A.
Notes:	Advisor: Ugander, Johan;Manning, Christopher.
Contained By:	Dissertations Abstracts International84-12A.
Subject:	Language.
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30462691
ISBN:	9798379653576

Project Recon: A Computational Framework for and Analysis of the California Parole Hearing System.
Hong, Jenny.

Project Recon: A Computational Framework for and Analysis of the California Parole Hearing System. - Ann Arbor : ProQuest Dissertations & Theses, 2023 - 197 p.

Source: Dissertations Abstracts International, Volume: 84-12, Section: A.

Thesis (Ph.D.)--Stanford University, 2023.

This item must not be sold to any third party vendors.

Parole decisions can tip a sentence toward fifteen years or fifty. Despite the great power that parole boards hold, their decision processes are poorly documented and largely hidden from public scrutiny. Parole hearings produce almost no structured data, only an unstructured transcript of hearing dialogue several hundred pages in length. In the following dissertation, we use natural language processing to analyze the transcripts of 35,105 parole hearings held between 2007 and 2019 for candidates serving life sentences in California, totalling approximately five million pages. Through regression analyses of data extracted from the transcripts, after controlling for relevant case factors, we find that several factors outside of the candidate’s control explain hearing outcomes. We find that commissioners vary widely in their punitiveness in previously unobserved ways; the assignment to a particular commissioner significantly influences the hearing outcome. Racial disparities limit the quality of legal representation that parole candidates receive as well as their voice in the hearing dialogue, and both significantly predict the parole outcome after again controlling for case factors. Previous analyses of parole systems have been limited by the unavailability of structured data or the task of hand-annotating hearing transcripts. Our results thus provide the most comprehensive picture of a parole system studied to date. While our results carry direct implications for legislative parole reform, our methodology—using machine learning to analyze legal hearings—can be extended to many other procedures in criminal and administrative law with limited structured data.

ISBN: 9798379653576Subjects--Topical Terms:

180769
Language.

Project Recon: A Computational Framework for and Analysis of the California Parole Hearing System.
LDR:02829nmm a2200349 4500 001 655760
005 20240414211923.5
006 m o d
007 cr#unu||||||||
008 240620s2023 ||||||||||||||||| ||eng d
020 $a 9798379653576
035 $a (MiAaPQ)AAI30462691
035 $a (MiAaPQ)STANFORDxn213ms8118
035 $a AAI30462691
040 $a MiAaPQ $c MiAaPQ
100 1 $a Hong, Jenny. $3 966827
245 1 0 $a Project Recon: A Computational Framework for and Analysis of the California Parole Hearing System.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2023
300 $a 197 p.
500 $a Source: Dissertations Abstracts International, Volume: 84-12, Section: A.
500 $a Advisor: Ugander, Johan;Manning, Christopher.
502 $a Thesis (Ph.D.)--Stanford University, 2023.
506 $a This item must not be sold to any third party vendors.
520 $a Parole decisions can tip a sentence toward fifteen years or fifty. Despite the great power that parole boards hold, their decision processes are poorly documented and largely hidden from public scrutiny. Parole hearings produce almost no structured data, only an unstructured transcript of hearing dialogue several hundred pages in length. In the following dissertation, we use natural language processing to analyze the transcripts of 35,105 parole hearings held between 2007 and 2019 for candidates serving life sentences in California, totalling approximately five million pages. Through regression analyses of data extracted from the transcripts, after controlling for relevant case factors, we find that several factors outside of the candidate’s control explain hearing outcomes. We find that commissioners vary widely in their punitiveness in previously unobserved ways; the assignment to a particular commissioner significantly influences the hearing outcome. Racial disparities limit the quality of legal representation that parole candidates receive as well as their voice in the hearing dialogue, and both significantly predict the parole outcome after again controlling for case factors. Previous analyses of parole systems have been limited by the unavailability of structured data or the task of hand-annotating hearing transcripts. Our results thus provide the most comprehensive picture of a parole system studied to date. While our results carry direct implications for legislative parole reform, our methodology—using machine learning to analyze legal hearings—can be extended to many other procedures in criminal and administrative law with limited structured data.
590 $a School code: 0212.
650 4 $a Language. $3 180769
650 4 $a Linguistics. $3 176897
650 4 $a Decision trees. $3 280975
650 4 $a Human performance. $3 966828
650 4 $a Annotations. $3 966829
650 4 $a Error correction & detection. $3 915679
650 4 $a Attorneys. $3 942620
650 4 $a Retrieval performance measures. $3 966830
650 4 $a Law. $3 207600
690 $a 0679
690 $a 0290
690 $a 0398
710 2 $a Stanford University. $3 212607
773 0 $t Dissertations Abstracts International $g 84-12A.
790 $a 0212
791 $a Ph.D.
792 $a 2023
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30462691