Conference Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 393 - NLP and Text Analysis
Type: Contributed
Date/Time: Wednesday, August 10, 2022 : 8:30 AM to 10:20 AM
Sponsor: Section on Statistical Learning and Data Science
Abstract #320988
Title: Words and Phrases Associated with Absconding Supervision Among Probationers in Tarrant County Texas Using Natural Language Processing
Author(s): Jialiang Liu* and Sumihiro Suzuki
Companies: Temple University and Rush University
Keywords: natural language processing; text regression; text summarization; text classification
Abstract:

Due to the limited resources and the increasing population of probationers, little effort is made to locate those who fail to complete probation by absconding from supervision. We used text data from case notes written by probation officers in their one-on-one meetings with the probationers to explore words and phrases associated with those who abscond a text regression method known as concise comparative summarization to a random sample of case notes from adult misdemeanors and felony offenders who received probation in Tarrant County, Texas. We found that phrases such as “cannabinoids”, “technical violations”, “failed pay”, and “transfer intake” were directly associated with probation absconding. Currently, the case notes are kept only for record-keeping purposes. Our study identified previously unknown commonalities in the case notes of absconders and may contribute to a new surveillance system that uses case notes systematically.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2022 program