John F Betak

The University of Texas at Austin, Center for Risk Management and Insurance, Faculty Member

Rutgers, The State University of New Jersey, Center for Advanced Infrastructure & Transportation, Research Fellow - Freight & Maritime Program

Followers

Following

Co-authors

Public Views

Senior researcher addressing transportation systems risk management, organizational decision making and marketing strategies.
Address: Albuquerque, New Mexico, United States

less

Interests

Uploads

Papers by John F Betak

A Comparison of LSA and LDA for the Analysis of Railroad Accident Text

Journal of Ubiquitous Systems and Pervasive Networks

Different Market Methods for Transferring Financial Risks in Construction

Risk Management in Construction Projects [Working Title]

Some Musings on Cognitive Processes and Spatial Behavior

Risk/Benefit Analysis in a Study of Vehicle Driving Habits

IRB: Ethics and Human Research, 1980

Programmable research approach to transit marketing

A program of research designed to illustrate a potentially useful series of methodologies for tra... more A program of research designed to illustrate a potentially useful series of methodologies for transportation marketing research is reported in three phases. Phase one of the research identified the characteristics of individuals who were likely to switch their mode of transportation from the automobile to mass transit, and investigated the transit-system characteristics that determined this modal choice. Based on the results of phase one, phases two and three, respectively, explored transit-use promotional strategies and used trade-off (conjoint) analysis to identify the relative levels of transit system characteristics that potential switchers to mass transit might be willing to accept. The research program took place in a medium-sized southwestern city. Travel patterns in the city reflect the dominance of the car, with over 97 percent of trips taken in private automobiles. The results of the research are specific to the characteristics of this research investigation; the methodolo...

2004 Evaluation Solvency and Efficiency Performances in US P

Identifying Themes in Railroad Equipment Accidents Using Text Mining and Text Visualization

by John F Betak and Trefor Williams

Text Mining Analysis of Railroad Accident Investigation Reports

by John F Betak and Trefor Williams

The National Transportation Safety Board in the United States and the Transportation Safety Board... more The National Transportation Safety Board in the United
States and the Transportation Safety Board of Canada publish
reports about major railroad accidents. The text from these
accident reports were analyzed using the text mining techniques
of probabilistic topic modeling and k-means clustering to
identify the recurring themes in major railroad accidents. The
output from these analyses indicates that the railroad accidents
can be successfully grouped into different topics. The output
also suggests that recurring accident types are track defects,
wheel defects, grade crossing accidents, and switching
accidents. A major difference between the Canadian and U.S.
reports is the finding that accidents related to bridges are found
to be more prominent in the Canadian reports.

Using Data Visualization to Analyze Grade Crossing Accidents

by John F Betak, Trefor Williams, and James Abello

The Federal Railroad Administration grade crossing accident database contains numerous interrelat... more The Federal Railroad Administration grade crossing accident
database contains numerous interrelated variables.
Understanding of how the variables are interrelated can be
enhanced using modern visualization techniques. These
techniques can allow managers from railroads and government
agencies to find complex variables relationships not usually
provided by routine statistical analyses. For this research we
have developed several dashboards of linked visualizations
using the Weave data visualization software [5]. Our
visualizations explore various accident types of concern to the
railroad industry including trespassing and pedestrian accidents,
passenger train accidents, actions of highway users involved in
accidents, and the effect of different types of warning devices
on grade crossing accidents. In addition, we are currently
developing an advanced visualization system that views the
accident data as time varying events occurring over a fixed
grade crossings topology. This view allows the application of a
recent network data abstraction termed “Graph Cards.” We present initial examples of the advanced system that provides a
variety of filtering mechanisms to view statistical distributions
and their time varying behavior over the grade crossings
topology.

APPLYING TOPIC MODELING TO RAILROAD GRADE CROSSING ACCIDENT REPORT TEXT

by John F Betak and Trefor Williams

The FRA railroad grade crossing accident database contains text comment fields that may provide a... more The FRA railroad grade crossing accident database
contains text comment fields that may provide additional
information about grade crossing accidents. New text mining
algorithms provide the potential to automatically extract
information from text that can enhance traditional numeric
analyses. Topic modeling algorithms are statistical methods
that analyze the words of original texts to automatically
discover the themes that run through them. A frequently used
topic-modeling algorithm is Latent Dirichlet Analysis (LDA).
In this paper we will show several examples of how labeled
LDA can be applied to the FRA grade crossing data to better
understand categories of words and phrases that are associated
with various types of grade crossing accidents

Identifying Themes in Railroad Equipment Accidents Using Text Mining and Text Visualization

by John F Betak and Trefor Williams

Developments in text mining now allow useful information to be automatically extracted from text.... more Developments in text mining now allow useful information to be automatically extracted from text. The Federal Railroad Administration (FRA) publishes a database of railroad equipment accidents. These accident records contain numeric data describing the accident and a text description of the accident. This paper discusses how Latent Dirichlet Analysis (LDA), a text-mining algorithm, can be used to identify major recurring accident themes from the text in the FRA reports. Other themes were also identified. Equipment accident reports from 2005 to 2015 were studied. This analysis identified railroad grade crossing accidents with large trucks, shoving accidents, and hump yard accidents as major themes in the accident reports. An alternative method of analyzing the text, text clustering, was also used to study the FRA data. This analysis also identified highway truck accidents, shoving and hump yard accidents as recurring accident themes. Additionally, it identified the accident themes of kicking cars, wide gauge and broken rails as major themes. Application of these two recently developed analytic techniques to the FRA databases demonstrates that large railroad databases containing text information can be automatically parsed to reveal insights into accident themes not easily ascertained via traditional statistical analyses of numeric data. Further, such analytical tools could be used on other railroad databases containing other text materials to identify precursor clusters of factors that may lead to events such as track failures, equipment failures, etc.

Object Identification in Aerial Photographs, A Preliminary Report

A Study of Alternative Means of Financing Mass Transportation Systems

Behavioral Geography, Multidimensional Scaling and the Mind

Interoperability in Intermodal Freight Transport

2004 Evaluation Solvency and Efficiency Performances in US P

by John F Betak, Karen Smith, and Patrick Brockett

Syntactic and Subjective Complexity: A Simple Test of a Two-dimensional Language Model

Geographical Analysis, 2010

suggests that twodimensional displays, such as maps, aerial photographs, polygons, etc., may be g... more suggests that twodimensional displays, such as maps, aerial photographs, polygons, etc., may be generated and/or described by twodimensional languages. Furthermore, it is suggested that human observers use such a language t o interpret, describe, and analyze an array of twodimensional data t o obtain information. These notions are expanded on by postulating a perceptual device M containing at least two components MI and M2. The first is a short-term memory that performs computations on an input as it is received and transmits the results of these computations to the second, which contains a long-term memory in which is stored a generative grammar. Since memory is finite and quite limited for real-time analytic operations [ 5 , 1 I ] , it is hypothesized that humans (assuming M is plausible for humans) will exhibit difficulty with displays constructed in particular ways. Specifically, displays with repeated nesting will be difficult t o interpret, etc.; displays with multibranching constructions will be optimal in terms of performance; displays nesting a long and complex element will be poorly treated. It is further suggested that a simple way to discover whether there is any meaningful relationship between these ideas and the way humans respond to displays is to perform a pairedcomparisons analysis on displays exhibiting different constructions. The focus of research here is on this specific approach t o evaluating

Download

Psychological meaning: Empirical directions for identification and strategy development

by John F Betak, linda golden, and Mark Alpert

Psychology & Marketing, 1989

Meaning is important in attitude and perception research. Consumers can assign meanings to produc... more Meaning is important in attitude and perception research. Consumers can assign meanings to product attributes that do not conform to standard usage or have not been considered by the researcher, and a misunderstanding of that meaning can result in ineffective marketing strategy. This paper explores different levels of meaning and, through empirical example, presents a methodology for investigating the psychological meaning of attributes. Alternative methodologies for studying psychological meaning are discussed, and techniques for investigating the strategic operationalization of empirical semantic meaning results are illustrated using a mass transit study.

Attracting Potential Switchers to Mass Transit: Mode Choice as a Multi-Attribute Decision Model

by linda golden, John F Betak, and Mark Alpert

Policy makers and transportation planners frequently have to make decisions regarding the charact... more Policy makers and transportation planners frequently have to make decisions regarding the characteristics to incorporate into new or revised mass transit systems. To ensure consumer patronage, it is necessary to identify the trade-offs which are most likely to attract potential consumers. This paper uses conjoint analysis to identify such trade-offs and presents results and policy implications of using these procedures in one medium-sized American city.

Mode Choice as a Multiple Criteria Decision Task

by John F Betak, linda golden, and Mark Alpert

Policy makers and transportation planners frequently have to make decisions regarding characteris... more Policy makers and transportation planners frequently have to make decisions regarding characteristics to incorporate into new or revised transportation systems. Typically, the planner and policy maker is unable to incorporate all the consumer's desired transportation characteristics into the system. Thus, the planner and policy maker must take trade-offs in system characteristics. To ensure consumer patronage, it is necessary to identify the trade-offs which are most likely to attract consumers. This paper presents a methodology for identifying such trade-offs and presents results and policy implications of using these procedures in one medium size southwestern city.

John F Betak

Uploads

Papers by John F Betak

Log In