As of October 1, 2016, the SWUTC concluded its 28 years of operation and is no longer an active center of the Texas A&M Transportation Institute. The archived SWUTC website remains available here.

600451-00011

SWUTC Research Project Description

An Evaluation of the Effectiveness of Voice-to-Text Programs at Reducing Incidences of Distracted Driving

University:  Texas A&M University

Principal Investigator:
Christine Yager
Texas Transportation Institute
(979) 845-6528

Project Monitor:
Joel M. Cooper, Ph.D.
Precision Driving Research
[email protected]

Funding Source:  USDOT and State of Texas General Revenue Funds

Total Project Cost: $56,626

Project Number:  600451-00011

Date Started: 4/1/12

Estimation Completion Date:  3/31/13

Project Summary

Project Abstract:
According to the Cellular Telecommunications Industry Association, the average number of text messages sent in the U.S. per day exploded from 1.1 million in 2001 to 6.6 billion in 2011. With the growing burst in smartphone technology, this trend is likely to continue. Previous research has shown that manual-entry texting while driving leads to a reduction in driver reaction time, impairments in the ability to maintain lateral lane position and speed, fewer glances to the forward roadway, and an increase in the overall likelihood of a missed response event when compared to not texting while driving.

Adding to the potential in-vehicle distractions, there have been several texting mechanisms recently developed with the intention of reducing the effects of manual-entry texting. For example, automobile manufacturers have developed in-vehicle sync systems like the Ford SYNC and Toyota Entune that have the ability to sync a driver’s mobile device to the vehicle’s computer system. Once synced, the driver can perform certain mobile tasks, like selecting music, placing phone calls, and sending/receiving text messages. Wireless providers and mobile application developers have also created voice-to-text software aimed to alleviate the manual entry associated with texting. Perhaps the most popular example of this technology at the present time is Siri developed for the iPhone 4S. The software is intended to be the “hands-free” option of the texting world. A driver can tell Siri to send a text message to a contact person, and then speak the message they would like to be sent.

There have been few evaluations of these in-vehicle sync technologies, and the few that have been conducted fail to determine the effectiveness of the systems at reducing incidences of distracted driving compared to open-ended manual entry texting. Furthermore, the few studies that have been conducted only look at one in-vehicle system (Ford), whereas at the present time there are several drivers who do not have Ford SYNC or similar systems, but instead rely on applications installed on their mobile phones as another mechanism that drivers may use to send/receive text messages. But the effectiveness of these mobile device voice-to-text applications is unknown.

Have the newer technologies, such as smart phones and in-vehicle sync systems, led to an increase in texting and driving behavior or changed the way in which drivers send/receive text messages? Of the people who choose to text and drive, what method are they using to accomplish that task?

As previously described, there have been little to no evaluations on these new technologies and their impact on driver behavior and safety. As rapidly as technology is evolving, evaluations seeking the potential benefits or dangers of these technologies need to strive to keep up with the quick pace. Furthermore, the driving public needs to be regularly updated on the safety impacts of these new technologies. Present public educational campaigns aimed to reduce texting while driving, fail to mention the impacts of these newer texting mechanisms.

Project Objectives:
The primary objective of this research is to evaluate the effectiveness of these newer technology texting mechanisms at reducing incidences of distracted driving. Secondary objectives include:

  • To survey 200-300 U.S. drivers to determine what method drivers use to send/receive text messages and to identify which in-vehicle sync systems and voice-to-text mobile applications are commonly used
  • To rank the specific new technologies identified using objective criteria to identify frontrunners that would benefit from empirical testing
  • To select one to two frontrunners for empirical evaluation (closed course driving study)
  • To share the results with the media (after receiving approval from SWUTC)

Task Descriptions:
Task 1: Plan and Develop Survey
This task will consist of planning the method by which the survey will be conducted, as well as developing questions for the survey. The research team will perform a brief literature review to determine the direction the survey questions should take. This task will also consist of requesting IRB approval for both the survey and closed course testing.

Task 2: Conduct and Analyze Survey
Based on the plan outlined in Task 1, the research team will administer the survey data collection, and then analyze the results. Data analyses will consist of identifying commonly used texting technologies, and ranking them using an objective criteria to determine frontrunners for experimental testing on a closed course. The object criteria will consist of: number of errors produced by the voice-to-text program, number of key presses to access and use the program, time to complete the voice-to-text task, and how ambient noise levels affect the number of errors produced.

Task 3: Develop Experimental Plan
The research team will determine the proper closed course route, objectives, and detailed plan in this project task. The roadway and vehicle will be equipped to measure driver reaction time, speed, lane position, eye glances to forward roadway, and text messaging rate. Participants will use their own personal mobile devices.

Task 4: Setup Course and Gather Materials
Based on the plan laid out in Task 3, the closed driving course will be reserved and setup accordingly. Any and all materials necessary to conduct the closed course testing and record the performance metrics will be acquired and setup.

Task 5: Pilot Test and Quality Check Data
This project task will include pilot testing the experimental plan and quality checking the data for errors. Changes to the experimental procedure will be made as necessary before data collection begins. At the end of this task, participant recruitment will begin.

Task 6: Collect Data
Closed course testing will be conducted during daytime hours and according to the most recent experimental plan. Preliminary data reduction and analyses will be done to ensure quality data is being collected.

Task 7: Reduce and Analyze Data
Upon completion of Task 6, all data will be reduced and analyzed in greater detail. The data will be analyzed according to appropriate statistical methods.

Task 8: Write Final Research Report
The final report will include a complete description of the background, methodology, findings, and conclusions derived from the research project. Additionally, the final report will be condensed into a “media-friendly” document available for distribution to media contacts (pending approval from SWUTC sponsors).


Implementation of Research Outcomes:
6/1/13 – The study is the first of its kind, as it is based on the performance of 43 research participants driving an actual vehicle on a closed course. Other research efforts have evaluated manual versus voice-activated tasks using devices installed in a vehicle, but the SWUTC analysis is the first to compare voice-to-text and manual texting on a handheld device in an actual driving environment.

Published paper: Yager, C.E. (2013). Driver Safety Impacts of Voice-to-Text Mobile Applications. Proceedings of the Human Factors and Ergonomics Society Annual Meeting, September 2013.

Summary of media coverage generated by this research during the first week after press release on 04-25-13:

Broadcast
Placements         105
Audience             8,529,477
Earned media value    $434,727

Print/Online
400+ articles
4,468,763 | Circ (print)
393,648,687 | Unique page views online
$336,791 | Earned media value

Estimated Twitter Reach: 12,048,595+ (this was as of end of day 4/24 – tweets still going on 4/25 and 4/26)

This is how many followers the top tier media tweeted to:

  • NBC Nightly News (202,944)
  • AAA Traffic Safety (7,188)
  • My Fox Houston (20,714)
  • Huffington Post (2,958,819)
  • Mashable (3,249,700)
  • Edmunds Auto (47,632)
  • Dallas Morning News (80,842)
  • New York Daily News (124,205)
  • USA Today (542,659)
  • Reuters (2,799,703)
  • Wired & Wired Autopia (2,000,000 / 14,189)

Impacts/Benefits of Implementation:
6/1/13 – Through widespread media coverage of study results, this research had an impact on driver’s perceptions, attitudes, behavior and knowledge about texting while driving and the potential impacts on driver safety.

Specifically, the research improved public knowledge, attitudes, skills and abilities. And facilitated in changing behavior, practices, decision making, policies (including regulatory policies), and social actions.

Web Links:
Final Report

Video highlighting study results:  http://vimeo.com/64641918