SaferDrive

An NLG-based behaviour change support system for drivers

Research output: Contribution to journalArticle

2 Citations (Scopus)
6 Downloads (Pure)

Abstract

Despite the long history of Natural Language Generation (NLG) research, the potential for influencing real world behaviour through automatically generated texts has not received much attention. In this paper, we present SaferDrive, a behaviour change support system that uses NLG and telematic data in order to create weekly textual feedback for automobile drivers, which is delivered through a smartphone application. Usage-based car insurances use sensors to track driver behaviour. Although the data collected by such insurances could provide detailed feedback about the driving style, they are typically withheld from the driver and used only to calculate insurance premiums. SaferDrive instead provides detailed textual feedback about the driving style, with the intent to help drivers improve their driving habits. We evaluate the system with real drivers and report that the textual feedback generated by our system does have a positive influence on driving habits, especially with regard to speeding.

Original languageEnglish
Pages (from-to)551-588
Number of pages38
JournalNatural Language Engineering
Volume24
Issue number4
Early online date19 Feb 2018
DOIs
Publication statusPublished - Jul 2018

Fingerprint

Insurance
driver
Feedback
insurance
language
Automobile drivers
habits
Railroad tracks
Smartphones
telematics
premium
Railroad cars
motor vehicle
Natural Language
Language Generation
Sensors
history
Habit

Cite this

SaferDrive : An NLG-based behaviour change support system for drivers. / Braun, Daniel; Reiter, Ehud; Siddharthan, Advaith.

In: Natural Language Engineering, Vol. 24, No. 4, 07.2018, p. 551-588.

Research output: Contribution to journalArticle

@article{a9c98ec42e5b4d98ae2484c08ad7791a,
title = "SaferDrive: An NLG-based behaviour change support system for drivers",
abstract = "Despite the long history of Natural Language Generation (NLG) research, the potential for influencing real world behaviour through automatically generated texts has not received much attention. In this paper, we present SaferDrive, a behaviour change support system that uses NLG and telematic data in order to create weekly textual feedback for automobile drivers, which is delivered through a smartphone application. Usage-based car insurances use sensors to track driver behaviour. Although the data collected by such insurances could provide detailed feedback about the driving style, they are typically withheld from the driver and used only to calculate insurance premiums. SaferDrive instead provides detailed textual feedback about the driving style, with the intent to help drivers improve their driving habits. We evaluate the system with real drivers and report that the textual feedback generated by our system does have a positive influence on driving habits, especially with regard to speeding.",
author = "Daniel Braun and Ehud Reiter and Advaith Siddharthan",
year = "2018",
month = "7",
doi = "10.1017/S1351324918000050",
language = "English",
volume = "24",
pages = "551--588",
journal = "Natural Language Engineering",
issn = "1351-3249",
publisher = "Cambridge University Press",
number = "4",

}

TY - JOUR

T1 - SaferDrive

T2 - An NLG-based behaviour change support system for drivers

AU - Braun, Daniel

AU - Reiter, Ehud

AU - Siddharthan, Advaith

PY - 2018/7

Y1 - 2018/7

N2 - Despite the long history of Natural Language Generation (NLG) research, the potential for influencing real world behaviour through automatically generated texts has not received much attention. In this paper, we present SaferDrive, a behaviour change support system that uses NLG and telematic data in order to create weekly textual feedback for automobile drivers, which is delivered through a smartphone application. Usage-based car insurances use sensors to track driver behaviour. Although the data collected by such insurances could provide detailed feedback about the driving style, they are typically withheld from the driver and used only to calculate insurance premiums. SaferDrive instead provides detailed textual feedback about the driving style, with the intent to help drivers improve their driving habits. We evaluate the system with real drivers and report that the textual feedback generated by our system does have a positive influence on driving habits, especially with regard to speeding.

AB - Despite the long history of Natural Language Generation (NLG) research, the potential for influencing real world behaviour through automatically generated texts has not received much attention. In this paper, we present SaferDrive, a behaviour change support system that uses NLG and telematic data in order to create weekly textual feedback for automobile drivers, which is delivered through a smartphone application. Usage-based car insurances use sensors to track driver behaviour. Although the data collected by such insurances could provide detailed feedback about the driving style, they are typically withheld from the driver and used only to calculate insurance premiums. SaferDrive instead provides detailed textual feedback about the driving style, with the intent to help drivers improve their driving habits. We evaluate the system with real drivers and report that the textual feedback generated by our system does have a positive influence on driving habits, especially with regard to speeding.

U2 - 10.1017/S1351324918000050

DO - 10.1017/S1351324918000050

M3 - Article

VL - 24

SP - 551

EP - 588

JO - Natural Language Engineering

JF - Natural Language Engineering

SN - 1351-3249

IS - 4

ER -