Towards more effective online environmental information provision through tailored Natural Language Generation: Profiles of Scottish river user groups and an evaluative online experiment

K.A.J. Arts*, C.J.A. Macleod, A.A.R. Ioris, X. Han, S. Sripada, J.F. Braga, Georgina Maffey, N. Jekjantuk, Cheng Zeng, R. van der Wal

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

As a result of societal transformations, political governance shifts, and advances in ICT, online information has become crucial in efforts by public authorities to make citizens better stewards of the environment. Yet, their environmental information provision may not always be attuned to end users' rationales, behaviours and appreciations. This study revolves around dynamic river level information provided by an environmental regulator – updated once a day or more, and collected by a sensor network of 333 gauging stations along 232 Scottish rivers. Employing an elaborate mixed methods approach with qualitative and quantitative elements, we examined if profiling of web page user groups and the subsequent employment of a specially designed Natural Language Generation (NLG) system could foster more effective online information provision. We identified profiles for the three main user groups: fishing, flood risk related, and paddling. The existence of well-distinguishable rationales and characteristics was in itself an argument for profiling; the same river level information was used in entirely different ways by the three groups. We subsequently constructed an advanced online experiment that implemented NLG based on live river level data. We found that textual information can be of much value in translating dynamic technical information into straightforward messages for the specific purposes of the user groups. We conclude that tailored NLG could be widely used in more effective online environmental information provision, and we provide five practical recommendations for public authorities and other information providers.
Original languageEnglish
Pages (from-to)643-655
JournalScience of the Total Environment
Volume673
DOIs
Publication statusPublished - 10 Jul 2019

Fingerprint

Rivers
river
experiment
Experiments
Gaging
Sensor networks
Websites
environmental information
fishing
sensor
public

Cite this

Arts, K.A.J. ; Macleod, C.J.A. ; Ioris, A.A.R. ; Han, X. ; Sripada, S. ; Braga, J.F. ; Maffey, Georgina ; Jekjantuk, N. ; Zeng, Cheng ; van der Wal, R. / Towards more effective online environmental information provision through tailored Natural Language Generation: Profiles of Scottish river user groups and an evaluative online experiment. In: Science of the Total Environment. 2019 ; Vol. 673. pp. 643-655.
@article{dd0b476d64634a35ab55907a06ef9acc,
title = "Towards more effective online environmental information provision through tailored Natural Language Generation: Profiles of Scottish river user groups and an evaluative online experiment",
abstract = "As a result of societal transformations, political governance shifts, and advances in ICT, online information has become crucial in efforts by public authorities to make citizens better stewards of the environment. Yet, their environmental information provision may not always be attuned to end users' rationales, behaviours and appreciations. This study revolves around dynamic river level information provided by an environmental regulator – updated once a day or more, and collected by a sensor network of 333 gauging stations along 232 Scottish rivers. Employing an elaborate mixed methods approach with qualitative and quantitative elements, we examined if profiling of web page user groups and the subsequent employment of a specially designed Natural Language Generation (NLG) system could foster more effective online information provision. We identified profiles for the three main user groups: fishing, flood risk related, and paddling. The existence of well-distinguishable rationales and characteristics was in itself an argument for profiling; the same river level information was used in entirely different ways by the three groups. We subsequently constructed an advanced online experiment that implemented NLG based on live river level data. We found that textual information can be of much value in translating dynamic technical information into straightforward messages for the specific purposes of the user groups. We conclude that tailored NLG could be widely used in more effective online environmental information provision, and we provide five practical recommendations for public authorities and other information providers.",
author = "K.A.J. Arts and C.J.A. Macleod and A.A.R. Ioris and X. Han and S. Sripada and J.F. Braga and Georgina Maffey and N. Jekjantuk and Cheng Zeng and {van der Wal}, R.",
year = "2019",
month = "7",
day = "10",
doi = "10.1016/j.scitotenv.2019.03.440",
language = "English",
volume = "673",
pages = "643--655",
journal = "Science of the Total Environment",
issn = "0048-9697",
publisher = "Elsevier",

}

Towards more effective online environmental information provision through tailored Natural Language Generation: Profiles of Scottish river user groups and an evaluative online experiment. / Arts, K.A.J.; Macleod, C.J.A.; Ioris, A.A.R.; Han, X.; Sripada, S.; Braga, J.F.; Maffey, Georgina; Jekjantuk, N.; Zeng, Cheng; van der Wal, R.

In: Science of the Total Environment, Vol. 673, 10.07.2019, p. 643-655.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Towards more effective online environmental information provision through tailored Natural Language Generation: Profiles of Scottish river user groups and an evaluative online experiment

AU - Arts, K.A.J.

AU - Macleod, C.J.A.

AU - Ioris, A.A.R.

AU - Han, X.

AU - Sripada, S.

AU - Braga, J.F.

AU - Maffey, Georgina

AU - Jekjantuk, N.

AU - Zeng, Cheng

AU - van der Wal, R.

PY - 2019/7/10

Y1 - 2019/7/10

N2 - As a result of societal transformations, political governance shifts, and advances in ICT, online information has become crucial in efforts by public authorities to make citizens better stewards of the environment. Yet, their environmental information provision may not always be attuned to end users' rationales, behaviours and appreciations. This study revolves around dynamic river level information provided by an environmental regulator – updated once a day or more, and collected by a sensor network of 333 gauging stations along 232 Scottish rivers. Employing an elaborate mixed methods approach with qualitative and quantitative elements, we examined if profiling of web page user groups and the subsequent employment of a specially designed Natural Language Generation (NLG) system could foster more effective online information provision. We identified profiles for the three main user groups: fishing, flood risk related, and paddling. The existence of well-distinguishable rationales and characteristics was in itself an argument for profiling; the same river level information was used in entirely different ways by the three groups. We subsequently constructed an advanced online experiment that implemented NLG based on live river level data. We found that textual information can be of much value in translating dynamic technical information into straightforward messages for the specific purposes of the user groups. We conclude that tailored NLG could be widely used in more effective online environmental information provision, and we provide five practical recommendations for public authorities and other information providers.

AB - As a result of societal transformations, political governance shifts, and advances in ICT, online information has become crucial in efforts by public authorities to make citizens better stewards of the environment. Yet, their environmental information provision may not always be attuned to end users' rationales, behaviours and appreciations. This study revolves around dynamic river level information provided by an environmental regulator – updated once a day or more, and collected by a sensor network of 333 gauging stations along 232 Scottish rivers. Employing an elaborate mixed methods approach with qualitative and quantitative elements, we examined if profiling of web page user groups and the subsequent employment of a specially designed Natural Language Generation (NLG) system could foster more effective online information provision. We identified profiles for the three main user groups: fishing, flood risk related, and paddling. The existence of well-distinguishable rationales and characteristics was in itself an argument for profiling; the same river level information was used in entirely different ways by the three groups. We subsequently constructed an advanced online experiment that implemented NLG based on live river level data. We found that textual information can be of much value in translating dynamic technical information into straightforward messages for the specific purposes of the user groups. We conclude that tailored NLG could be widely used in more effective online environmental information provision, and we provide five practical recommendations for public authorities and other information providers.

U2 - 10.1016/j.scitotenv.2019.03.440

DO - 10.1016/j.scitotenv.2019.03.440

M3 - Article

VL - 673

SP - 643

EP - 655

JO - Science of the Total Environment

JF - Science of the Total Environment

SN - 0048-9697

ER -