Towards more effective online environmental information provision through tailored natural language generation: profiles of Scottish river user groups and an evaluative online experiment

Arts, Koen, Macleod, Christopher J. A., Ioris, Antonio A. R. ORCID: https://orcid.org/0000-0003-0156-2737, Han, Xiwu, Sripada, Somayajulu, Braga, João F., Maffey, Georgina, Jekjantuk, Nophadol, Zeng, Cheng and van der Wal, René 2019. Towards more effective online environmental information provision through tailored natural language generation: profiles of Scottish river user groups and an evaluative online experiment. Science of the Total Environment 673 , pp. 643-655. 10.1016/j.scitotenv.2019.03.440

PDF - Published Version Available under License Creative Commons Attribution. Download (2MB)

Abstract

As a result of societal transformations, political governance shifts, and advances in ICT, online information has become a crucial dimension in efforts by public authorities to make citizens better stewards of the environment. Yet their environmental information provision often lacks focus and knowledge of end users’ rationales, behaviours and appreciations. Our case study was 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. We examined if profiling of web page user groups (phase 1 of this study) and the subsequent associated employment of a specially designed Natural Language Generation (NLG) system (phase 2), could be steps towards more effective (tailored) online information provision. We employed an online survey (ran over 222 days, n=1264), interviews (n=32), workshops (n=15), as well as a small-scale yet advanced online experiment to evaluate (additional) information provision through NLG (including pre- and post-experiment surveys, ‘like’ buttons, feedback boxes and the monitoring of website visit behaviour through mouse clicks and time spent on 2 sections). In phase 1, we identified and described profiles for the three main user groups: ‘fishing’, ‘flood risk related’, and ‘kayaking’. The clear delineation and existence of welldistinguishable rationales was in itself an argument for profiling; the same river level information was used in entirely different ways by the three groups. Still, in terms of provided information categories through Natural Language Generation (phase 2), the category of ‘temporal trend’ came out as most important. The experiment also showed that, besides visual information, textual information can (still) be of much value; the additional textual layer of interpretation plays an important role in translating complex technical information to straightforward messages for the specific purposes of the user groups. A key recommendation is that tailoring of environmental information merits more attention as it can aid more effective, and potentially more inclusive, information provision and communication.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Geography and Planning (GEOPL)
Publisher:	Elsevier
ISSN:	0048-9697
Date of First Compliant Deposit:	6 July 2020
Date of Acceptance:	27 March 2019
Last Modified:	20 Nov 2024 16:45
URI:	https://orca.cardiff.ac.uk/id/eprint/133134

Citation Data

Cited 3 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item