When a Graph is Poorer than 100 Words

A Comparison of Computerised Natural Language Generation, Human Generated Descriptions and Graphical Displays in Neonatal Intensive Care

Marian van der Meulen, Robert H. Logie, Yvonne Freer, Cindy Sykes, Neil McIntosh, Jim Hunter

Research output: Contribution to journalArticle

19 Citations (Scopus)

Abstract

Volunteer staff from a Neonatal Intensive Care Unit (NICU) were presented with sets of anonymised physiological data recorded over approximately 45 minute periods from former patients. Staff were asked to select medical/nursing actions appropriate for each of the patients whose data were displayed. Data were shown in one of three conditions (a) as multiple line graphs similar to those commonly shown on the ward, or as textual descriptions generated by (b) expert medical/nursing staff or (c) computerised natural language generation (NLG). An overall advantage was found for the human generated text, but NLG resulted in decisions that were at least as good as those for the graphical displays with which staff were familiar. It is suggested that NLG might offer a viable automated approach to removing noise and artefacts in real, complex and dynamic data sets, thereby reducing visual complexity and mental workload, and enhancing decision-making particularly for inexperienced staff.
Original languageEnglish
Pages (from-to)77-89
Number of pages13
JournalApplied Cognitive Psychology
Volume24
Issue number1
Early online date19 Dec 2008
DOIs
Publication statusPublished - Jan 2010

Fingerprint

Neonatal Intensive Care
Language
Nursing Staff
Neonatal Intensive Care Units
Medical Staff
Workload
Artifacts
Noise
Volunteers
Decision Making
Nursing
Natural Language
Graph
Language Generation
Intensive Care
Staff

Cite this

When a Graph is Poorer than 100 Words : A Comparison of Computerised Natural Language Generation, Human Generated Descriptions and Graphical Displays in Neonatal Intensive Care. / van der Meulen, Marian; Logie, Robert H.; Freer, Yvonne; Sykes, Cindy; McIntosh, Neil; Hunter, Jim.

In: Applied Cognitive Psychology, Vol. 24, No. 1, 01.2010, p. 77-89.

Research output: Contribution to journalArticle

@article{7539ddf05b9d46a2bddbdd40eca60200,
title = "When a Graph is Poorer than 100 Words: A Comparison of Computerised Natural Language Generation, Human Generated Descriptions and Graphical Displays in Neonatal Intensive Care",
abstract = "Volunteer staff from a Neonatal Intensive Care Unit (NICU) were presented with sets of anonymised physiological data recorded over approximately 45 minute periods from former patients. Staff were asked to select medical/nursing actions appropriate for each of the patients whose data were displayed. Data were shown in one of three conditions (a) as multiple line graphs similar to those commonly shown on the ward, or as textual descriptions generated by (b) expert medical/nursing staff or (c) computerised natural language generation (NLG). An overall advantage was found for the human generated text, but NLG resulted in decisions that were at least as good as those for the graphical displays with which staff were familiar. It is suggested that NLG might offer a viable automated approach to removing noise and artefacts in real, complex and dynamic data sets, thereby reducing visual complexity and mental workload, and enhancing decision-making particularly for inexperienced staff.",
author = "{van der Meulen}, Marian and Logie, {Robert H.} and Yvonne Freer and Cindy Sykes and Neil McIntosh and Jim Hunter",
year = "2010",
month = "1",
doi = "10.1002/acp.1545",
language = "English",
volume = "24",
pages = "77--89",
journal = "Applied Cognitive Psychology",
issn = "0888-4080",
publisher = "John Wiley and Sons Ltd",
number = "1",

}

TY - JOUR

T1 - When a Graph is Poorer than 100 Words

T2 - A Comparison of Computerised Natural Language Generation, Human Generated Descriptions and Graphical Displays in Neonatal Intensive Care

AU - van der Meulen, Marian

AU - Logie, Robert H.

AU - Freer, Yvonne

AU - Sykes, Cindy

AU - McIntosh, Neil

AU - Hunter, Jim

PY - 2010/1

Y1 - 2010/1

N2 - Volunteer staff from a Neonatal Intensive Care Unit (NICU) were presented with sets of anonymised physiological data recorded over approximately 45 minute periods from former patients. Staff were asked to select medical/nursing actions appropriate for each of the patients whose data were displayed. Data were shown in one of three conditions (a) as multiple line graphs similar to those commonly shown on the ward, or as textual descriptions generated by (b) expert medical/nursing staff or (c) computerised natural language generation (NLG). An overall advantage was found for the human generated text, but NLG resulted in decisions that were at least as good as those for the graphical displays with which staff were familiar. It is suggested that NLG might offer a viable automated approach to removing noise and artefacts in real, complex and dynamic data sets, thereby reducing visual complexity and mental workload, and enhancing decision-making particularly for inexperienced staff.

AB - Volunteer staff from a Neonatal Intensive Care Unit (NICU) were presented with sets of anonymised physiological data recorded over approximately 45 minute periods from former patients. Staff were asked to select medical/nursing actions appropriate for each of the patients whose data were displayed. Data were shown in one of three conditions (a) as multiple line graphs similar to those commonly shown on the ward, or as textual descriptions generated by (b) expert medical/nursing staff or (c) computerised natural language generation (NLG). An overall advantage was found for the human generated text, but NLG resulted in decisions that were at least as good as those for the graphical displays with which staff were familiar. It is suggested that NLG might offer a viable automated approach to removing noise and artefacts in real, complex and dynamic data sets, thereby reducing visual complexity and mental workload, and enhancing decision-making particularly for inexperienced staff.

U2 - 10.1002/acp.1545

DO - 10.1002/acp.1545

M3 - Article

VL - 24

SP - 77

EP - 89

JO - Applied Cognitive Psychology

JF - Applied Cognitive Psychology

SN - 0888-4080

IS - 1

ER -