Literature DB >> 18608144

The effect of context priming and task type on augmentative communication performance.

D Jeffery Higginbotham1, Ann M Bisantz, Michelle Sunm, Kim Adams, Fen Yik.   

Abstract

Augmentative and Alternative Communication (AAC) devices include special purpose electronic devices that generate speech output and are used by individuals to augment or replace vocal communication. Word prediction, including context specific prediction, has been proposed to help overcome barriers to the use of these devices (e.g., slow communication rates and limited access to situation-related vocabulary), but has not been tested in terms of effects during actual task performance. In this study, we compared AAC device use, task performance, and user perceptions across three tasks, in conditions where the AAC device used either was, or was not, primed with task specific vocabularies. The participants in this study were adults with normal physical, cognitive, and communication abilities. Context priming had a marginally significant effect on AAC device use as measured by keystroke savings; however, these advantages did not translate into higher level measures of rate, task performance, or user perceptions. In contrast, there were various statistically significant process and performance differences across task type. Additionally, results for two different emulations of human performance showed significant keystroke savings across context conditions. However, these effects were mitigated in actual performance and did not translate into keystroke savings. This indicates to AAC device designers and users that keystroke-based measures of device use may not be predictive of high level performance.

Entities:  

Mesh:

Year:  2009        PMID: 18608144     DOI: 10.1080/07434610802131869

Source DB:  PubMed          Journal:  Augment Altern Commun        ISSN: 0743-4618            Impact factor:   2.214


  2 in total

1.  Leveraging user's performance in reporting patient safety events by utilizing text prediction in narrative data entry.

Authors:  Yang Gong; Lei Hua; Shen Wang
Journal:  Comput Methods Programs Biomed       Date:  2016-04-08       Impact factor: 5.428

2.  Text prediction on structured data entry in healthcare: a two-group randomized usability study measuring the prediction impact on user performance.

Authors:  L Hua; S Wang; Y Gong
Journal:  Appl Clin Inform       Date:  2014-03-19       Impact factor: 2.342

  2 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.