The increased demand of systems able to generate reports in natural language from numerical data involves the search for new solutions. This paper presents an adaptation of standard natural language generation methodologies to generate customized linguistic descriptions of data. Namely, we merge one of the most well-known architectures in the natural language generation research field together with our previous architecture for generating linguistic descriptions of complex phenomena. The latter is supported by the computational theory of perceptions which comes from the fuzzy sets and systems research field. We include a practical case of use dealing with the problem of inefficient consumption of energy at households. It generates natural language recommendations adapted to each household to promote a more responsible consumption. The proposal reveals opportunities of collaboration between the different research communities that are involved. Communicated by C. M. Vide, A. H. Dediu.
Purpose
– The purpose of this paper is to improve and facilitate the work of developers and usability evaluators by providing an adaptable and effective support. A well-defined set of criteria and a range of evaluation values for each criterion as well as a complete websites classification, will guide evaluators. A usability percentage and a list of prioritized criteria, adapted to the type of website by a new usability metric, will help developers to improve the website. This improvement will increase the degree of web user satisfaction.
Design/methodology/approach
– Having established and validated a new usability evaluation framework, several usability tools have been analyzed. None of them totally fulfills the requirements of the evaluation framework. As a result of being unable to customize any of them, a new one has been developed. A study of 42 enterprise websites in an economically depressed region of Europe was performed using the new tool. This study involved 42 evaluators and 118 web users. Users have evaluated the websites before and after the redesign. A end-user computing satisfaction model-based questionary was used to collect data about end-user satisfaction. The results validate the proposal.
Findings
– The study confirms that the proposed tool provides valuable information during the process of web development, evaluation and redesign. In adittion, it reveals that improving websites usability by ensuring criteria compliance has a positive effect on web users satisfaction.
Originality/value
– Unlike previous purposes, the proposed tool allows to evaluate any type of website with a well-defined set of evaluation criteria and specific criteria values. As outcomes, the tool provides the website usability degree and a list of criteria ordered by priority repair. These results are adapted to the specific type of website. This makes easier and more effective the redesign of the evaluated website.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.