Lavalle, Ana, Maté, Alejandro, Trujillo, Juan, Teruel, Miguel A., Rizzi, Stefano
A methodology to automatically translate user requirements into visualizations: Experimental validation
Information and Software Technology. 2021, 136: 106592. https://doi.org/10.1016/j.infsof.2021.106592
URI: http://hdl.handle.net/10045/114167
DOI: 10.1016/j.infsof.2021.106592
ISSN: 0950-5849 (Print)
Abstract: 
Context: Information visualization is paramount for the analysis of Big Data. The volume of data requiring interpretation is continuously growing. However, users are usually not experts in information visualization. Thus, defining the visualization that best suits a determined context is a very challenging task for them. Moreover, it is often the case that users do not have a clear idea of what objectives they are building the visualizations for. Consequently, it is possible that graphics are misinterpreted, making wrong decisions that lead to missed opportunities. One of the underlying problems in this process is the lack of methodologies and tools that non-expert users in visualizations can use to define their objectives and visualizations. Objective: The main objectives of this paper are to (i) enable non-expert users in data visualization to communicate their analytical needs with little effort, (ii) generate the visualizations that best fit their requirements, and (iii) evaluate the impact of our proposal with reference to a case study, describing an experiment with 97 non-expert users in data visualization. Methods: We propose a methodology that collects user requirements and semi-automatically creates suitable visualizations. Our proposal covers the whole process, from the definition of requirements to the implementation of visualizations. The methodology has been tested with several groups to measure its effectiveness and perceived usefulness. Results: The experiments increase our confidence about the utility of our methodology. It significantly improves over the case when users face the same problem manually. Specifically: (i) users are allowed to cover more analytical questions, (ii) the visualizations produced are more effective, and (iii) the overall satisfaction of the users is larger. Conclusion: By following our proposal, non-expert users will be able to more effectively express their analytical needs and obtain the set of visualizations that best suits their goals.
Keywords:Data visualization, Big data analytics, Model-driven development, Requirements engineering, Experimental validation
Elsevier
info:eu-repo/semantics/article