Bitte benutzen Sie diese Kennung, um auf die Ressource zu verweisen: http://dx.doi.org/10.18419/opus-13686
Autor(en): Guo, Yi
Cao, Nan
Cai, Ligan
Wu, Yanqiu
Weiskopf, Daniel
Shi, Danqing
Chen, Qing
Titel: Datamator : an authoring tool for creating datamations via data query decomposition
Erscheinungsdatum: 2023
Dokumentart: Zeitschriftenartikel
Seiten: 18
Erschienen in: Applied sciences 13 (2023), No. 9709
URI: http://nbn-resolving.de/urn:nbn:de:bsz:93-opus-ds-137052
http://elib.uni-stuttgart.de/handle/11682/13705
http://dx.doi.org/10.18419/opus-13686
ISSN: 2076-3417
Zusammenfassung: Datamation is designed to animate an analysis pipeline step by step, serving as an intuitive and efficient method for interpreting data analysis outcomes and facilitating easy sharing with others. However, the creation of a datamation is a difficult task that demands expertise in diverse skills. To simplify this task, we introduce Datamator, a language-oriented authoring tool developed to support datamation generation. In this system, we develop a data query analyzer that enables users to generate an initial datamation effortlessly by inputting a data question in natural language. Then, the datamation is displayed in an interactive editor that affords users the ability to both edit the analysis progression and delve into the specifics of each step undertaken. Notably, the Datamator incorporates a novel calibration network that is able to optimize the outputs of the query decomposition network using a small amount of user feedback. To demonstrate the effectiveness of Datamator, we conduct a series of evaluations including performance validation, a controlled user study, and expert interviews.
Enthalten in den Sammlungen:13 Zentrale Universitätseinrichtungen

Dateien zu dieser Ressource:
Datei Beschreibung GrößeFormat 
applsci-13-09709.pdfArtikel9,94 MBAdobe PDFÖffnen/Anzeigen
applsci-13-09709-s001.zipSupplement50,7 MBUnknownÖffnen/Anzeigen


Diese Ressource wurde unter folgender Copyright-Bestimmung veröffentlicht: Lizenz von Creative Commons Creative Commons