Spacewalker: Traversing Representation Spaces for Fast Interactive Exploration and Annotation of Unstructured Data

Simple item page
dc.contributor.authorHeine, Lukasen_US
dc.contributor.authorHörst, Fabianen_US
dc.contributor.authorFragemann, Janaen_US
dc.contributor.authorLuijten, Gijsen_US
dc.contributor.authorEgger, Janen_US
dc.contributor.authorBahnsen, Fin Hendriken_US
dc.contributor.authorSarfraz, M. Saquiben_US
dc.contributor.authorKleesiek, Jensen_US
dc.contributor.authorSeibold, Constantinen_US
dc.contributor.editorArchambault, Danielen_US
dc.contributor.editorNabney, Ianen_US
dc.contributor.editorPeltonen, Jaakkoen_US
dc.date.accessioned2025-05-26T07:12:42Z
dc.date.available2025-05-26T07:12:42Z
dc.date.issued2025
dc.description.abstractIn industries such as healthcare, finance, and manufacturing, analysis of unstructured textual data presents significant challenges for analysis and decision making. Uncovering patterns within large-scale corpora and understanding their semantic impact is critical, but depends on domain experts or resource-intensive manual reviews. In response, we introduce Spacewalker, an interactive tool designed to analyze, explore, and annotate data across multiple modalities. It allows users to extract data representations, visualize them in low-dimensional spaces and traverse large datasets either exploratorily or by querying regions of interest. We evaluated Spacewalker through extensive studies, assessing its efficacy in improving data integrity verification and annotation. We show that Spacewalker reduces time and effort compared to traditional methods. The code of this work is publicly available on https://github.com/TIO-IKIM/Spacewalker.en_US
dc.description.sectionheadersPapers
dc.description.seriesinformationMachine Learning Methods in Visualisation for Big Data
dc.identifier.doi10.2312/mlvis.20251155
dc.identifier.isbn978-3-03868-288-2
dc.identifier.pages5 pages
dc.identifier.urihttps://doi.org/10.2312/mlvis.20251155
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/mlvis20251155
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Information systems → Document representation; Human-centered computing → Visualization systems and tools
dc.subjectInformation systems → Document representation
dc.subjectHuman centered computing → Visualization systems and tools
dc.titleSpacewalker: Traversing Representation Spaces for Fast Interactive Exploration and Annotation of Unstructured Dataen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
mlvis20251155.pdf
Size:
2.28 MB
Format:
Adobe Portable Document Format
Download
Collections
Machine Learning Methods in Visualisation for Big Data 2025