EuroVisPosters2018

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/2632399

Browse

Browsing EuroVisPosters2018 by Subject "Information systems"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Extending Document Exploration with Image Retrieval: Concept and First Results
    (The Eurographics Association, 2018) Shao, Lin; Glatz, Mathias; Gergely, Eric; Müller, Markus; Munter, Denis; Papst, Stefan; Schreck, Tobias; Anna Puig and Renata Raidou
    Information retrieval provides to date effective methods to search for documents relevant to user queries, and to support exploration of clusters of similar documents. Typically, the retrieval relies on text-based queries and similarity functions. However, in many cases also visual content is important in documents, for example, in the visualization field. There, researchers may want to search for papers based on similar example visualizations, which is difficult by relying on keyword search alone. We present a concept to automatically label visualization types in research papers and search for similar images, relying on state of the art image descriptors. We created a prototype that allows to search for papers showing images similar to a query image. Preliminary results of applying it on a corpus of VAST papers indicate the chosen descriptors can retrieve papers with similar images. Our approach for image-based search can complement text-based search and in perspective, support document corpus exploration based on clustering contained images. In future work, we want to explore if image-based search can also support the formation of taxonomies of a corpus or research papers, based on image similarity.
  • Thumbnail Image
    Item
    Visual Analysis of Sentiment and Stance in Social Media Texts
    (The Eurographics Association, 2018) Kucher, Kostiantyn; Paradis, Carita; Kerren, Andreas; Anna Puig and Renata Raidou
    Despite the growing interest for visualization of sentiments and emotions in textual data, the task of detecting and visualizing various stances is not addressed well by the existing approaches. The challenges associated with this task include development of the underlying computational methods and visualization of the corresponding multi-label stance classification results. In this poster abstract, we describe the ongoing work on a visual analytics platform, called StanceVis Prime, which is designed for analysis of sentiment and stance in temporal text data from various social media data sources. Our approach consumes documents from several text stream sources, applies sentiment and stance classification, and provides end users with both an overview of the resulting data series and a detailed view for close reading and examination of the classifiers' output. The intended use case scenarios for StanceVis Prime include social media monitoring and research in sociolinguistics.
  • Thumbnail Image
    Item
    Visually Exploring Data Provenance and Quality of Open Data
    (The Eurographics Association, 2018) Bors, Christian; Gschwandtner, Theresia; Miksch, Silvia; Anna Puig and Renata Raidou
    While open data platforms are increasingly popular among end-users as well as data providers, there is a growing problem with inconsistent update frequencies and lack of quality in datasets. Efforts to monitor data quality are currently limited to checking meta-information and creating revisions to allow manual inspection of former datasets.We employ a Visual Analytics framework for generating and visualizing data provenance from data quality to facilitate data analysis and help users to understand the impact of updates on the data. Data quality metrics are utilized to quantify the development of data quality over time for open data projects. We combine quality metrics, data provenance, and data transformation information in an interactive exploration environment to expedite assessment and selection of appropriate open datasets.