Judging Visual Correspondence in Web Archives using Similarity Measurements

  • Author(s) / Creator(s)
  • Paper and presentation delivered at the Workshop on Web Archiving and Digital Libraries (WADL) at the Joint Conference on Digital Libraries (JCDL 2019) in Champaign, Illinois. Web archives are becoming increasingly important to our digital infrastructure, as is judging the quality of these archives. With the growing popularity of complex visual styling enabled by Javascript, AJAX, and cascading style sheets (CSS), visual representation of information on the web has become an important part of judging the quality of archived web pages. In the context of web archives, we define visual correspondence as “the similarity in appearance between the original website and the archived website”, as initially defined by Reyes Ayala. This paper examines how the visual correspondence of an archived website can be measured using popular image similarity measures. Using these measures we evaluate how visual correspondence can be used as an indication of overall archive quality. We are interested in answering the following research question: How effective are different similarity measures at measuring the visual correspondence between an archived website and its live counterpart?

  • Date created
  • Subjects / Keywords
  • Type of Item
    Article (Draft / Submitted)
  • DOI
  • License
    Attribution-NonCommercial 4.0 International
  • Language
  • Link to related item