Metrics and Testbed Working Group

Goals & objectives

This Working Group is organized to define metrics for Web archiving and define and characterize an evaluation process for the coverage and performance of Web archiving tools and processes. The main tasks will be to identify a testbed to use for evaluating Web crawlers and to define the set of metrics for use in that evaluation. This set of metrics may evolve during the testing process.

The Working Group has developed an inventory and a taxonomy to address the methodological characteristics and issues of collecting, rendering, and preserving data from the Web . The Working Group is surveying each aspect and designing a working document that will serve as a guide to develop a common understanding of these issues. The metrics derived from this work will formalize the development of a test bed that will assist in measuring the quality and performance of tools and processes.

Expected deliverables

• Testbed taxonomies for each issue: collection, rendering, and preserving data
• Test cases/data sets
• Metrics

Leaders

Martha Anderson and Gina Jones, The Library of Congress, USA

Others: Framework / Researchers Requirements / Access Tools / Metrics and Testbed / Deep Web / Content Management