iSearch is an information retrieval (IR) test collection to facilitate the evaluation of integrated search, i.e. search across a range of different sources but with one search box and one ranked result list, and describes and analyses a new test collection constructed for this purpose. The test collection consists of approx. 18,000 monographic records, 160,000 papers and journal articles in PDF and 275,000 abstracts with a varied set of metadata and vocabularies from the physics domain, 65 topics based on real work tasks and corresponding graded relevance assessments. The test collection may be used for systems as well as user-oriented evaluation.

The data set was crawled from the arXiv and from the Danish National Library. The collection also contains approx. 3.5 million citations to complement the document data.

For further details please refer to the following publication:

Lykke, M., Larsen, B., Lund, H. & Ingwersen, P. (2010). Developing a test collection for the evaluation of integrated search. ECIR, p. 627-630. [PDF]

• archives The original files from the distributor

  • iSearch-direct-citations.tgz Direct citations within the dataset

  • iSearchIDs.tgz Mapping of internal IDs and arXiv IDs / URLs

  • iSearch-references.tgz Extracted reference information

  • iSearch-v1.0_documents-PF-pdf.tgz PDF fulltext for a subset of the documents

  • iSearch-v1.0_documents.tgz Document metadata

  • iSearch-v1.0_topics+assessments.tgz Topics and relevance assessments

• scripts Sample scripts to work with the data