CoChat

User Variability and IR System Evaluation

Open access
Bailey, Peter, Moffat, Alistair, Scholer, Falk, Thomas, Paul · 2015 · Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval
Cited by 73

The DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.

Abstract

Test collection design eliminates sources of user variability to make statistical comparisons among information retrieval (IR) systems more affordable. Does this choice unnecessarily limit generalizability of the outcomes to real usage scenarios? We explore two aspects of user variability with regard to evaluating the relative performance of IR systems, assessing effectiveness in the context of a subset of topics from three TREC collections, with the embodied information needs categorized against three levels of increasing task complexity. First, we explore the impact of widely differing queries that searchers construct for the same information need description. By executing those queries, we demonstrate that query formulation is critical to query effectiveness. The results also show that the range of scores characterizing effectiveness for a single system arising from these queries is comparable or greater than the range of scores arising from variation among systems using only a single query per topic. Second, our experiments reveal that searchers display substantial individual variation in the numbers of documents and queries they anticipate needing to issue, and there are underlying significant differences in these numbers in line with increasing task complexity levels. Our conclusion is that test collection design would be improved by the use of multiple query variations per topic, and could be further improved by the use of metrics which are sensitive to the expected numbers of useful documents.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1145/2766462.2767728

Cites

3 of 3 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 34

  1. 10.1145/1480506.1480508 · DOI · Paper page
  2. L. W. Anderson and D. A. Krathwohl . A Taxonomy for Learning, Teaching and Assessing: A Revision of Bloom's Taxonomy of Educational Objectives . Longman , New York , 2001 . L. W. Anderson and D. A. Krathwohl. A Taxonomy for Learning, Teaching and Assessing: A Revision of Bloom's Taxonomy of Educational Objectives. Longman, New York, 2001.
  3. 10.1145/2484028.2484049 · DOI
  4. 10.1145/1390334.1390447 · DOI · Paper page
  5. 10.1145/160688.160760 · DOI · Paper page
  6. 10.1016/0306-4573(94)00057-A · DOI · Paper page
  7. D. J. Bell and I. Ruthven . Searchers' assessments of task complexity for web searching . In Proc. ECIR , pages 57 -- 71 , 2004 . D. J. Bell and I. Ruthven. Searchers' assessments of task complexity for web searching. In Proc. ECIR, pages 57--71, 2004.
  8. C. Buckley and J. Walz . The TREC-8 query track . In Proc. TREC , 1999 . NIST Special Publication 500--246. C. Buckley and J. Walz. The TREC-8 query track. In Proc. TREC, 1999. NIST Special Publication 500--246.
  9. 10.1016/0306-4573(94)00041-Z · doi:10.1016/0306-4573(94)00041-z · Paper page
  10. 10.1145/1645953.1646033 · DOI · Paper page
  11. 10.1002/asi.5090190108 · DOI · Paper page
  12. 10.1007/978-3-642-34752-8_5 · doi:10.1007/978-3-642-34752-8_5
  13. 10.1002/meet.14504301167 · DOI · Paper page
  14. 10.1145/2396761.2396779 · DOI
  15. 10.1016/j.ipm.2007.12.006 · DOI
  16. 10.1145/1076034.1076115 · DOI · Paper page
  17. 10.2105/AJPH.2014.302070 · DOI
  18. 10.1007/978-3-642-45068-6_1 · DOI
  19. 10.1145/1416950.1416952 · DOI · Paper page
  20. 10.1145/2505515.2507665 · DOI
  21. 10.1145/2348283.2348402 · doi:10.1145/2348283.2348402
  22. 10.1007/s10791-008-9059-7 · DOI
  23. T. Saracevic . Relevance reconsidered . In Proc. Conf. Conceptions of Library and Inf. Sc. , pages 201 -- 218 , 1996 . T. Saracevic. Relevance reconsidered. In Proc. Conf. Conceptions of Library and Inf. Sc., pages 201--218, 1996.
  24. 10.1145/1935826.1935930 · DOI
  25. 10.1145/2348283.2348300 · DOI · Paper page
  26. K. Sparck Jones and R. Bates . Report on the Design Study for the "Ideal" Information Retrieval Test Collection . British Library Research and Development Report , 5428, 1977 . K. Sparck Jones and R. Bates. Report on the Design Study for the "Ideal" Information Retrieval Test Collection. British Library Research and Development Report, 5428, 1977.
  27. 10.1007/978-3-540-85902-4_31 · DOI
  28. 10.1016/S0306-4573(99)00028-X · DOI · Paper page
  29. 10.1016/S0306-4573(00)00010-8 · DOI · Paper page
  30. 10.1145/1390334.1390456 · DOI
  31. 10.1145/1183614.1183659 · DOI · Paper page
  32. 10.1145/2362724.2362768 · DOI · Paper page
  33. 10.1145/2600428.2609626 · DOI
  34. 10.1145/1183614.1183633 · DOI · Paper page

Cited by

See all 73

Metadata

Authors
Bailey, P., Moffat, A., Scholer, F., & Thomas, P.
Venue
Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval
Publisher
ACM
Published
2015-08-09
Pages
625-634
OpenAlex
W2090035194
Cited by
73
References
3
FWCI
10.52
Type
conference paper
Language
en
Open access
green
Funders
Australian Research Council (DP110101934, DP140102655)

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.