Relevance Feedback

Relevance Feedback is an interactive query reformulation technique in information retrieval that uses explicit or implicit assessments of the relevance of initially retrieved documents to modify the query representation—typically by reweighting and/or expanding its terms—in order to improve the ranking of subsequent retrieval results.

2.5K

Publications

172.5K

Citations

4.6K

Authors

1.1K

Institutions

Publications per year

2017–2026

396

Authors

4.6K

  1. WB
    W. Bruce Croft

    University of Massachusetts Amherst, United States

    37 publications · 4.8K citations

    25

    h-index

  2. CZ
    ChengXiang Zhai

    University of Illinois Urbana-Champaign, United States

    31 publications · 2.2K citations

    22

    h-index

  3. SR
    Stephen Robertson

    Microsoft Research (United Kingdom), United Kingdom

    28 publications · 5.4K citations

    21

    h-index

  4. JA
    James Allan

    University of Massachusetts Amherst, United States

    24 publications · 1.5K citations

    20

    h-index

  5. SM
    Shaoping Ma

    Tsinghua University, China

    23 publications · 1K citations

    20

    h-index

1–5 of 4.6K

Venues

  1. Information Processing & Management

    86 publications · 5.1K citations

    39

    h-index

  2. ACM Transactions on Information Systems

    43 publications · 9.8K citations

    31

    h-index

  3. Journal of the American Society for Information Science

    JASIS · 34 publications · 3.8K citations

    24

    h-index

  4. 22

    h-index

  5. ACM SIGIR Forum

    35 publications · 4.5K citations

    21

    h-index

1–5