SIGIR 2017 Test of Time Award

The SIGIR Test of Time Award recognizes research that has had long-lasting influence, including impact on a subarea of information retrieval research, across subareas of information retrieval research, and outside of the information retrieval research community (e.g. non-information retrieval research or industry). The winning paper is selected from the set of full papers presented at the main SIGIR conference 10-12 years before. The SIGIR 2017 award will be selected from the set of full papers presented at SIGIR 2005, 2006, and 2007. A detailed description of the 2014 selection process can be found in the December 2014 SIGIR Forum. Previous years’ awards can be found on the SIGIR Test of Time page.

The Test of Time Award winner will be announced at SIGIR 2017. The award consists of,

  • reprinting the paper in the December SIGIR Forum with a short preface written by the committee,
  • a plaque, and
  • documentation on the SIGIR website.

In addition to the Test of Time Award winner, the committee will select up to three honorable mentions presented at SIGIR 2004.

The award is selected by a committee composed of past Program Committee chairs as well as a Test of Time Award chair selected by the Executive Committee. This year’s committee will be announced in the coming weeks.

The committee will select a subset of the candidates to evaluate for the award. Of the qualifying papers, the top 5 papers from the SIGIR main conference ranked by citation according to the ACM Digital Library will automatically be nominated for consideration.* This year’s automatically nominated papers are listed below. In addition, we encourage nominations from the community of papers not automatically selected. Nominations should include,

  1. citation of nominated paper,
  2. a short paragraph justifying consideration, and
  3. names of at least three members of the community who endorse the nomination.

None of the endorsers may have a conflict of interest with the paper. A definition of what constitutes a conflict can be found below.

Nominations are due by January 31, 2017 (anywhere in the world).

Please submit nominations using this form.

Automatically-Nominated Publications

SIGIR 2005

  • A Markov random field model for term dependencies
    Donald Metzler, W. Bruce Croft
  • Personalizing search via automated analysis of interests and activities
    Jaime Teevan, Susan T. Dumais, Eric Horvitz
  • Information retrieval system evaluation: effort, sensitivity, and reliability
    Mark Sanderson, Justin Zobel
  • Context-sensitive information retrieval using implicit feedback
    Xuehua Shen, Bin Tan, ChengXiang Zhai
  • Scalable collaborative filtering using cluster-based smoothing
    Gui-Rong Xue, Chenxi Lin, Qiang Yang, WenSi Xi, Hua-Jun Zeng, Yong Yu, Zheng Chen

SIGIR 2006

  • Improving web search ranking by incorporating user behavior information
    Eugene Agichtein, Eric Brill, Susan Dumais
  • LDA-based document models for ad-hoc retrieval
    Xing Wei, W. Bruce Croft
  • Formal models for expert finding in enterprise corpora
    Krisztian Balog, Leif Azzopardi, Maarten de Rijke
  • Learning user interaction models for predicting web search result preferences
    Eugene Agichtein, Eric Brill, Susan Dumais, Robert Ragno
  • Less is more: probabilistic models for retrieving fewer relevant documents
    Harr Chen, David R. Karger

SIGIR 2007

  • Towards automatic extraction of event and place semantics from flickr tags
    Tye Rattenbury, Nathaniel Good, Mor Naaman
  • AdaRank: a boosting algorithm for information retrieval
    Jun Xu, Hang Li
  • Random walks on the click graph
    Nick Craswell, Martin Szummer
  • A support vector method for optimizing average precision
    Yisong Yue, Thomas Finley, Filip Radlinski, Thorsten Joachims
  • A semantic approach to contextual advertising
    Andrei Broder, Marcus Fontoura, Vanja Josifovski, Lance Riedel

Conflicts of Interest

An individual is in conflict with a paper if,

  1. the individual is a co-author of the nominated paper,
  2. the individual was at the same institution as a co-author of the nominated paper when the paper was published,
  3. the individual is at the same institution as a co-author of the nominated paper currently,
  4. the individual is at the same institution as a co-author of the nominated paper when the paper was published, or
  5. the individual is a relative of a co-author of the nominated paper.


Selection in progress.

*measured on November 23, 2016. Previous Test of Time Award winners removed