Early precision measures: implications from the downside of blind feedback

Authors:
Stephen Tomlinson
Affiliations:
Hummingbird, Ottawa, Canada
Venue:
SIGIR '06 Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval
Year:
2006

Citing 1
Cited 3

The NRRC reliable information access (RIA) workshop

Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrieval

Portfolio theory of information retrieval

Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval
On statistical analysis and optimization of information retrieval effectiveness metrics

Proceedings of the 33rd international ACM SIGIR conference on Research and development in information retrieval
Comparing the robustness of expansion techniques and retrieval measures

CLEF'06 Proceedings of the 7th international conference on Cross-Language Evaluation Forum: evaluation of multilingual and multi-modal information retrieval

Quantified Score

Hi-index	0.00

Visualization

Abstract

We report the statistically significant mean impacts of blind feedback, as implemented by 7 participants for the 2003 Reliable Information Access (RIA) Workshop, on 30 retrieval measures, including several primary recall measures not originally reported. We find that blind feedback was detrimental to measures focused on the first relevant item even when it boosted "early precision" measures such as mean Precision@10, implying that the conventional reporting of ad hoc precision needs enhancement.