The Relationship between Recall and Precision

@article{Buckland1994TheRB,
  title={The Relationship between Recall and Precision},
  author={Michael K. Buckland and Fredric C. Gey},
  journal={J. Am. Soc. Inf. Sci.},
  year={1994},
  volume={45},
  pages={12-19}
}
Empirical studies of retrieval performance have shown a tendency for Precision to decline as Recall increases. This article examines the nature of the relationship between Precision and Recall. The relationships between Recall and the number of documents retrieved, between Precision and the number of documents retrieved, and between Precision and Recall are described in the context of different assumptions about retrieval performance. It is demonstrated that a tradeoff between Recall and… 

Figures and Tables from this paper

An exact analytical relation among recall , precision , and classification accuracy in information retrieval
TLDR
The present paper presents for the first time a general mathematical relation linking classification accuracy with precision and recall, and shows that this relation implies a trade-off between recall and precision under certain conditions on the accuracy.
A Geometric View of Relevance Effectiveness in Information Retrieval
TLDR
It is shown that the empirical relation P=NR/x (P=precision, R=recall, N=total number of relevant documents, x=the number of retrieved documents) can be formally easily obtained and the name of effectiveness surface is suggested for it.
The tipping point: F-score as a function of the number of retrieved items
Statistical inference on recall, precision and average precision under random selection
  • P. Zhang, Wanhua Su
  • Computer Science
    2012 9th International Conference on Fuzzy Systems and Knowledge Discovery
  • 2012
TLDR
A framework for conducting statistical inference on recall, precision and average precision through establishing their asymptotic properties is developed and can be applied in other areas where ranking systems need to be evaluated, such as information retrieval.
No zero match browsing of hierarchically categorized information entities
TLDR
A user interface based approach to the browsing of hierarchically organized information entities that avoids these problems by allowing the incremental narrowing down of a set of search results and by pruning the organizational structure after each user selection to show the consequences of the selection.
Simultaneous exploitation of explicit and implicit tags in affect-based multimedia retrieval
  • Joep J. M. Kierkels, T. Pun
  • Computer Science
    2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops
  • 2009
TLDR
The novelty of this paper is to show that affect-based retrieval accuracy (as measured by precision and recall) benefits from having a database that contains both explicit and implicit tags.
Search Result Reranking Using Clustering
TLDR
The goal of this project is to find out if it is possible to use statistical methods in Biomedical Information Retrieval and improve retrieval performance, i.e. finding ways of fulfilling user information needs, in the biomedical domain using clustering with knowledge from the BioTracer project.
Quality of search engines: how good is Google pagerank?
TLDR
It is concluded that PageRank is not a useful indicator of the relevance of results in Traditional Chinese search engines and Google needs to enhance its PageRank algorithm.
On the Construction of Selection Systems.
TLDR
The authors argue that all selection systems can be represented in terms of combinations of these components, which are of only two types: representations of data objects and functions that operate on them.
A survey on the use of relevance feedback for information access systems
TLDR
This paper surveys relevance feedback techniques and studies both automatic techniques, in which the system modifies the user's query, and interactive techniques, which the user has control over query modification.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 13 REFERENCES
Recall-precision trade-off: A derivation
TLDR
This article sees that the recall-precision trade-off hinges on a deceleration in the proportion of relevant documents which are retrieved, successively, over time, and concludes that the equation that best models recall as a function of time is the logarithm of a quadratic function.
Explicit and implicit variables in information retrieval (IR) systems
TLDR
The possibility is suggested that all variables affecting the performance of retrieval systems can be decomposed into M‐factors, and the implications of these ideas for laboratory tests on retrieval systems are discussed.
On the Inverse Relationship of Recall and Precision.
It is now ten years since some slight experimental evidence was presented which appeared to support the hypothesis that there was an inverse relationship between recall and precision. The idea of
THE ANOMALOUS BEHAVIOUR OF PRECISION IN THE SWETS MODEL, AND ITS RESOLUTION
TLDR
This paper extends Heine's result to the case where the criterion‐parameter can assume discrete as well as continuous values and shows that for that model, Recall and Precision are in fact inversely related.
OASIS: a front-end for prototyping catalog enhancements
TLDR
It is believed that the next generation of online catalogs should and will have features such as those discussed and illustrated in this article.
Special issue: Evaluation issues in information retrieval
  • Information Processing and Management,
  • 1992
Retrieval techniques
Information Retrieval at the Sedgwick Museum
  • Information Technology: Research and Development,
  • 1983
...
1
2
...