Generating Estimates of Classification Confidence for a Case-Based Spam Filter
Generating Estimates of Classification Confidence for a Case-Based Spam Filter
复制标题
生成基于案例的垃圾邮件过滤器的分类置信度估计
DOI：
10.1007/11536406_16
复制
发表时间：
2005
期刊：
影响因子：
--
通讯作者：
Anton Zamolotskikh
中科院分区：
文献类型：
--
作者：
Sarah Jane Delany;P. Cunningham;Dónal Doyle;Anton Zamolotskikh
对分类置信度进行估计是非常困难的。人们可能会期望能够产生数字分类分数的分类器（例如k近邻，朴素贝叶斯或支持向量机）可以很容易地产生基于阈值的置信度估计。事实上，事实证明并非如此，可能是因为这些不是严格意义上的概率分类器。来自k近邻、朴素贝叶斯和支持向量机分类器的数字分数与分类置信度没有很好的相关性。在本文中，我们描述了一个基于案例的垃圾邮件过滤应用程序，该应用程序将显著受益于将置信度预测附加到积极分类（即分类为垃圾邮件的消息）的能力。我们表明，基于案例的分类器的“明显”置信度指标是无效的。我们提出了一个类似集成的解决方案，该解决方案聚合了一系列置信度指标，并表明这在垃圾邮件过滤领域提供了一个有效的解决方案。
Producing estimates of classification confidence is surprisingly difficult. One might expect that classifiers that can produce numeric classification scores (e.g. k-Nearest Neighbour, Naive Bayes or Support Vector Machines) could readily produce confidence estimates based on thresholds. In fact, this proves not to be the case, probably because these are not probabilistic classifiers in the strict sense. The numeric scores coming from k-Nearest Neighbour, Naive Bayes and Support Vector Machine classifiers are not well correlated with classification confidence. In this paper we describe a case-based spam filtering application that would benefit significantly from an ability to attach confidence predictions to positive classifications (i.e. messages classified as spam). We show that ‘obvious' confidence metrics for a case-based classifier are not effective. We propose an ensemble-like solution that aggregates a collection of confidence metrics and show that this offers an effective solution in this spam filtering domain.
基于案例的推理研究与开发
DOI：
10.1007/978-3-642-39056-2_11
发表时间：
2013
期刊：
--
影响因子：
--
作者：
Horsburgh B
通讯作者：
Horsburgh B