An early decision algorithm to accelerate web content filtering

Abstract

Real-time content analysis can be a bottleneck in Web filtering. This work presents a simple, but effective early decision algorithm to accelerate the filtering process by examining only part of the Web content. The algorithm can make the filtering decision, either to block or to pass the Web content, as soon as it is confident with a high probability that the content should belong to a banned or an allowable category. The experiments show the algorithms can examine only around one-fourth of the Web content on average, while the accuracy remains fairly good: 89% in the banned content and 93% in the allowable content. This algorithm can complement other Web filtering approaches to filter the Web content with high efficiency.