ABSTRACT
Academic research in information retrieval did not make its way into commercial retrieval products until the last 15 years. Early web search engines also made little use of information retrieval research, in part because of significant differences in the retrieval environment on the Web, such as higher transaction volume and much shorter queries. Recently, however, academic research has taken root in search engines. This paper describes recent developments with a probabilistic retrieval model originating prior to the Web, but with features which could lead to effective retrieval on the Web. Just as graph structure algorithms make use of the graph structure of hyperlinking on the Web, which can be considered a form of relevance judgments, the model of this paper suggests how relevance judgments of web searchers, not just web authors, can be taken into account in ranking. This paper also shows how the combination of expert opinion probabilistic information retrieval model can be made computationally efficient through a new derivation of the mean and standard deviation of the model’s main probability distribution.
