This chapter reports the project MARS (Multiplicative Adaptive Refinement Search), which applies a new multiplicative adaptive algorithm for user preference retrieval to Web searches. The new algorithm uses a multiplicative query expansion strategy to adaptively improve and reformulate the query vector to learn users’ information preference. The algorithm has provable better performance than the popular Rocchio’s similarity-based relevance feedback algorithm in learning a user preference that is determined by a linear classifier with a small number of non-zero coefficients over the real-valued vector space. A meta-search engine based on the aforementioned algorithm is built, and analysis of its search performance is presented.
Collaborative retrieval allows increasing the amount of relevant information found and sharing history with others. The collaborative retrieval can reduce the retrieval time performed by the users of the same profile. This chapter proposes a new relevance feedback algorithm to collaborative information retrieval based on a confidence network, which performs propagation relevance between annotations terms. The main contribution in this work is the extraction of relevant terms to reformulate the initial user query considering the annotations as an information source. The proposed model introduces the concept of necessity that allows determining the terms that have strong association relationships estimated to the measure of a confidence. Since the user is overwhelmed by a variety of contradictory annotations, another contribution consists of determining the relevant annotations for a given evidence source. The experimental study gives very encouraging results.
In this paper, we address the enhancing of Google Scholar engine, in the context of text retrieval, through two mechanisms related to the interrogation protocol of that query expansion and reformulation. The both schemes are applied with re-ranking results using a pseudo relevance feedback algorithm that we have proposed previously in the context of Content based Image Retrieval (CBIR) namely Majority Voting Re-ranking Algorithm (MVRA). The experiments conducted using ten queries reveal very promising results in terms of effectiveness.
Direct kernel biased discriminant analysis: a new content-based image retrieval relevance feedback algorithm
