Adaptive cluster-based browsing using incrementally expanded queries and its effects (poster abstract)

Abstract

The accuracy of document clustering depends on the user's viewpoints.We make use of queries as the user's viewpoints to enhance cluster-based browsing for a large amount of search results, reflecting the user's interests. Here the queries are incrementally expanded in the process of cluster-based browsing. We present an application of the proposed method to an IR system on the WWW and evaluate its performance by basic experiments.

Unsupervised document classification using sequential information maximization

“…(3). Additionally since I(T ; Y ) is indeed upper bounded we are guaranteed to converge to a local maximum of the information.…”

“…To estimate these measures we first assign all the documents in some cluster t ∈ T with the most dominant label in that cluster. 3 Given these uni-labeled assignments we can estimate for each category c ∈ C the following quantities: α(c, T ) defines the number of documents correctly assigned to c (i.e., their true label sets include c), β(c, T ) defines the number of documents incorrectly assigned to c and γ(c, T ) defines the number of documents incorrectly not assigned to c. The micro-averaged precision is now defined by…”

Incremental mining of information interest for personalized web scanning

“…Interaction is a common way to disambiguate the user's interest [15,16]. Human-system interactions often helped to refine the queries for the next round of information retrieval [17][18][19]. To conduct such interaction, users need to read and process the retrieved information and then provide relevance feedback to the system.…”

“…Such a feature selection task was routinely conducted for various purposes, including query refinement (e.g. [17][18][19]24] (e.g. [25]), document classification (e.g.…”

An artificial immune system approach to document clustering

“…It has been proposed for use in navigating and browsing document collections [6] or as a tool for Web search engines [8,12]. The Hierarchical Agglomerative Clustering (HAC) and K-means are two commonly used clustering techniques for document clustering [9].…”