A two-stage decision model for information filtering

Information mismatch and overload are two fundamental issues influencing the effectiveness of information filtering systems. Even though both term-based and pattern-based approaches have been proposed to address the issues, neither of these approaches alone can provide a satisfactory decision for determining the relevant information. This paper presents a novel two-stage decision model for solving the issues. The first stage is a novel rough analysis model to address the overload problem. The second stage is a pattern taxonomy mining model to address the mismatch problem. The experimental results on RCV1 and TREC filtering topics show that the proposed model significantly outperforms the state-of-the-art filtering systems.

► We present a two-stage decision model for information mismatch and overload. ► A rough threshold model for the first stage removes most noisy information. ► Rough threshold + pattern mining is the best choice of two-stage decision making. ► It provides a promising methodology for information filtering systems. ► It improves the performance of text classifications that use only positive feedback.