A compound correlation model for disjoint literature‐based knowledge discovery

Purpose – The algorithm of disjoint literature‐based knowledge discovery provides a convenient, efficient and effective auxiliary method for scientific research. Based on an analysis of Swanson's A‐B‐C model of disjoint literature‐based knowledge discovery and Gordon's intermediate literature theory, this paper seeks to propose a more comprehensive compound correlation model for disjoint literature‐based knowledge discovery. Design/methodology/approach – A new algorithm of vector space model (VSM) based disjoint literature‐based knowledge discovery is designed to implement the compound correlation model. Findings – The validity tests showed that this new model not only simulated both of Swanson's early and well‐known discoveries of Raynaud's disease‐fish oil and migraine‐magnesium connections successfully, but also applied to knowledge discovery in the agricultural economics literature in the Chinese language. Research limitations/implications – Although the workload was reduced to the minimum under the compound correlation model compared with other algorithms and models, part of the work needed some manual intervention in the process of disjoint literature‐based knowledge discovery with the VSM‐based compound correlation model. Practical implications – The algorithm was capable of knowledge discovery with a large‐scale dataset and had an advantage in identifying a series of hidden connections among a set of literatures. Therefore, application of the model might be extended to more fields. Originality/value – Traditional two‐step knowledge discovery procedures were integrated into the model, which contained open and closed disjoint literature‐based knowledge discovery.