Clustering algorithm in literature-based discovery

Literature-based discovery is linking two or more literature concepts that have heretofore not been linked (i.e., disjoint), in order to produce novel, interesting, plausible, and intelligible knowledge. Cluster analysis is the core of literature-based discovery. This paper proposes an improved fuzzy c means (FCM) algorithm based on the analysis of existing clustering analysis of literature-based discovery. The new FCM algorithm mainly focus on the fuzzy degree of membership and make the FCM algorithm achieve better clustering results in despite of the existence of isolated points or low-frequency terms. And because of the relaxation of the normalization condition, the final clustering result is not very sensitive to the number of the pre-determined clusters. The new FCM algorithm takes the low-frequency terms into full account, and reduces the impaction of the pre-determined number of clusters on the final clustering.