An Efficient Clustering Sentence-Level Text Using A Novel Hierarchical Fuzzy Relational Clustering Algorithm

Abstract: In comparison with hard and soft clustering methods, in which a pattern belongs to a single cluster, fuzzy clustering algorithms allow patterns to belong to all clusters with differing degrees of membership. In Existing a novel fuzzy clustering algorithm that operates on relational input data; i.e., data in the form of a square matrix of pair-wise similarities between data objects. However, the major disadvantage of the Fuzzy Relational Eigenvector Centrality- based Clustering Algorithm (FRECCA) is its time complexity. The FRECCA lies in its ability to identify fuzzy clusters, and if the objective is to perform only hard clustering. This paper presents a novel hierarchical fuzzy relational clustering algorithm that operates on relational input data; i.e., data in the form of a square matrix of pair-wise similarities between data objects. The algorithm uses a graph representation of the data, and operates in a Fuzzification Degree framework in which the graph centrality of an object in the graph is interpreted as likelihood. Results of applying the algorithm to sentence clustering tasks demonstrate that the algorithm is capable of identifying overlapping clusters of semantically related sentences, and that it is therefore of potential use in a variety of text mining tasks. We also include results of applying the algorithm to benchmark data sets in several other domains.

Keywords: Hierarchical fuzzy relational clustering, Fuzzification Degree, Hard Clustering, Soft Clustering.