Sequential and Unsupervised Document Authorial Clustering Based on Hidden Markov Model

Abstract

Document clustering groups documents of certain similar characteristics in one cluster. Document clustering has shown advantages on organization, retrieval, navigation and summarization of a huge amount of text documents on Internet. This paper presents a novel, unsupervised approach for clustering single-author documents into groups based on authorship. The key novelty is that we propose to extract contextual correlations to depict the writing style hidden among sentences of each document for clustering the documents. For this purpose, we build an Hidden Markov Model (HMM) for representing the relations of sequential sentences, and a two-level, unsupervised framework is constructed. Our proposed approach is evaluated on four benchmark datasets, widely used for document authorship analysis. A scientific paper is also used to demonstrate the performance of the approach on clustering short segments of a text into authorial components. Experimental results show that the proposed approach outperforms the state-of-the-art approaches.

A Framework for Authorial Clustering of Shorter Texts in Latent Semantic Spaces

“…García-Mondeja et al used a Bag-of-Words language model with binary features, because the documents were too short to use frequencies, and then applied a β-compact algorithm that placed documents in the same cluster if they were maximally similar and more proximal than the threshold β [9]. Aldebei et al proposed a two-level HMM to model relations of sequential sentences in order to cluster single-author documents by authorship [2]. While the approach was for long documents, they also tested it on smaller segments of texts as well [2].…”

“…Aldebei et al proposed a two-level HMM to model relations of sequential sentences in order to cluster single-author documents by authorship [2]. While the approach was for long documents, they also tested it on smaller segments of texts as well [2]. Gómez-Adorno et al used a hierarchical agglomerative clustering algorithm with average linkage and cosine similarity, and with the Calinski-Harabasz optimization criterion to determine the cut-off layer of the dendrogram [10].…”