Multi-Dimension Topic Mining Based on Hierarchical Semantic Graph Model

Abstract

Topic mining of scientific literature can accurately capture the contextual structure of a topic, track research hotspots within a field, and improve the availability of information about the literature. This paper introduces a multi-dimensional topic mining method based on a hierarchical semantic graph model. The main innovations include (1) the hierarchical extraction of feature terms and construction of a corresponding semantic graph and (2) multi-dimensional topic mining based on graph segmentation and structure analysis. The process of semantic graph construction is based primarily on hierarchical feature term extraction, which can effectively reveal the hierarchical structural distribution of feature terms within documents. Our graph model also takes into account the complementarity of content-and context-related feature terms in documents while avoiding the loss of textual information. In addition, the multi-dimensional features of the topic can be mined effectively via an in-depth analysis of the constructed graph, resulting in a quantitative visualization of the many-to-many association between the topic and feature terms. A variety of experiments on existing document datasets demonstrate that the proposed approach is able to outperform state-of-the-art methods in terms of accuracy and efficacy. INDEX TERMS Topic mining, multi-dimensional topic, hierarchical semantic graph.

News topic detection based on capsule semantic graph

“…Sayyadi and Raschid [15] constructed a graph of the co-occurrence relationship of words in the entire document corpus, conducted community detection to divide the graph into several parts, and performed topic detection by assigning documents to each community. Zhang et al [16] proposed a multidimensional topic extraction method on the basis of a hierarchical semantic graph model, conducted the hierarchical extraction of feature words to construct a semantic graph, and performed segmentation and structural analysis of the semantic graph to extract topics. Hamm et al [17] used posIdfRank to sort words to extract keywords and constructed a keyword map to discover topics.…”

“…Hierarchical semantic graph model (HGM): HGM is a topic mining method based on hierarchical semantic graph model proposed by Zhang et al [16] The construction of a semantic graph is mainly based on hierarchical feature word extraction. WebKey: Rasouli et al [30] constructed a word cooccurrence graph by identifying words that suddenly appear in news documents.…”

Term-Community-Based Topic Detection with Variable Resolution

“…[43] identify topics as cliques in a word co-occurrence network. The hierarchical semantic graph model in [44] is based on a hierarchy of terms and uses subgraph segmentation via the normalized cut algorithm [45] for community detection. Gerlach et.…”

Term-community-based topic detection with variable resolution

“…[43] identifies topics as cliques in a word cooccurence network. The hierarchical semantic graph model in [44] is based on a hierarchy of terms and uses subgraph segmentation via the normalized cut algorithm [45] for community detection. [46] finds topics as communities in a bipartite document-word graph with a Stochastic Block Model [47].…”