Semantic information retrieval research based on co-occurrence analysis

Abstract

Purpose

The paper aims to develop a new method for potential relations retrieval. It aims to find common aspects between co-occurrence analysis and ontology to build a model of semantic information retrieval based on co-occurrence analysis.

Design/methodology/approach

This paper used a literature review, co-occurrence analysis, ontology build and other methods to design a model and process of semantic information retrieval based on co-occurrence analysis. Archaeological data from Wuhan University Library's bibliographic retrieval systems was used for experimental analysis.

Findings

The literature review found that semantic information retrieval research mainly concentrates on ontology-based query techniques, semantic annotation and semantic relation retrieval. Moreover most recent systems can only achieve obvious relations retrieval. Ontology and co-occurrence analysis have strong similarities in theoretical ideas, data types, expressions, and applications.

Research limitations/implications

The experiment data came from a Chinese university which perhaps limits its usefulness elsewhere.

Practical implications

This paper constructed a model to understand potential relations retrieval. An experiment proved the feasibility of co-occurrence analysis used in semantic information retrieval. Compared with traditional retrieval, semantic information retrieval based on co-occurrence analysis is more user-friendly.

Originality/value

This study is one of the first to combine co-occurrence analysis with semantic information retrieval to find detailed relationships.

Citation

Lou, W. and Qiu, J. (2014), "Semantic information retrieval research based on co-occurrence analysis", Online Information Review, Vol. 38 No. 1, pp. 4-23. https://doi.org/10.1108/OIR-11-2012-0203