Skip to main content

Table 1 Summary of semantic similarity approaches

From: Developing a similarity searching module for patient safety event reporting system using semantic similarity measures

Measures for terms
Approach Techniques Algorithms Pros & Cons
Edge-based Distance; Common path [16, 35,36,37] Pros: intuitive, easy to perform.
Cons: edge-based approaches assume all the nodes
and edges are uniformly distributed and treat them who are in the same depth equally, which is not applicable for real data.
Node-based MICAa; DCAb [18, 28, 38,39,40,41] Pros: node-based approaches measure the terms independent of their depth in the ontology.
Cons: the common used term would make more contribution when calculating the similarity.
Measures for sets of terms
Approach Techniques Algorithms Pros & Cons
Pairwise All pairs [42] Pros: the contributions from every pair of terms are concerned.
Cons: over-reliance on the quality of data; time-consuming
Best Pairs [16, 18, 19, 39, 43]  
Group-wise Set-based Not common Pros: group-wise approaches compare term combinations from a macro view instead of relying on integrating similarity between individual terms; time-saving.
Cons: excessive choices could be a trouble.
Graph-based [15, 44,45,46,47,48,49,50]
Vector-based [51, 52]
  1. aMICA = the most informative common ancestor
  2. bDCA = the disjoint common ancestor