A modern semantic similarity method using multiple resources for enhancing influenza detection

With the widespread of the data resources over the World Wide Web (WWW), there is an overlapping between these resources that contributes to helping researchers in discovering more information and facts. However, extracting information and data and then, calculating the semantic similarity between them is a non-trivial task as such resources have varying ways to describe the information. Thus, such a problem can be overcome by designing a new semantic similarity method which takes into account different factors and not exclusive on the syntactical description of the data. The paper describes a new semantic similarity method which exploits different factors to calculate the semantic similarity between different resources. The factors are the description of the node and the surrounded relations (i.e. ascending and descending) from multiple ontologies. This will contribute to calculating semantic similarity based on many perspectives and will help to strengthen the similarity relations between different resources to discover new semantic similarities between influenza symptoms. This may lead to control the expansion of the influenza outbreak. The method has been applied over a set of influenza ontologies to find new cases of similarity that may not be explicit in the original resources. An off-line evaluation method has been also conducted on a set of ontologies and compared with the baseline and specialist methods where it exceeded both methods and satisfied more accurate similarity scores.

Automated summary

With the widespread of data resources on the internet, overlapping between these resources can provide researchers with more information. Extracting and calculating the semantic similarity between these resources is a challenging task due to their varying descriptions. To address this issue, the paper presents a new semantic similarity method that considers different factors to calculate the semantic similarity between different resources. By utilizing node descriptions and relations from multiple ontologies, this method strengthens the similarity relations between resources and discovers new semantic similarities.