Semantic Web in Data Mining and Knowledge Discovery: A Comprehensive Survey

Abstract

a b s t r a c tData Mining and Knowledge Discovery in Databases (KDD) is a research field concerned with deriving higher-level insights from data. The tasks performed in that field are knowledge intensive and can often benefit from using additional knowledge from various sources. Therefore, many approaches have been proposed in this area that combine Semantic Web data with the data mining and knowledge discovery process. This survey article gives a comprehensive overview of those approaches in different stages of the knowledge discovery process. As an example, we show how Linked Open Data can be used at various stages for building content-based recommender systems. The survey shows that, while there are numerous interesting research works performed, the full potential of the Semantic Web and Linked Open Data for data mining and KDD is still to be unlocked.

Biased graph walks for RDF graph embeddings

“…Linking entities in a machine learning task to those in the LOD cloud helps generating additional features, which may help improving the overall learning outcome [37]. For example, when learning a predictive model for the success of a movie, adding knowledge from the LOD cloud (such as the movie's budget, director, genre, etc.)…”

“…Linked Open Data (LOD) [40], and in particular large-scale, crossdomain knowledge graphs such as DBpedia [17], have been recognized as a valuable source of background knowledge in many data mining tasks and knowledge discovery in general [37]. Augmenting a dataset with features taken from knowledge graphs can, in many cases, improve the results of a data mining problem at hand, while externalizing the cost of maintaining that background knowledge [28,37].…”

“…Augmenting a dataset with features taken from knowledge graphs can, in many cases, improve the results of a data mining problem at hand, while externalizing the cost of maintaining that background knowledge [28,37].…”

RDF2Vec: RDF Graph Embeddings for Data Mining

“…Linked Open Data (LOD) [29] has been recognized as a valuable source of background knowledge in many data mining tasks and knowledge discovery in general [25]. Augmenting a dataset with features taken from Linked Open Data can, in many cases, improve the results of a data mining problem at hand, while externalizing the cost of maintaining that background knowledge [18].…”

Editorial: BZN goes electronic-only

“…Still, in the ever more semantic web (e.g., Ristoski & Paulheim, 2016;Waagmeester et al, 2016), scientific names for taxa are underpinning the biological sciences by providing fundamental tags for indexing and interconnecting information (Patterson et al, 2010(Patterson et al, , 2016Pyle, 2016), although the potentially ambiguous relationship between nomenclatural syntax and taxonomy demands comprehensive taxonomic databases for modelling the relationships between names and taxa (Remsen, 2016). Permanency and persistence will remain core issues for nomenclatural data, as they are for science in general, but scientific publishing will continue to evolve along with technological advances as well as with changing needs in our society.…”