%0 Journal Article %1 10.1145/3345551 %A Mountantonakis, Michalis %A Tzitzikas, Yannis %C New York, NY, USA %D 2019 %I Association for Computing Machinery %J ACM Comput. Surv. %K integration linkedData metadata semanticWeb %N 5 %R 10.1145/3345551 %T Large-scale Semantic Integration of Linked Data: A Survey %U https://doi.org/10.1145/3345551 %V 52 %X A large number of published datasets (or sources) that follow Linked Data principles is currently available and this number grows rapidly. However, the major target of Linked Data, i.e., linking and integration, is not easy to achieve. In general, information integration is difficult, because (a) datasets are produced, kept, or managed by different organizations using different models, schemas, or formats, (b) the same real-world entities or relationships are referred with different URIs or names and in different natural languages,<?brk?>(c) datasets usually contain complementary information, (d) datasets can contain data that are erroneous, out-of-date, or conflicting, (e) datasets even about the same domain may follow different conceptualizations of the domain, (f) everything can change (e.g., schemas, data) as time passes. This article surveys the work that has been done in the area of Linked Data integration, it identifies the main actors and use cases, it analyzes and factorizes the integration process according to various dimensions, and it discusses the methods that are used in each step. Emphasis is given on methods that can be used for integrating several datasets. Based on this analysis, the article concludes with directions that are worth further research.

@article{10.1145/3345551, abstract = {A large number of published datasets (or sources) that follow Linked Data principles is currently available and this number grows rapidly. However, the major target of Linked Data, i.e., linking and integration, is not easy to achieve. In general, information integration is difficult, because (a) datasets are produced, kept, or managed by different organizations using different models, schemas, or formats, (b) the same real-world entities or relationships are referred with different URIs or names and in different natural languages,<?brk?>(c) datasets usually contain complementary information, (d) datasets can contain data that are erroneous, out-of-date, or conflicting, (e) datasets even about the same domain may follow different conceptualizations of the domain, (f) everything can change (e.g., schemas, data) as time passes. This article surveys the work that has been done in the area of Linked Data integration, it identifies the main actors and use cases, it analyzes and factorizes the integration process according to various dimensions, and it discusses the methods that are used in each step. Emphasis is given on methods that can be used for integrating several datasets. Based on this analysis, the article concludes with directions that are worth further research.}, added-at = {2024-06-19T15:02:54.000+0200}, address = {New York, NY, USA}, articleno = {103}, author = {Mountantonakis, Michalis and Tzitzikas, Yannis}, biburl = {https://puma.ub.uni-stuttgart.de/bibtex/24f334c0f8c03d6160eb15a0b62579558/diglezakis}, doi = {10.1145/3345551}, interhash = {c96c3eac1cff15103a34fbbb1025b9a0}, intrahash = {4f334c0f8c03d6160eb15a0b62579558}, issn = {0360-0300}, issue_date = {September 2020}, journal = {ACM Comput. Surv.}, keywords = {integration linkedData metadata semanticWeb}, month = sep, number = 5, numpages = {40}, publisher = {Association for Computing Machinery}, timestamp = {2024-06-19T15:02:54.000+0200}, title = {Large-scale Semantic Integration of Linked Data: A Survey}, url = {https://doi.org/10.1145/3345551}, volume = 52, year = 2019 }