@inproceedings{weber_odarchive_2020, address = {Cham}, series = {Lecture {Notes} in {Computer} {Science}}, title = {{ODArchive} – {Creating} an {Archive} for {Structured} {Data} from {Open} {Data} {Portals}}, isbn = {978-3-030-62466-8}, doi = {10/gh38b8}, abstract = {We present ODArchive, a large corpus of structured data collected from over 260 Open Data portals worldwide, alongside with curated, integrated metadata. Furthermore we enrich the harvested datasets by heuristic annotations using the type hierarchies in existing Knowledge Graphs. We both (i) present the underlying distributed architecture to scale up regular harvesting and monitoring changes on these portals, and (ii) make the corpus available via different APIs. Moreover, we (iii) analyse the characteristics of tabular data within the corpus. Our APIs can be used to regularly run such analyses or to reproduce experiments from the literature that have worked on static, not publicly available corpora.}, language = {en}, booktitle = {The {Semantic} {Web} – {ISWC} 2020}, publisher = {Springer International Publishing}, author = {Weber, Thomas and Mitöhner, Johann and Neumaier, Sebastian and Polleres, Axel}, editor = {Pan, Jeff Z. and Tamma, Valentina and d’Amato, Claudia and Janowicz, Krzysztof and Fu, Bo and Polleres, Axel and Seneviratne, Oshani and Kagal, Lalana}, year = {2020}, keywords = {Archiving, Extern, Forschungsgruppe Data Intelligence, Institut für IT Sicherheitsforschung, Open data, Profiling, Reference tables, Wiss. Beitrag, best, best-neumaier, peer-reviewed}, pages = {311--327}, }