{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T13:44:49Z","timestamp":1758462289682,"version":"3.44.0"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032057266","type":"print"},{"value":"9783032057273","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T00:00:00Z","timestamp":1758499200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T00:00:00Z","timestamp":1758499200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-05727-3_25","type":"book-chapter","created":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T07:44:39Z","timestamp":1758440679000},"page":"280-295","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Improving Data Discovery Effectiveness: Experimental Evaluation of\u00a0Content-Based Catalogs in\u00a0Data Spaces"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-1124-9682","authenticated-orcid":false,"given":"Adriana","family":"Morej\u00f3n","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2867-8329","authenticated-orcid":false,"given":"Alberto","family":"Berenguer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1477-6999","authenticated-orcid":false,"given":"Luc\u00eda de","family":"Espona","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3287-9366","authenticated-orcid":false,"given":"David","family":"Tom\u00e1s","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7924-0880","authenticated-orcid":false,"given":"Jose-Norberto","family":"Maz\u00f3n","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,22]]},"reference":[{"issue":"3","key":"25_CR1","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1145\/3572751.3572755","volume":"51","author":"SA Azcoitia","year":"2022","unstructured":"Azcoitia, S.A., Laoutaris, N.: A survey of data marketplaces and their business models. ACM SIGMOD Rec. 51(3), 18\u201329 (2022)","journal-title":"ACM SIGMOD Rec."},{"key":"25_CR2","doi-asserted-by":"crossref","unstructured":"Bacco, M., Kocian, A., Chessa, S., Crivello, A., Barsocchi, P.: What are data spaces? Systematic survey and future outlook. Data Brief 57, 110969 (2024)","DOI":"10.1016\/j.dib.2024.110969"},{"key":"25_CR3","doi-asserted-by":"publisher","unstructured":"Berenguer, A., Alcaraz, O., Tom\u00e1s, D., Maz\u00f3n, J.: From research on data-intensive software to innovation in data spaces: a search service for tabular data. IEEE Softw. 41(3), 59\u201366 (2024). https:\/\/doi.org\/10.1109\/MS.2024.3359333","DOI":"10.1109\/MS.2024.3359333"},{"key":"25_CR4","doi-asserted-by":"publisher","unstructured":"Berenguer, A., Maz\u00f3n, J., Tom\u00e1s, D.: Word embeddings for retrieving tabular data from research publications. Mach. Learn. 113(4), 2227\u20132248 (2024). https:\/\/doi.org\/10.1007\/s10994-023-06472-0","DOI":"10.1007\/s10994-023-06472-0"},{"key":"25_CR5","unstructured":"Berenguer, A., Tom\u00e1s, D., Maz\u00f3n, J.: Tabular open government data search for data spaces based on word embeddings. In: Gallinucci, E., Golab, L. (eds.) Proceedings of the 25th International Workshop on Design, Optimization, Languages and Analytical Processing of Big Data (DOLAP 2023). CEUR Workshop Proceedings, vol.\u00a03369, pp. 61\u201370. CEUR-WS.org (2023). https:\/\/ceur-ws.org\/Vol-3369\/paper6.pdf"},{"key":"25_CR6","unstructured":"Bhandari, A., et\u00a0al.: Examples are all you need: iterative data discovery by example in data lakes. In: CIDR (2022)"},{"key":"25_CR7","doi-asserted-by":"publisher","unstructured":"Bogatu, A., Fernandes, A.A.A., Paton, N.W., Konstantinou, N.: Dataset discovery in data lakes. In: 2020 IEEE 36th International Conference on Data Engineering (ICDE), pp. 709\u2013720 (2020). https:\/\/doi.org\/10.1109\/ICDE48307.2020.00067","DOI":"10.1109\/ICDE48307.2020.00067"},{"key":"25_CR8","doi-asserted-by":"publisher","unstructured":"Castelo, S., Rampin, R., Santos, A., Bessa, A., Chirigati, F., Freire, J.: Auctus: a dataset search engine for data discovery and augmentation. Proc. VLDB Endow. 14(12), 2791\u20132794 (2021). https:\/\/doi.org\/10.14778\/3476311.3476346","DOI":"10.14778\/3476311.3476346"},{"key":"25_CR9","doi-asserted-by":"publisher","unstructured":"Chu, M.T., Khosla, R.: Index evaluations and business strategies on communities of practice. Expert Syst. Appl. 36(2, Part 1), 1549\u20131558 (2009). https:\/\/doi.org\/10.1016\/j.eswa.2007.11.053","DOI":"10.1016\/j.eswa.2007.11.053"},{"key":"25_CR10","doi-asserted-by":"publisher","unstructured":"Cinquini, M., Giannotti, F., Guidotti, R.: Boosting synthetic data generation with effective nonlinear causal discovery. In: 2021 IEEE Third International Conference on Cognitive Machine Intelligence (CogMI), pp. 54\u201363 (2021). https:\/\/doi.org\/10.1109\/CogMI52975.2021.00016","DOI":"10.1109\/CogMI52975.2021.00016"},{"key":"25_CR11","unstructured":"Cong, T., Nargesian, F., Jagadish, H.V.: Pylon: Semantic table union search in data lakes (2023). https:\/\/arxiv.org\/abs\/2301.04901"},{"key":"25_CR12","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1016\/j.neucom.2014.03.034","volume":"140","author":"Y Cui","year":"2014","unstructured":"Cui, Y., Jin, Z., Jiang, J.: A novel supervised feature extraction and classification fusion algorithm for land cover recognition of the off-land scenario. Neurocomputing 140, 77\u201383 (2014). https:\/\/doi.org\/10.1016\/j.neucom.2014.03.034","journal-title":"Neurocomputing"},{"key":"25_CR13","doi-asserted-by":"crossref","unstructured":"Dong, Y., Xiao, C., Nozawa, T., Enomoto, M., Oyamada, M.: Deepjoin: Joinable table discovery with pre-trained language models (2023). https:\/\/arxiv.org\/abs\/2212.07588","DOI":"10.14778\/3603581.3603587"},{"key":"25_CR14","doi-asserted-by":"crossref","unstructured":"Eichler, R., Gr\u00f6ger, C., Hoos, E., Schwarz, H., Mitschang, B.: Data shopping\u2014how an enterprise data marketplace supports data democratization in companies. In: International Conference on Advanced Information Systems Engineering, pp. 19\u201326. Springer (2022)","DOI":"10.1007\/978-3-031-07481-3_3"},{"key":"25_CR15","unstructured":"Esmailoghli, M., Schnell, C., Miller, R.J., Abedjan, Z.: Blend: A unified data discovery system (2024). https:\/\/arxiv.org\/abs\/2310.02656"},{"key":"25_CR16","doi-asserted-by":"crossref","unstructured":"Fan, G., Wang, J., Li, Y., Zhang, D., Miller, R.: Semantics-aware dataset discovery from data lakes with contextualized column-based representation learning (2023). https:\/\/arxiv.org\/abs\/2210.01922","DOI":"10.14778\/3587136.3587146"},{"issue":"12","key":"25_CR17","doi-asserted-by":"publisher","first-page":"1933","DOI":"10.14778\/3407790.3407800","volume":"13","author":"RC Fernandez","year":"2020","unstructured":"Fernandez, R.C., Subramaniam, P., Franklin, M.J.: Data market platforms: trading data assets to solve data problems. Proc. VLDB Endowment 13(12), 1933\u20131947 (2020)","journal-title":"Proc. VLDB Endowment"},{"issue":"2","key":"25_CR18","doi-asserted-by":"publisher","first-page":"274","DOI":"10.2218\/ijdc.v12i2.577","volume":"12","author":"D Fowler","year":"2017","unstructured":"Fowler, D., Barratt, J., Walsh, P.: Frictionless data: making research data quality visible. Int. J. Digit. Curation 12(2), 274\u2013285 (2017)","journal-title":"Int. J. Digit. Curation"},{"key":"25_CR19","unstructured":"Gie\u00df, A., M\u00f6ller, F., Schoormann, T., Otto, B.: Design options for data spaces. In: Thirty-First European Conference on Information Systems (ECIS 2023) (2023)"},{"key":"25_CR20","doi-asserted-by":"crossref","unstructured":"Gr\u00f6ger, C.: There is no AI without data. Commun. ACM 64(11), 98\u2013108 (2021)","DOI":"10.1145\/3448247"},{"key":"25_CR21","unstructured":"Hauff, M., Comet, L.M., Moosmann, P., Lange, C., Chrysakis, I., Theissen-Lipp, J.: FAIRness in dataspaces: the role of semantics for data management. In: The Second International Workshop on Semantics in Dataspaces, co-located with the Extended Semantic Web Conference (2024)"},{"key":"25_CR22","doi-asserted-by":"publisher","unstructured":"Hewagamage, P., Mihiranga, A., Perera, D., Fernando, R., Thilakarathna, T., Kasthurirathna, D.: Computer-vision enabled waste management system for green environment. In: 2021 3rd International Conference on Advancements in Computing (ICAC), pp. 276\u2013281 (2021). https:\/\/doi.org\/10.1109\/ICAC54203.2021.9671222","DOI":"10.1109\/ICAC54203.2021.9671222"},{"key":"25_CR23","doi-asserted-by":"publisher","unstructured":"Hu, X., et al.: Automatic table union search with tabular representation learning. In: Rogers, A., Boyd-Graber, J., Okazaki, N. (eds.) Findings of the Association for Computational Linguistics: ACL 2023, pp. 3786\u20133800. Association for Computational Linguistics, Toronto, Canada (2023). https:\/\/doi.org\/10.18653\/v1\/2023.findings-acl.233","DOI":"10.18653\/v1\/2023.findings-acl.233"},{"issue":"1","key":"25_CR24","doi-asserted-by":"publisher","first-page":"205395172098201","DOI":"10.1177\/2053951720982012","volume":"8","author":"P Hummel","year":"2021","unstructured":"Hummel, P., Braun, M., Tretter, M., Dabrock, P.: Data sovereignty: a review. Big Data Soc. 8(1), 2053951720982012 (2021)","journal-title":"Big Data Soc."},{"key":"25_CR25","doi-asserted-by":"publisher","unstructured":"Imielinski, T., Mannila, H.: A database perspective on knowledge discovery. Commun. ACM 39(11), 58\u201364 (1996). https:\/\/doi.org\/10.1145\/240455.240472","DOI":"10.1145\/240455.240472"},{"key":"25_CR26","unstructured":"International Data Spaces Association: Position Paper - GAIA-X and IDS (2021). https:\/\/internationaldataspaces.org\/wp-content\/uploads\/dlm_uploads\/IDSA-Position-Paper-GAIA-X-and-IDS.pdf"},{"key":"25_CR27","unstructured":"International Data Spaces Association: IDS Reference Architecture Model, Version 4.0 (2022). https:\/\/docs.internationaldataspaces.org\/ids-knowledgebase\/ids-ram-4\/introduction\/1_1_goals_of_the_international_data_spaces"},{"issue":"2","key":"25_CR28","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1007\/s13222-023-00445-2","volume":"23","author":"N Jahnke","year":"2023","unstructured":"Jahnke, N., Otto, B.: Data catalogs in the enterprise: applications and integration. Datenbank-Spektrum 23(2), 89\u201396 (2023)","journal-title":"Datenbank-Spektrum"},{"key":"25_CR29","doi-asserted-by":"crossref","unstructured":"Labadie, C., Legner, C., Eurich, M., Fadler, M.: Fair enough? Enhancing the usage of enterprise data with data catalogs. In: 2020 IEEE 22nd Conference on Business Informatics (CBI). vol.\u00a01, pp. 201\u2013210. IEEE (2020)","DOI":"10.1109\/CBI49978.2020.00029"},{"key":"25_CR30","doi-asserted-by":"crossref","unstructured":"M\u00f6ller, F., et al.: Industrial data ecosystems and data spaces. Electron. Mark. 34(1), 1\u201317 (2024)","DOI":"10.1007\/s12525-024-00724-0"},{"key":"25_CR31","unstructured":"Morej\u00f3n, A., et\u00a0al.: Exploring content-based catalogs for enhanced discovery services in data spaces. In: Mat\u00e9\u2019, A., Lissandrini, M. (eds.) Proceedings of the 27th International Workshop on Design, Optimization, Languages and Analytical Processing of Big Data (DOLAP 2025). CEUR Workshop Proceedings, vol.\u00a03931, pp. 79\u201384. CEUR (2025). https:\/\/ceur-ws.org\/Vol-3931\/short7.pdf"},{"key":"25_CR32","doi-asserted-by":"crossref","unstructured":"Nargesian, F., Asudeh, A., Jagadish, H.V.: Responsible data integration: next-generation challenges. In: Proceedings of the 2022 International Conference on Management of Data, pp. 2458\u20132464. SIGMOD \u201922, Association for Computing Machinery, New York, NY, USA (2022). https:\/\/doi.org\/10.1145\/3514221.3522567","DOI":"10.1145\/3514221.3522567"},{"key":"25_CR33","doi-asserted-by":"publisher","unstructured":"Otto, B.: A federated infrastructure for European data spaces. Commun. ACM 65(4), 44\u201345 (2022). https:\/\/doi.org\/10.1145\/3512341","DOI":"10.1145\/3512341"},{"key":"25_CR34","doi-asserted-by":"publisher","unstructured":"Pilaluisa, J., Tom\u00e1s, D., Navarro-Colorado, B., Maz\u00f3n, J.: Contextual word embeddings for tabular data search and integration. Neural Comput. Appl. 35(13), 9319\u20139333 (2023). https:\/\/doi.org\/10.1007\/s00521-022-08066-8","DOI":"10.1007\/s00521-022-08066-8"},{"key":"25_CR35","doi-asserted-by":"publisher","unstructured":"Ramos\u00a0Rojas, J.A., Beth\u00a0Kery, M., Rosenthal, S., Dey, A.: Sampling techniques to improve big data exploration. In: 2017 IEEE 7th Symposium on Large Data Analysis and Visualization (LDAV), pp. 26\u201335 (2017). https:\/\/doi.org\/10.1109\/LDAV.2017.8231848","DOI":"10.1109\/LDAV.2017.8231848"},{"key":"25_CR36","doi-asserted-by":"publisher","unstructured":"Santos, A., Bessa, A., Chirigati, F., Musco, C., Freire, J.: Correlation sketches for approximate join-correlation queries. In: Proceedings of the 2021 International Conference on Management of Data, pp. 1531\u20131544. SIGMOD\/PODS \u201921, ACM (2021). https:\/\/doi.org\/10.1145\/3448016.3458456","DOI":"10.1145\/3448016.3458456"},{"key":"25_CR37","doi-asserted-by":"publisher","unstructured":"Wang, F., Sun, K., Chen, M., Pujara, J., Szekely, P.: Retrieving complex tables with multi-granular graph representation learning. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1472\u20131482. SIGIR \u201921, ACM (2021). https:\/\/doi.org\/10.1145\/3404835.3462909","DOI":"10.1145\/3404835.3462909"},{"key":"25_CR38","doi-asserted-by":"publisher","unstructured":"Wang, Q., Castro\u00a0Fernandez, R.: Solo: data discovery using natural language questions via a self-supervised approach. Proc. ACM Manag. Data 1(4) (2023). https:\/\/doi.org\/10.1145\/3626756","DOI":"10.1145\/3626756"},{"key":"25_CR39","doi-asserted-by":"publisher","unstructured":"Xu, P., Ji, X., Li, M., Lu, W.: Virtual sample generation in machine learning assisted materials design and discovery. J. Mater. Inf. 3(3) (2023). https:\/\/doi.org\/10.20517\/jmi.2023.18","DOI":"10.20517\/jmi.2023.18"},{"key":"25_CR40","doi-asserted-by":"publisher","unstructured":"Zhang, S., Balog, K.: Ad hoc table retrieval using semantic similarity. In: Proceedings of the 2018 World Wide Web Conference on World Wide Web - WWW \u201918, pp. 1553\u20131562. WWW \u201918, ACM Press (2018). https:\/\/doi.org\/10.1145\/3178876.3186067","DOI":"10.1145\/3178876.3186067"}],"container-title":["Communications in Computer and Information Science","New Trends in Database and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-05727-3_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T07:44:47Z","timestamp":1758440687000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-05727-3_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,22]]},"ISBN":["9783032057266","9783032057273"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-05727-3_25","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,22]]},"assertion":[{"value":"22 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ADBIS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Advances in Databases and Information Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tampere","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Finland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"adbis2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/adbis2025.github.io\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}