{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T22:10:41Z","timestamp":1758924641342,"version":"3.40.3"},"publisher-location":"Cham","reference-count":14,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031168017"},{"type":"electronic","value":"9783031168024"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-16802-4_9","type":"book-chapter","created":{"date-parts":[[2022,9,14]],"date-time":"2022-09-14T10:05:31Z","timestamp":1663149931000},"page":"107-119","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["DETEXA: Declarative Extensible Text Exploration and\u00a0Analysis"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2785-946X","authenticated-orcid":false,"given":"Yannis","family":"Foufoulas","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0426-337X","authenticated-orcid":false,"given":"Eleni","family":"Zacharia","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9791-587X","authenticated-orcid":false,"given":"Harry","family":"Dimitropoulos","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3477-3082","authenticated-orcid":false,"given":"Natalia","family":"Manola","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1705-8247","authenticated-orcid":false,"given":"Yannis","family":"Ioannidis","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,9,15]]},"reference":[{"key":"9_CR1","unstructured":"NLTK. https:\/\/www.nltk.org"},{"key":"9_CR2","unstructured":"PySpark. https:\/\/spark.apache.org\/docs\/latest\/api\/python\/"},{"key":"9_CR3","unstructured":"Dask. https:\/\/dask.org"},{"key":"9_CR4","doi-asserted-by":"crossref","unstructured":"Raasveldt, M., M\u00fchleisen, H.: Vectorized UDFs in column-stores. In: Proceedings of the 28th International Conference on Scientific and Statistical Database Management (2016)","DOI":"10.1145\/2949689.2949703"},{"key":"9_CR5","unstructured":"https:\/\/www.postgresql.org\/docs\/current\/xfunc.html"},{"key":"9_CR6","unstructured":"https:\/\/www.vertica.com\/docs\/9.2.x\/HTML\/Content\/Authoring\/ExtendingVertica\/UDF-SQLFunctions\/CreatingUser-DefinedSQLFunctions.htm"},{"key":"9_CR7","unstructured":"Declarative Extensible Text EXploration and Analysis (DETEXA). https:\/\/github.com\/madgik\/detexa"},{"key":"9_CR8","doi-asserted-by":"crossref","unstructured":"Foufoulas, Y., Simitsis, A., Stamatogiannakis, L., Ioannidis, Y.: YeSQL: \u201cYou extend SQL\u201d with rich and highly performant user-defined functions in relational databases. PVLDB (2022)","DOI":"10.14778\/3547305.3547328"},{"key":"9_CR9","unstructured":"OpenAIRE. https:\/\/www.openaire.eu"},{"issue":"1","key":"9_CR10","first-page":"29","volume":"19","author":"G Varoquaux","year":"2015","unstructured":"Varoquaux, G., et al.: Scikit-learn: machine learning without learning the machinery. GetMob.: Mob. Comput. Commun. 19(1), 29\u201333 (2015)","journal-title":"GetMob.: Mob. Comput. Commun."},{"key":"9_CR11","unstructured":"Vasiliev, Y.: Natural Language Processing with Python and SpaCy: A Practical Introduction. No Starch Press (2020)"},{"key":"9_CR12","unstructured":"Gensim text processing library. https:\/\/radimrehurek.com\/gensim"},{"key":"9_CR13","series-title":"Communications in Computer and Information Science","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1007\/978-3-319-08425-1_10","volume-title":"Theory and Practice of Digital Libraries \u2013 TPDL 2013 Selected Workshops","author":"T Giannakopoulos","year":"2014","unstructured":"Giannakopoulos, T., Stamatogiannakis, E., Foufoulas, I., Dimitropoulos, H., Manola, N., Ioannidis, Y.: Content visualization of scientific corpora using an extensible relational database implementation. In: Bolikowski, \u0141, Casarosa, V., Goodale, P., Houssos, N., Manghi, P., Schirrwagen, J. (eds.) TPDL 2013. CCIS, vol. 416, pp. 101\u2013112. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-08425-1_10"},{"key":"9_CR14","unstructured":"tfidf algorithm. https:\/\/www.kaggle.com\/code\/xfffrank\/tfidf-stemming\/notebook"}],"container-title":["Lecture Notes in Computer Science","Linking Theory and Practice of Digital Libraries"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-16802-4_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T18:40:09Z","timestamp":1710268809000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-16802-4_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031168017","9783031168024"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-16802-4_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"15 September 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"TPDL","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Theory and Practice of Digital Libraries","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Padua","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"tpdl2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tpdl2022.dei.unipd.it\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"107","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"18","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"27","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"17% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"15 accelerating innovation papers included in these proceedings","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}