{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T13:12:53Z","timestamp":1742994773093,"version":"3.40.3"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031417733"},{"type":"electronic","value":"9783031417740"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-41774-0_24","type":"book-chapter","created":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T03:25:20Z","timestamp":1695266720000},"page":"300-312","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Evaluating Web Crawlers with\u00a0Machine Learning Algorithms for\u00a0Accurate Location Extraction from\u00a0Job Offers"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3163-9408","authenticated-orcid":false,"given":"Pawe\u0142","family":"Drozda","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2577-4470","authenticated-orcid":false,"given":"Bartosz A.","family":"Nowak","sequence":"additional","affiliation":[]},{"given":"Arkadiusz","family":"Talun","sequence":"additional","affiliation":[]},{"given":"Leszek","family":"Bukowski","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,9,22]]},"reference":[{"key":"24_CR1","doi-asserted-by":"publisher","unstructured":"Zhang, J., Niu, Y., Nie, H.: Web document classification based on fuzzy k-NN algorithm. In: 2009 International Conference on Computational Intelligence and Security, 2009, pp. 193\u2013196 (2009). https:\/\/doi.org\/10.1109\/CIS.2009.28","DOI":"10.1109\/CIS.2009.28"},{"key":"24_CR2","doi-asserted-by":"publisher","unstructured":"Dilip Patel, A., Pandya, V.N.: Web page classification based on context to the content extraction of articles. In: 2017 2nd International Conference for Convergence in Technology (I2CT), 2017, pp. 539\u2013541 (2017). https:\/\/doi.org\/10.1109\/I2CT.2017.8226188","DOI":"10.1109\/I2CT.2017.8226188"},{"key":"24_CR3","doi-asserted-by":"publisher","unstructured":"Weir, G. R. S., Dos Santos, E., Cartwright, B., Frank, R.: Positing the problem: enhancing classification of extremist web content through textual analysis. In: 2016 IEEE International Conference on Cybercrime and Computer Forensic (ICCCF), 2016, pp. 1\u20133 (2016). https:\/\/doi.org\/10.1109\/ICCCF.2016.7740431","DOI":"10.1109\/ICCCF.2016.7740431"},{"key":"24_CR4","doi-asserted-by":"publisher","unstructured":"Shen, D.: Text categorization. In: Liu, L., Ozsu, M.T. (eds.) Encyclopedia of Database Systems. Springer, Boston (2009). https:\/\/doi.org\/10.1007\/978-0-387-39940-9_414","DOI":"10.1007\/978-0-387-39940-9_414"},{"key":"24_CR5","doi-asserted-by":"publisher","unstructured":"Joachims, T.: Text classification. In: Learning to Classify Text Using Support Vector Machines. The Springer International Series in Engineering and Computer Science, vol. 668. Springer, Boston (2002). https:\/\/doi.org\/10.1007\/978-1-4615-0907-3_2","DOI":"10.1007\/978-1-4615-0907-3_2"},{"key":"24_CR6","doi-asserted-by":"publisher","unstructured":"Singh, A.K., Goyal, N.: Detection of malicious webpages using deep learning. In: 2021 IEEE International Conference on Big Data (Big Data), 2021, pp. 3370\u20133379 (2021). https:\/\/doi.org\/10.1109\/BigData52589.2021.9671622","DOI":"10.1109\/BigData52589.2021.9671622"},{"key":"24_CR7","doi-asserted-by":"publisher","unstructured":"Atari, M., Al-Mousa, A.: A machine-learning based approach for detecting phishing URLs. In: 2022 International Conference on Intelligent Data Science Technologies and Applications (IDSTA), 2022, pp. 82\u201388 (2022). https:\/\/doi.org\/10.1109\/IDSTA55301.2022.9923050","DOI":"10.1109\/IDSTA55301.2022.9923050"},{"key":"24_CR8","doi-asserted-by":"publisher","unstructured":"Liao, G.D., You, M.Z., Wang, G.C.: Experimental economic research for matching job positions. In: 2015 International Conference on Behavioral, Economic and Socio-cultural Computing (BESC), 2015, pp. 96\u2013101 (2015). https:\/\/doi.org\/10.1109\/BESC.2015.7365965","DOI":"10.1109\/BESC.2015.7365965"},{"key":"24_CR9","series-title":"Communications in Computer and Information Science","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1007\/978-3-030-59872-3_11","volume-title":"GIS LATAM","author":"MG Elizabeth","year":"2020","unstructured":"Elizabeth, M.G., Rivera, M.F.M., Alfonso, C.G.E.: Grouping mixed documents: Mexico job offers case study. In: Mata-Rivera, M.F., Zagal-Flores, R., Arellano Verdejo, J., Lazcano Hernandez, H.E. (eds.) GIS LATAM 2020. CCIS, vol. 1276, pp. 151\u2013159. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-59872-3_11"},{"key":"24_CR10","doi-asserted-by":"publisher","unstructured":"Di Meglio, E., Grassia, M., Misuraca, M.: The ideal candidate. Analysis of professional competences through text mining of job offers. In: Fabbris, L. (eds.) Effectiveness of University Education in Italy. Physica-Verlag HD, Heidelberg (2007). https:\/\/doi.org\/10.1007\/978-3-7908-1751-5_19","DOI":"10.1007\/978-3-7908-1751-5_19"},{"key":"24_CR11","doi-asserted-by":"publisher","unstructured":"Pektor, O., Walek, B., Martinik, I.: A data mining approach for finding similar job positions to upgrade a job position in a system for evaluating competencies. In: 2020 21th International Carpathian Control Conference (ICCC), 2020, pp. 1\u20135 (2020). https:\/\/doi.org\/10.1109\/ICCC49264.2020.9257298","DOI":"10.1109\/ICCC49264.2020.9257298"},{"key":"24_CR12","doi-asserted-by":"publisher","unstructured":"Liu, B., Menczer, F.: Web crawling. In: Web Data Mining. Data-Centric Systems and Applications. Springer, Berlin, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-3-642-19460-3_8","DOI":"10.1007\/978-3-642-19460-3_8"},{"key":"24_CR13","doi-asserted-by":"publisher","unstructured":"Khder, M.: Web scraping or web crawling: state of art, techniques, approaches and application. Int. J. Adv. Soft Comput. Appl. 13(3), 145\u2013168 (2021). https:\/\/doi.org\/10.15849\/IJASCA.211128.11","DOI":"10.15849\/IJASCA.211128.11"},{"key":"24_CR14","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"435","DOI":"10.1007\/978-3-030-61534-5_39","volume-title":"Artificial Intelligence and Soft Computing","author":"A Talun","year":"2020","unstructured":"Talun, A., Drozda, P., Bukowski, L., Scherer, R.: FastText and XGBoost content-based classification for employment web scraping. In: Rutkowski, L., Scherer, R., Korytkowski, M., Pedrycz, W., Tadeusiewicz, R., Zurada, J.M. (eds.) ICAISC 2020. LNCS (LNAI), vol. 12416, pp. 435\u2013444. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-61534-5_39"},{"key":"24_CR15","unstructured":"Drozda, P., Talun, A., Bukowski, L.: Emplobot-design of the system. In: Proceedings of the 28th International Workshop on Concurrency, Specification and Programming (2019)"},{"key":"24_CR16","doi-asserted-by":"publisher","unstructured":"Chen, T., Guestrin, C.E: XGBoost: a scalable tree boosting system. In: KDD \u201916: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 785\u2013794, August 2016. https:\/\/doi.org\/10.1145\/2939672.2939785","DOI":"10.1145\/2939672.2939785"},{"key":"24_CR17","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1007\/978-3-319-93782-3_6","volume-title":"Human Language Technology. Challenges for Computer Science and Linguistics","author":"J Ma\u0142yszko","year":"2018","unstructured":"Ma\u0142yszko, J., Abramowicz, W., Filipowska, A., Wagner, T.: Lemmatization of multi-word entity names for polish language using rules automatically generated based on the corpus analysis. In: Vetulani, Z., Mariani, J., Kubis, M. (eds.) LTC 2015. LNCS (LNAI), vol. 10930, pp. 74\u201384. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-93782-3_6"},{"key":"24_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"532","DOI":"10.1007\/978-3-662-49192-8_43","volume-title":"SOFSEM 2016: Theory and Practice of Computer Science","author":"L Gallay","year":"2016","unstructured":"Gallay, L., \u0160imko, M.: Utilizing vector models for automatic text lemmatization. In: Freivalds, R.M., Engels, G., Catania, B. (eds.) SOFSEM 2016. LNCS, vol. 9587, pp. 532\u2013543. Springer, Heidelberg (2016). https:\/\/doi.org\/10.1007\/978-3-662-49192-8_43"},{"key":"24_CR19","doi-asserted-by":"publisher","unstructured":"Ho, T.K.: Random decision forests. In: Proceedings of 3rd International Conference on Document Analysis and Recognition, 1995, vol. 1, pp. 278\u2013282 (1995). https:\/\/doi.org\/10.1109\/ICDAR.1995.598994","DOI":"10.1109\/ICDAR.1995.598994"},{"key":"24_CR20","doi-asserted-by":"publisher","unstructured":"Quinlan, J.R.: Induction of decision trees. Mach. Learn. 1, 81\u2013106 (1986). https:\/\/doi.org\/10.1007\/BF00116251","DOI":"10.1007\/BF00116251"},{"key":"24_CR21","doi-asserted-by":"publisher","unstructured":"Costa, V., Pedreira, C.: Recent advances in decision trees: an updated survey. Artif. Intell. Rev. (2022). https:\/\/doi.org\/10.1007\/s10462-022-10275-5","DOI":"10.1007\/s10462-022-10275-5"},{"key":"24_CR22","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1007\/BF00058655","volume":"24","author":"L Breiman","year":"1996","unstructured":"Breiman, L.: Bagging predictors. Mach. Learn. 24, 123\u2013140 (1996). https:\/\/doi.org\/10.1007\/BF00058655","journal-title":"Mach. Learn."},{"key":"24_CR23","doi-asserted-by":"crossref","unstructured":"Breiman, L.: Arcing classifiers. Ann. Stat. 26(3), 801\u2013824 (1998). pp. 801\u2013823. https:\/\/www.jstor.org\/stable\/120055","DOI":"10.1214\/aos\/1024691079"},{"key":"24_CR24","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1007\/BF00994018","volume":"20","author":"C Cortes","year":"1995","unstructured":"Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20, 273\u2013297 (1995). https:\/\/doi.org\/10.1007\/BF00994018","journal-title":"Mach. Learn."}],"container-title":["Communications in Computer and Information Science","Advances in Computational Collective Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-41774-0_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T06:33:15Z","timestamp":1695277995000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-41774-0_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031417733","9783031417740"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-41774-0_24","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"22 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICCCI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Collective Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Budapest","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hungary","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iccci2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iccci.pwr.edu.pl\/2023\/","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":"218","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":"59","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":"0","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":"27% - 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":"3.01","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":"1.86","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}