Publication Information

{'id': 'https://openalex.org/W2104086170', 'doi': None, 'title': 'RoadRunner: Towards Automatic Data Extraction from Large Web Sites', 'display_name': 'RoadRunner: Towards Automatic Data Extraction from Large Web Sites', 'publication_year': 2001, 'publication_date': '2001-09-11', 'ids': {'openalex': 'https://openalex.org/W2104086170', 'mag': '2104086170'}, 'language': 'en', 'primary_location': {'is_oa': False, 'landing_page_url': 'https://www.cse.iitb.ac.in/infolab/Data/Conferences/vldb2k1/015_109.pdf', 'pdf_url': None, 'source': {'id': 'https://openalex.org/S4306421142', 'display_name': 'Very Large Data Bases', 'issn_l': None, 'issn': None, 'is_oa': False, 'is_in_doaj': False, 'is_core': False, 'host_organization': None, 'host_organization_name': None, 'host_organization_lineage': [], 'host_organization_lineage_names': [], 'type': 'conference'}, 'license': None, 'license_id': None, 'version': None, 'is_accepted': False, 'is_published': False}, 'type': 'article', 'type_crossref': 'proceedings-article', 'indexed_in': [], 'open_access': {'is_oa': False, 'oa_status': 'closed', 'oa_url': None, 'any_repository_has_fulltext': False}, 'authorships': [{'author_position': 'first', 'author': {'id': 'https://openalex.org/A5030700727', 'display_name': 'Valter Crescenzi', 'orcid': None}, 'institutions': [{'id': 'https://openalex.org/I119003972', 'display_name': 'Roma Tre University', 'ror': 'https://ror.org/05vf0dg29', 'country_code': 'IT', 'type': 'education', 'lineage': ['https://openalex.org/I119003972']}], 'countries': ['IT'], 'is_corresponding': False, 'raw_author_name': 'Valter Crescenzi', 'raw_affiliation_strings': ['Roma Tre University#TAB#'], 'affiliations': [{'raw_affiliation_string': 'Roma Tre University#TAB#', 'institution_ids': ['https://openalex.org/I119003972']}]}, {'author_position': 'middle', 'author': {'id': 'https://openalex.org/A5008291639', 'display_name': 'Giansalvatore Mecca', 'orcid': 'https://orcid.org/0000-0002-1189-1481'}, 'institutions': [{'id': 'https://openalex.org/I20272500', 'display_name': 'University of Basilicata', 'ror': 'https://ror.org/03tc05689', 'country_code': 'IT', 'type': 'education', 'lineage': ['https://openalex.org/I20272500']}], 'countries': ['IT'], 'is_corresponding': False, 'raw_author_name': 'Giansalvatore Mecca', 'raw_affiliation_strings': ['University of Basilicata'], 'affiliations': [{'raw_affiliation_string': 'University of Basilicata', 'institution_ids': ['https://openalex.org/I20272500']}]}, {'author_position': 'last', 'author': {'id': 'https://openalex.org/A5022736687', 'display_name': 'Paolo Merialdo', 'orcid': 'https://orcid.org/0000-0002-3852-8092'}, 'institutions': [{'id': 'https://openalex.org/I119003972', 'display_name': 'Roma Tre University', 'ror': 'https://ror.org/05vf0dg29', 'country_code': 'IT', 'type': 'education', 'lineage': ['https://openalex.org/I119003972']}], 'countries': ['IT'], 'is_corresponding': False, 'raw_author_name': 'Paolo Merialdo', 'raw_affiliation_strings': ['Roma Tre University#TAB#'], 'affiliations': [{'raw_affiliation_string': 'Roma Tre University#TAB#', 'institution_ids': ['https://openalex.org/I119003972']}]}], 'institution_assertions': [], 'countries_distinct_count': 1, 'institutions_distinct_count': 2, 'corresponding_author_ids': [], 'corresponding_institution_ids': [], 'apc_list': None, 'apc_paid': None, 'fwci': 24.483, 'has_fulltext': False, 'cited_by_count': 951, 'citation_normalized_percentile': {'value': 0.971138, 'is_in_top_1_percent': False, 'is_in_top_10_percent': True}, 'cited_by_percentile_year': {'min': 99, 'max': 100}, 'biblio': {'volume': None, 'issue': '27', 'first_page': '109', 'last_page': '118'}, 'is_retracted': False, 'is_paratext': False, 'primary_topic': {'id': 'https://openalex.org/T12016', 'display_name': 'Web Data Mining and Analysis', 'score': 1.0, 'subfield': {'id': 'https://openalex.org/subfields/1710', 'display_name': 'Information Systems'}, 'field': {'id': 'https://openalex.org/fields/17', 'display_name': 'Computer Science'}, 'domain': {'id': 'https://openalex.org/domains/3', 'display_name': 'Physical Sciences'}}, 'topics': [{'id': 'https://openalex.org/T12016', 'display_name': 'Web Data Mining and Analysis', 'score': 1.0, 'subfield': {'id': 'https://openalex.org/subfields/1710', 'display_name': 'Information Systems'}, 'field': {'id': 'https://openalex.org/fields/17', 'display_name': 'Computer Science'}, 'domain': {'id': 'https://openalex.org/domains/3', 'display_name': 'Physical Sciences'}}, {'id': 'https://openalex.org/T11269', 'display_name': 'Algorithms and Data Compression', 'score': 0.9934, 'subfield': {'id': 'https://openalex.org/subfields/1702', 'display_name': 'Artificial Intelligence'}, 'field': {'id': 'https://openalex.org/fields/17', 'display_name': 'Computer Science'}, 'domain': {'id': 'https://openalex.org/domains/3', 'display_name': 'Physical Sciences'}}, {'id': 'https://openalex.org/T11241', 'display_name': 'Advanced Malware Detection Techniques', 'score': 0.984, 'subfield': {'id': 'https://openalex.org/subfields/1711', 'display_name': 'Signal Processing'}, 'field': {'id': 'https://openalex.org/fields/17', 'display_name': 'Computer Science'}, 'domain': {'id': 'https://openalex.org/domains/3', 'display_name': 'Physical Sciences'}}], 'keywords': [{'id': 'https://openalex.org/keywords/data-extraction', 'display_name': 'Data extraction', 'score': 0.6617092}], 'concepts': [{'id': 'https://openalex.org/C41008148', 'wikidata': 'https://www.wikidata.org/wiki/Q21198', 'display_name': 'Computer science', 'level': 0, 'score': 0.7900658}, {'id': 'https://openalex.org/C2777466982', 'wikidata': 'https://www.wikidata.org/wiki/Q5227287', 'display_name': 'Data extraction', 'level': 3, 'score': 0.6617092}, {'id': 'https://openalex.org/C98045186', 'wikidata': 'https://www.wikidata.org/wiki/Q205663', 'display_name': 'Process (computing)', 'level': 2, 'score': 0.59674525}, {'id': 'https://openalex.org/C124101348', 'wikidata': 'https://www.wikidata.org/wiki/Q172491', 'display_name': 'Data mining', 'level': 1, 'score': 0.53629035}, {'id': 'https://openalex.org/C4725764', 'wikidata': 'https://www.wikidata.org/wiki/Q844704', 'display_name': 'Extraction (chemistry)', 'level': 2, 'score': 0.50927866}, {'id': 'https://openalex.org/C21959979', 'wikidata': 'https://www.wikidata.org/wiki/Q36774', 'display_name': 'Web page', 'level': 2, 'score': 0.4778697}, {'id': 'https://openalex.org/C77088390', 'wikidata': 'https://www.wikidata.org/wiki/Q8513', 'display_name': 'Database', 'level': 1, 'score': 0.40913206}, {'id': 'https://openalex.org/C23123220', 'wikidata': 'https://www.wikidata.org/wiki/Q816826', 'display_name': 'Information retrieval', 'level': 1, 'score': 0.33634064}, {'id': 'https://openalex.org/C136764020', 'wikidata': 'https://www.wikidata.org/wiki/Q466', 'display_name': 'World Wide Web', 'level': 1, 'score': 0.27363428}, {'id': 'https://openalex.org/C111919701', 'wikidata': 'https://www.wikidata.org/wiki/Q9135', 'display_name': 'Operating system', 'level': 1, 'score': 0.15867263}, {'id': 'https://openalex.org/C185592680', 'wikidata': 'https://www.wikidata.org/wiki/Q2329', 'display_name': 'Chemistry', 'level': 0, 'score': 0.0}, {'id': 'https://openalex.org/C2779473830', 'wikidata': 'https://www.wikidata.org/wiki/Q1540899', 'display_name': 'MEDLINE', 'level': 2, 'score': 0.0}, {'id': 'https://openalex.org/C43617362', 'wikidata': 'https://www.wikidata.org/wiki/Q170050', 'display_name': 'Chromatography', 'level': 1, 'score': 0.0}, {'id': 'https://openalex.org/C17744445', 'wikidata': 'https://www.wikidata.org/wiki/Q36442', 'display_name': 'Political science', 'level': 0, 'score': 0.0}, {'id': 'https://openalex.org/C199539241', 'wikidata': 'https://www.wikidata.org/wiki/Q7748', 'display_name': 'Law', 'level': 1, 'score': 0.0}], 'mesh': [], 'locations_count': 1, 'locations': [{'is_oa': False, 'landing_page_url': 'https://www.cse.iitb.ac.in/infolab/Data/Conferences/vldb2k1/015_109.pdf', 'pdf_url': None, 'source': {'id': 'https://openalex.org/S4306421142', 'display_name': 'Very Large Data Bases', 'issn_l': None, 'issn': None, 'is_oa': False, 'is_in_doaj': False, 'is_core': False, 'host_organization': None, 'host_organization_name': None, 'host_organization_lineage': [], 'host_organization_lineage_names': [], 'type': 'conference'}, 'license': None, 'license_id': None, 'version': None, 'is_accepted': False, 'is_published': False}], 'best_oa_location': None, 'sustainable_development_goals': [{'display_name': 'Responsible consumption and production', 'score': 0.48, 'id': 'https://metadata.un.org/sdg/12'}], 'grants': [], 'datasets': [], 'versions': [], 'referenced_works_count': 19, 'referenced_works': ['https://openalex.org/W1487227972', 'https://openalex.org/W1543195558', 'https://openalex.org/W1553019137', 'https://openalex.org/W1588659924', 'https://openalex.org/W1607995248', 'https://openalex.org/W1887448736', 'https://openalex.org/W1969005071', 'https://openalex.org/W1983736818', 'https://openalex.org/W1990117407', 'https://openalex.org/W2017603160', 'https://openalex.org/W2037504378', 'https://openalex.org/W2037600449', 'https://openalex.org/W2049851508', 'https://openalex.org/W2065568440', 'https://openalex.org/W2083317499', 'https://openalex.org/W2135479443', 'https://openalex.org/W2140327372', 'https://openalex.org/W2153072229', 'https://openalex.org/W2162340487'], 'related_works': ['https://openalex.org/W2166407869', 'https://openalex.org/W2162340487', 'https://openalex.org/W2160196229', 'https://openalex.org/W2153072229', 'https://openalex.org/W2150721933', 'https://openalex.org/W2148210463', 'https://openalex.org/W2143309843', 'https://openalex.org/W2140327372', 'https://openalex.org/W2135479443', 'https://openalex.org/W2134150392', 'https://openalex.org/W2128836931', 'https://openalex.org/W2128341918', 'https://openalex.org/W2069388662', 'https://openalex.org/W2067416210', 'https://openalex.org/W2065568440', 'https://openalex.org/W2015551056', 'https://openalex.org/W2005646337', 'https://openalex.org/W1927338256', 'https://openalex.org/W1616576116', 'https://openalex.org/W1553019137'], 'abstract_inverted_index': {'The': [0], 'paper': [1, 28], 'investigates': [2], 'techniques': [3], 'for': [4], 'extracting': [5], 'data': [6, 24], 'from': [7], 'HTML': [8, 35], 'sites': [9, 53], 'through': [10], 'the': [11, 19, 23, 27, 55, 58], 'use': [12], 'of': [13, 57], 'automatically': [14], 'generated': [15], 'wrappers.': [16], 'To': [17], 'automate': [18], 'wrapper': [20, 40], 'generation': [21], 'and': [22, 37, 45], 'extraction': [25], 'process,': [26], 'develops': [29], 'a': [30, 39], 'novel': [31], 'technique': [32], 'to': [33], 'compare': [34], 'pages': [36], 'generate': [38], 'based': [41], 'on': [42, 49], 'their': [43], 'similarities': [44], 'dierences.': [46], 'Experimental': [47], 'results': [48], 'real-life': [50], 'data-intensive': [51], 'Web': [52], 'confirm': [54], 'feasibility': [56], 'approach.': [59]}, 'cited_by_api_url': 'https://api.openalex.org/works?filter=cites:W2104086170', 'counts_by_year': [{'year': 2023, 'cited_by_count': 1}, {'year': 2022, 'cited_by_count': 4}, {'year': 2021, 'cited_by_count': 10}, {'year': 2020, 'cited_by_count': 8}, {'year': 2019, 'cited_by_count': 10}, {'year': 2018, 'cited_by_count': 28}, {'year': 2017, 'cited_by_count': 21}, {'year': 2016, 'cited_by_count': 30}, {'year': 2015, 'cited_by_count': 51}, {'year': 2014, 'cited_by_count': 75}, {'year': 2013, 'cited_by_count': 51}, {'year': 2012, 'cited_by_count': 55}], 'updated_date': '2025-01-03T23:52:52.373476', 'created_date': '2016-06-24'}