Publication Information

{'id': 'https://openalex.org/W4254300012', 'doi': 'https://doi.org/10.1109/wi.2004.10097', 'title': 'The Evolution of Link-Attributes for Pages and Its Implications on Web Crawling', 'display_name': 'The Evolution of Link-Attributes for Pages and Its Implications on Web Crawling', 'publication_year': 2005, 'publication_date': '2005-03-31', 'ids': {'openalex': 'https://openalex.org/W4254300012', 'doi': 'https://doi.org/10.1109/wi.2004.10097'}, 'language': 'en', 'primary_location': {'is_oa': False, 'landing_page_url': 'https://doi.org/10.1109/wi.2004.10097', 'pdf_url': None, 'source': {'id': 'https://openalex.org/S4363608128', 'display_name': "IEEE/WIC/ACM International Conference on Web Intelligence (WI'04)", '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': ['crossref'], '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/A5101481970', 'display_name': 'Tao Meng', 'orcid': 'https://orcid.org/0000-0003-2988-7269'}, 'institutions': [{'id': 'https://openalex.org/I20231570', 'display_name': 'Peking University', 'ror': 'https://ror.org/02v51f717', 'country_code': 'CN', 'type': 'education', 'lineage': ['https://openalex.org/I20231570']}], 'countries': ['CN'], 'is_corresponding': False, 'raw_author_name': 'None Tao Meng', 'raw_affiliation_strings': ['Computer Networks and Distributed Systems Laboratory, Department of Computer Science and Technology, Peking University, Beijing, China'], 'affiliations': [{'raw_affiliation_string': 'Computer Networks and Distributed Systems Laboratory, Department of Computer Science and Technology, Peking University, Beijing, China', 'institution_ids': ['https://openalex.org/I20231570']}]}, {'author_position': 'middle', 'author': {'id': 'https://openalex.org/A5100934344', 'display_name': 'Hongfei Yan', 'orcid': None}, 'institutions': [{'id': 'https://openalex.org/I20231570', 'display_name': 'Peking University', 'ror': 'https://ror.org/02v51f717', 'country_code': 'CN', 'type': 'education', 'lineage': ['https://openalex.org/I20231570']}], 'countries': ['CN'], 'is_corresponding': False, 'raw_author_name': 'None Hongfei Yan', 'raw_affiliation_strings': ['Computer Networks and Distributed Systems Laboratory, Department of Computer Science and Technology, Peking University, Beijing, China'], 'affiliations': [{'raw_affiliation_string': 'Computer Networks and Distributed Systems Laboratory, Department of Computer Science and Technology, Peking University, Beijing, China', 'institution_ids': ['https://openalex.org/I20231570']}]}, {'author_position': 'middle', 'author': {'id': 'https://openalex.org/A5104005209', 'display_name': 'Jimin Wang', 'orcid': None}, 'institutions': [{'id': 'https://openalex.org/I20231570', 'display_name': 'Peking University', 'ror': 'https://ror.org/02v51f717', 'country_code': 'CN', 'type': 'education', 'lineage': ['https://openalex.org/I20231570']}], 'countries': ['CN'], 'is_corresponding': False, 'raw_author_name': 'None Jimin Wang', 'raw_affiliation_strings': ['Computer Networks and Distributed Systems Laboratory, Department of Computer Science and Technology, Peking University, Beijing, China'], 'affiliations': [{'raw_affiliation_string': 'Computer Networks and Distributed Systems Laboratory, Department of Computer Science and Technology, Peking University, Beijing, China', 'institution_ids': ['https://openalex.org/I20231570']}]}, {'author_position': 'last', 'author': {'id': 'https://openalex.org/A5021280609', 'display_name': 'Xiaoming Li', 'orcid': 'https://orcid.org/0000-0001-7085-2768'}, 'institutions': [{'id': 'https://openalex.org/I20231570', 'display_name': 'Peking University', 'ror': 'https://ror.org/02v51f717', 'country_code': 'CN', 'type': 'education', 'lineage': ['https://openalex.org/I20231570']}], 'countries': ['CN'], 'is_corresponding': False, 'raw_author_name': 'None Xiaoming Li', 'raw_affiliation_strings': ['Computer Networks and Distributed Systems Laboratory, Department of Computer Science and Technology, Peking University, Beijing, China'], 'affiliations': [{'raw_affiliation_string': 'Computer Networks and Distributed Systems Laboratory, Department of Computer Science and Technology, Peking University, Beijing, China', 'institution_ids': ['https://openalex.org/I20231570']}]}], 'institution_assertions': [], 'countries_distinct_count': 1, 'institutions_distinct_count': 1, 'corresponding_author_ids': [], 'corresponding_institution_ids': [], 'apc_list': None, 'apc_paid': None, 'fwci': 0.409, 'has_fulltext': True, 'fulltext_origin': 'ngrams', 'cited_by_count': 4, 'citation_normalized_percentile': {'value': 0.561838, 'is_in_top_1_percent': False, 'is_in_top_10_percent': False}, 'cited_by_percentile_year': {'min': 74, 'max': 76}, 'biblio': {'volume': None, 'issue': None, 'first_page': '578', 'last_page': '581'}, 'is_retracted': False, 'is_paratext': False, 'primary_topic': {'id': 'https://openalex.org/T12016', 'display_name': 'Web Data Mining and Analysis', 'score': 0.9997, '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': 0.9997, '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': 0.9533, '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/T11478', 'display_name': 'Caching and Content Delivery', 'score': 0.9136, 'subfield': {'id': 'https://openalex.org/subfields/1705', 'display_name': 'Computer Networks and Communications'}, '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/web-crawler', 'display_name': 'Web crawler', 'score': 0.92600703}, {'id': 'https://openalex.org/keywords/crawling', 'display_name': 'Crawling', 'score': 0.8777598}, {'id': 'https://openalex.org/keywords/pagerank', 'display_name': 'PageRank', 'score': 0.7494348}, {'id': 'https://openalex.org/keywords/hits-algorithm', 'display_name': 'HITS algorithm', 'score': 0.6675205}, {'id': 'https://openalex.org/keywords/focused-crawler', 'display_name': 'Focused crawler', 'score': 0.5828818}, {'id': 'https://openalex.org/keywords/link', 'display_name': 'Link (geometry)', 'score': 0.5599143}, {'id': 'https://openalex.org/keywords/link-analysis', 'display_name': 'Link analysis', 'score': 0.55123144}], 'concepts': [{'id': 'https://openalex.org/C13743948', 'wikidata': 'https://www.wikidata.org/wiki/Q45842', 'display_name': 'Web crawler', 'level': 2, 'score': 0.92600703}, {'id': 'https://openalex.org/C100368936', 'wikidata': 'https://www.wikidata.org/wiki/Q1411725', 'display_name': 'Crawling', 'level': 2, 'score': 0.8777598}, {'id': 'https://openalex.org/C21959979', 'wikidata': 'https://www.wikidata.org/wiki/Q36774', 'display_name': 'Web page', 'level': 2, 'score': 0.8087914}, {'id': 'https://openalex.org/C41008148', 'wikidata': 'https://www.wikidata.org/wiki/Q21198', 'display_name': 'Computer science', 'level': 0, 'score': 0.7502303}, {'id': 'https://openalex.org/C2779172887', 'wikidata': 'https://www.wikidata.org/wiki/Q184316', 'display_name': 'PageRank', 'level': 2, 'score': 0.7494348}, {'id': 'https://openalex.org/C195409031', 'wikidata': 'https://www.wikidata.org/wiki/Q1031957', 'display_name': 'HITS algorithm', 'level': 5, 'score': 0.6675205}, {'id': 'https://openalex.org/C23123220', 'wikidata': 'https://www.wikidata.org/wiki/Q816826', 'display_name': 'Information retrieval', 'level': 1, 'score': 0.6415961}, {'id': 'https://openalex.org/C73340581', 'wikidata': 'https://www.wikidata.org/wiki/Q5463958', 'display_name': 'Focused crawler', 'level': 5, 'score': 0.5828818}, {'id': 'https://openalex.org/C2777382242', 'wikidata': 'https://www.wikidata.org/wiki/Q6017816', 'display_name': 'Index (typography)', 'level': 2, 'score': 0.569617}, {'id': 'https://openalex.org/C136764020', 'wikidata': 'https://www.wikidata.org/wiki/Q466', 'display_name': 'World Wide Web', 'level': 1, 'score': 0.56578404}, {'id': 'https://openalex.org/C2778753846', 'wikidata': 'https://www.wikidata.org/wiki/Q6554239', 'display_name': 'Link (geometry)', 'level': 2, 'score': 0.5599143}, {'id': 'https://openalex.org/C1173588', 'wikidata': 'https://www.wikidata.org/wiki/Q6554294', 'display_name': 'Link analysis', 'level': 2, 'score': 0.55123144}, {'id': 'https://openalex.org/C521815418', 'wikidata': 'https://www.wikidata.org/wiki/Q4182287', 'display_name': 'Web search engine', 'level': 4, 'score': 0.5351193}, {'id': 'https://openalex.org/C173576120', 'wikidata': 'https://www.wikidata.org/wiki/Q2641220', 'display_name': 'Static web page', 'level': 4, 'score': 0.50217867}, {'id': 'https://openalex.org/C97854310', 'wikidata': 'https://www.wikidata.org/wiki/Q19541', 'display_name': 'Search engine', 'level': 2, 'score': 0.45869344}, {'id': 'https://openalex.org/C25343380', 'wikidata': 'https://www.wikidata.org/wiki/Q277521', 'display_name': 'Relation (database)', 'level': 2, 'score': 0.42853373}, {'id': 'https://openalex.org/C124101348', 'wikidata': 'https://www.wikidata.org/wiki/Q172491', 'display_name': 'Data mining', 'level': 1, 'score': 0.3052526}, {'id': 'https://openalex.org/C79373723', 'wikidata': 'https://www.wikidata.org/wiki/Q386275', 'display_name': 'Web development', 'level': 3, 'score': 0.17516613}, {'id': 'https://openalex.org/C71924100', 'wikidata': 'https://www.wikidata.org/wiki/Q11190', 'display_name': 'Medicine', 'level': 0, 'score': 0.0}, {'id': 'https://openalex.org/C31258907', 'wikidata': 'https://www.wikidata.org/wiki/Q1301371', 'display_name': 'Computer network', 'level': 1, 'score': 0.0}, {'id': 'https://openalex.org/C105702510', 'wikidata': 'https://www.wikidata.org/wiki/Q514', 'display_name': 'Anatomy', 'level': 1, 'score': 0.0}], 'mesh': [], 'locations_count': 1, 'locations': [{'is_oa': False, 'landing_page_url': 'https://doi.org/10.1109/wi.2004.10097', 'pdf_url': None, 'source': {'id': 'https://openalex.org/S4363608128', 'display_name': "IEEE/WIC/ACM International Conference on Web Intelligence (WI'04)", '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': [], 'grants': [], 'datasets': [], 'versions': [], 'referenced_works_count': 8, 'referenced_works': ['https://openalex.org/W1566984846', 'https://openalex.org/W1854214752', 'https://openalex.org/W2081470778', 'https://openalex.org/W2129620481', 'https://openalex.org/W2164542999', 'https://openalex.org/W2169557227', 'https://openalex.org/W2170582301', 'https://openalex.org/W4251434705'], 'related_works': ['https://openalex.org/W4254300012', 'https://openalex.org/W3201526811', 'https://openalex.org/W2610451498', 'https://openalex.org/W2417265363', 'https://openalex.org/W2402678663', 'https://openalex.org/W2379145789', 'https://openalex.org/W2377634017', 'https://openalex.org/W2097704339', 'https://openalex.org/W1999548128', 'https://openalex.org/W1994958611'], 'abstract_inverted_index': {'It': [0], 'is': [1, 156], 'important': [2], 'for': [3, 31, 160], 'an': [4, 36, 152], 'incremental': [5, 32, 153], 'crawler': [6], 'to': [7, 38, 121, 134, 146], 'know': [8], 'how': [9], 'web': [10, 54, 128, 165], 'pages': [11, 55, 105, 110, 119, 137], 'evolve': [12], 'and': [13, 20, 34, 92, 164], 'the': [14, 21, 40, 46, 50, 53, 72, 109, 118, 124, 127, 149, 157], 'relation': [15], 'between': [16, 42], 'their': [17], 'changing': [18], 'frequencies': [19], 'link-attributes': [22, 51, 94, 103], 'such': [23], 'as': [24], 'indegrees.': [25], 'This': [26], 'paper': [27], 'proposes': [28], 'a': [29, 98, 139], 'model': [30], 'crawling': [33], 'performs': [35], 'experiment': [37], 'verify': [39], 'correlation': [41], 'them,': [43], 'by': [44], 'monitoring': [45], 'evolution': [47], 'of': [48, 52, 67, 104, 117, 123, 151], 'all': [49, 95], 'within': [56], 'one': [57, 64], 'website.': [58, 140], 'Particularly,': [59], 'we': [60, 74], 'look': [61], 'deeply': [62], 'into': [63], 'special': [65], 'kind': [66], 'page': [68], 'named': [69], 'Index-pages.': [70], 'From': [71], 'experiment,': [73], 'can': [75, 143], 'make': [76], 'four': [77], 'conclusions:': [78], '(1)': [79], 'Pages': [80], 'which': [81, 155], 'have': [82], 'bigger': [83], 'indegrees,': [84], 'outdegrees': [85], 'or': [86], 'PageRank': [87], 'values': [88], 'change': [89, 107, 111], 'more': [90], 'often,': [91], 'these': [93], 'approximately': [96], 'obey': [97], 'power-law': [99], 'distribution.': [100], '(2)': [101], 'The': [102, 131], 'seldom': [106], 'though': [108], 'themselves.': [112], '(3)': [113], 'A': [114], 'small': [115], 'proportion': [116], 'link': [120, 133], 'most': [122], 'vertexes': [125], 'in': [126, 138], 'graph.': [129], '(4)': [130], 'Index-pages': [132], 'sizeable': [135], 'new': [136], 'These': [141], 'conclusions': [142], 'be': [144], 'used': [145], 'greatly': [147], 'enhance': [148], 'performance': [150], 'crawler,': [154], 'foremost': [158], 'component': [159], 'general': [161], 'search': [162], 'engines': [163], 'information': [166], 'stores.': [167]}, 'cited_by_api_url': 'https://api.openalex.org/works?filter=cites:W4254300012', 'counts_by_year': [{'year': 2013, 'cited_by_count': 1}], 'updated_date': '2024-12-11T18:28:44.837166', 'created_date': '2022-05-12'}