Publication Information

{'id': 'https://openalex.org/W1585432388', 'doi': 'https://doi.org/10.1109/iciiecs.2015.7193044', 'title': 'Web data extraction and alignment using tag and value similarity', 'display_name': 'Web data extraction and alignment using tag and value similarity', 'publication_year': 2015, 'publication_date': '2015-03-01', 'ids': {'openalex': 'https://openalex.org/W1585432388', 'doi': 'https://doi.org/10.1109/iciiecs.2015.7193044', 'mag': '1585432388'}, 'language': 'en', 'primary_location': {'is_oa': False, 'landing_page_url': 'https://doi.org/10.1109/iciiecs.2015.7193044', 'pdf_url': None, 'source': None, '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/A5045012777', 'display_name': 'K.A. Pakojwar', 'orcid': None}, 'institutions': [], 'countries': ['IN'], 'is_corresponding': False, 'raw_author_name': 'K.A. Pakojwar', 'raw_affiliation_strings': ['Department of Computer Engg., BDCE Sewagram, Wardha-442001, India'], 'affiliations': [{'raw_affiliation_string': 'Department of Computer Engg., BDCE Sewagram, Wardha-442001, India', 'institution_ids': []}]}, {'author_position': 'middle', 'author': {'id': 'https://openalex.org/A5025325866', 'display_name': 'Ramchandra Mangrulkar', 'orcid': 'https://orcid.org/0000-0002-9020-0713'}, 'institutions': [], 'countries': ['IN'], 'is_corresponding': False, 'raw_author_name': 'R.S. Mangrulkar', 'raw_affiliation_strings': ['Department of Computer Engg., BDCE Sewagram, Wardha-442001, India'], 'affiliations': [{'raw_affiliation_string': 'Department of Computer Engg., BDCE Sewagram, Wardha-442001, India', 'institution_ids': []}]}, {'author_position': 'last', 'author': {'id': 'https://openalex.org/A5076418654', 'display_name': 'Vaishali G. Bhujade', 'orcid': None}, 'institutions': [], 'countries': ['IN'], 'is_corresponding': False, 'raw_author_name': 'V.G. Bhujade', 'raw_affiliation_strings': ['Department of Computer Engg., BDCE Sewagram, Wardha-442001, India'], 'affiliations': [{'raw_affiliation_string': 'Department of Computer Engg., BDCE Sewagram, Wardha-442001, India', 'institution_ids': []}]}], 'institution_assertions': [], 'countries_distinct_count': 1, 'institutions_distinct_count': 0, 'corresponding_author_ids': [], 'corresponding_institution_ids': [], 'apc_list': None, 'apc_paid': None, 'fwci': 0.414, 'has_fulltext': True, 'fulltext_origin': 'ngrams', 'cited_by_count': 5, 'citation_normalized_percentile': {'value': 0.502588, 'is_in_top_1_percent': False, 'is_in_top_10_percent': False}, 'cited_by_percentile_year': {'min': 81, 'max': 82}, 'biblio': {'volume': None, 'issue': None, 'first_page': '1', 'last_page': '4'}, '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/T11478', 'display_name': 'Caching and Content Delivery', 'score': 0.9701, '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'}}, {'id': 'https://openalex.org/T11269', 'display_name': 'Algorithms and Data Compression', 'score': 0.9682, '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'}}], 'keywords': [{'id': 'https://openalex.org/keywords/data-extraction', 'display_name': 'Data extraction', 'score': 0.5315428}, {'id': 'https://openalex.org/keywords/similarity', 'display_name': 'Similarity (geometry)', 'score': 0.4699704}], 'concepts': [{'id': 'https://openalex.org/C41008148', 'wikidata': 'https://www.wikidata.org/wiki/Q21198', 'display_name': 'Computer science', 'level': 0, 'score': 0.8624783}, {'id': 'https://openalex.org/C23123220', 'wikidata': 'https://www.wikidata.org/wiki/Q816826', 'display_name': 'Information retrieval', 'level': 1, 'score': 0.62718}, {'id': 'https://openalex.org/C2777466982', 'wikidata': 'https://www.wikidata.org/wiki/Q5227287', 'display_name': 'Data extraction', 'level': 3, 'score': 0.5315428}, {'id': 'https://openalex.org/C21959979', 'wikidata': 'https://www.wikidata.org/wiki/Q36774', 'display_name': 'Web page', 'level': 2, 'score': 0.5109776}, {'id': 'https://openalex.org/C110875604', 'wikidata': 'https://www.wikidata.org/wiki/Q75', 'display_name': 'The Internet', 'level': 2, 'score': 0.5036616}, {'id': 'https://openalex.org/C103278499', 'wikidata': 'https://www.wikidata.org/wiki/Q254465', 'display_name': 'Similarity (geometry)', 'level': 3, 'score': 0.4699704}, {'id': 'https://openalex.org/C118689300', 'wikidata': 'https://www.wikidata.org/wiki/Q7978614', 'display_name': 'Web query classification', 'level': 4, 'score': 0.4654029}, {'id': 'https://openalex.org/C124101348', 'wikidata': 'https://www.wikidata.org/wiki/Q172491', 'display_name': 'Data mining', 'level': 1, 'score': 0.46157727}, {'id': 'https://openalex.org/C164120249', 'wikidata': 'https://www.wikidata.org/wiki/Q995982', 'display_name': 'Web search query', 'level': 3, 'score': 0.410432}, {'id': 'https://openalex.org/C77088390', 'wikidata': 'https://www.wikidata.org/wiki/Q8513', 'display_name': 'Database', 'level': 1, 'score': 0.3599385}, {'id': 'https://openalex.org/C136764020', 'wikidata': 'https://www.wikidata.org/wiki/Q466', 'display_name': 'World Wide Web', 'level': 1, 'score': 0.32164496}, {'id': 'https://openalex.org/C97854310', 'wikidata': 'https://www.wikidata.org/wiki/Q19541', 'display_name': 'Search engine', 'level': 2, 'score': 0.2093383}, {'id': 'https://openalex.org/C154945302', 'wikidata': 'https://www.wikidata.org/wiki/Q11660', 'display_name': 'Artificial intelligence', 'level': 1, 'score': 0.08268389}, {'id': 'https://openalex.org/C115961682', 'wikidata': 'https://www.wikidata.org/wiki/Q860623', 'display_name': 'Image (mathematics)', 'level': 2, '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/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://doi.org/10.1109/iciiecs.2015.7193044', 'pdf_url': None, 'source': None, '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': 17, 'referenced_works': ['https://openalex.org/W2015551056', 'https://openalex.org/W2069388662', 'https://openalex.org/W2104086170', 'https://openalex.org/W2122282348', 'https://openalex.org/W2128341918', 'https://openalex.org/W2133669904', 'https://openalex.org/W2134150392', 'https://openalex.org/W2139599797', 'https://openalex.org/W2143309843', 'https://openalex.org/W2168358004', 'https://openalex.org/W2186691091', 'https://openalex.org/W2187259317', 'https://openalex.org/W2329504021', 'https://openalex.org/W2338630521', 'https://openalex.org/W4232071090', 'https://openalex.org/W4233962457', 'https://openalex.org/W4285719527'], 'related_works': ['https://openalex.org/W3114052401', 'https://openalex.org/W2901901036', 'https://openalex.org/W2330073594', 'https://openalex.org/W2163573236', 'https://openalex.org/W2124814993', 'https://openalex.org/W2096359267', 'https://openalex.org/W2093300859', 'https://openalex.org/W2026738364', 'https://openalex.org/W2013069866', 'https://openalex.org/W1521725692'], 'abstract_inverted_index': {'Based': [0], 'on': [1], 'the': [2, 15, 55, 93], 'query': [3, 10, 77], 'entered': [4], 'by': [5], 'user': [6], 'web': [7, 38], 'databases': [8], 'generate': [9], 'result': [11, 20], 'pages.': [12], 'To': [13], 'extract': [14, 45], 'data': [16, 30, 46, 65, 71, 83, 101], 'from': [17, 72, 102], 'these': [18], 'generated': [19], 'pages': [21], 'automatically': [22], 'is': [23, 95], 'very': [24, 115], 'useful': [25], 'for': [26, 64], 'various': [27], 'applications,': [28], 'like': [29], 'integration,': [31], 'which': [32, 78], 'need': [33], 'to': [34, 44, 75, 96, 117], 'work': [35], 'with': [36], 'different': [37, 119], 'databases.': [39], 'Many': [40], 'techniques': [41], 'are': [42], 'available': [43], 'and': [47, 67, 84, 104], 'align': [48, 105], 'it': [49, 85, 103, 106, 112], 'but': [50], 'they': [51], 'did': [52], 'not': [53], 'consider': [54], 'unstructured': [56, 89], 'data.': [57, 120], 'This': [58], 'paper': [59], 'presents': [60], 'a': [61], 'novel': [62], 'technique': [63], 'extraction': [66], 'alignment.': [68], 'It': [69], 'collects': [70], 'internet': [73], 'related': [74], "user's": [76], 'contains': [79], 'huge': [80], 'amount': [81], 'of': [82], 'can': [86], 'be': [87, 114], 'in': [88, 107], 'form': [90, 109], 'also.': [91], 'Here': [92], 'aim': [94], 'find': [97], 'out': [98], 'only': [99], 'important': [100], 'tabular': [108], 'so': [110], 'that': [111], 'will': [113], 'easy': [116], 'compare': [118]}, 'cited_by_api_url': 'https://api.openalex.org/works?filter=cites:W1585432388', 'counts_by_year': [{'year': 2020, 'cited_by_count': 3}, {'year': 2018, 'cited_by_count': 1}, {'year': 2016, 'cited_by_count': 1}], 'updated_date': '2024-12-11T11:34:16.565954', 'created_date': '2016-06-24'}