{"id":"https://openalex.org/W1969183489","doi":"https://doi.org/10.1145/1324185.1324190","title":"Overview and semantic issues of text mining","display_name":"Overview and semantic issues of text mining","publication_year":2007,"publication_date":"2007-09-01","ids":{"openalex":"https://openalex.org/W1969183489","doi":"https://doi.org/10.1145/1324185.1324190","mag":"1969183489"},"language":"en","primary_location":{"id":"doi:10.1145/1324185.1324190","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1324185.1324190","pdf_url":null,"source":{"id":"https://openalex.org/S47508943","display_name":"ACM SIGMOD Record","issn_l":"0163-5808","issn":["0163-5808","1943-5835"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGMOD Record","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064566826","display_name":"Anna Stavrianou","orcid":null},"institutions":[{"id":"https://openalex.org/I188626449","display_name":"Universit\u00e9 Lumi\u00e8re Lyon 2","ror":"https://ror.org/03rth4p18","country_code":"FR","type":"education","lineage":["https://openalex.org/I188626449","https://openalex.org/I203339264"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Anna Stavrianou","raw_affiliation_strings":["Universit\u00e9 Lumi\u00e8re Lyon2, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Lumi\u00e8re Lyon2, France","institution_ids":["https://openalex.org/I188626449"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000377124","display_name":"Periklis Andritsos","orcid":null},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Periklis Andritsos","raw_affiliation_strings":["University of Trento, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Trento, Italy","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041229251","display_name":"Nicolas Nicoloyannis","orcid":null},"institutions":[{"id":"https://openalex.org/I188626449","display_name":"Universit\u00e9 Lumi\u00e8re Lyon 2","ror":"https://ror.org/03rth4p18","country_code":"FR","type":"education","lineage":["https://openalex.org/I188626449","https://openalex.org/I203339264"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nicolas Nicoloyannis","raw_affiliation_strings":["Universit\u00e9 Lumi\u00e8re Lyon2, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Lumi\u00e8re Lyon2, France","institution_ids":["https://openalex.org/I188626449"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.2972,"has_fulltext":false,"cited_by_count":149,"citation_normalized_percentile":{"value":0.9608499,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":"36","issue":"3","first_page":"23","last_page":"34"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9994999766349792,"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/T10028","display_name":"Topic Modeling","score":0.9991999864578247,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9984999895095825,"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/computer-science","display_name":"Computer science","score":0.8660222291946411},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.7389489412307739},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5795486569404602},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5273034572601318},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.5013782978057861},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.49785685539245605},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4860828220844269},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4736802875995636},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4226214587688446},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.420515239238739},{"id":"https://openalex.org/keywords/concept-mining","display_name":"Concept mining","score":0.4192020893096924},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34027987718582153},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2987246513366699},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.14223849773406982}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8660222291946411},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.7389489412307739},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5795486569404602},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5273034572601318},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.5013782978057861},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.49785685539245605},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4860828220844269},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4736802875995636},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4226214587688446},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.420515239238739},{"id":"https://openalex.org/C176775163","wikidata":"https://www.wikidata.org/wiki/Q5158396","display_name":"Concept mining","level":4,"score":0.4192020893096924},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34027987718582153},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2987246513366699},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.14223849773406982},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C35578498","wikidata":"https://www.wikidata.org/wiki/Q193424","display_name":"Web service","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"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/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":2,"locations":[{"id":"doi:10.1145/1324185.1324190","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1324185.1324190","pdf_url":null,"source":{"id":"https://openalex.org/S47508943","display_name":"ACM SIGMOD Record","issn_l":"0163-5808","issn":["0163-5808","1943-5835"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGMOD Record","raw_type":"journal-article"},{"id":"pmh:oai:iris.unitn.it:11572/70382","is_oa":false,"landing_page_url":"http://hdl.handle.net/11572/70382","pdf_url":null,"source":{"id":"https://openalex.org/S4306401913","display_name":"Institutional Research Information System (Universit\u00e0 degli Studi di Trento)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193223587","host_organization_name":"University of Trento","host_organization_lineage":["https://openalex.org/I193223587"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8500000238418579,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":87,"referenced_works":["https://openalex.org/W41401133","https://openalex.org/W69295931","https://openalex.org/W108101778","https://openalex.org/W182379871","https://openalex.org/W252892187","https://openalex.org/W291570921","https://openalex.org/W312068707","https://openalex.org/W1484719069","https://openalex.org/W1531437147","https://openalex.org/W1540371141","https://openalex.org/W1569415500","https://openalex.org/W1569835270","https://openalex.org/W1574025516","https://openalex.org/W1574901103","https://openalex.org/W1576676390","https://openalex.org/W1600320866","https://openalex.org/W1659833910","https://openalex.org/W1668989518","https://openalex.org/W1687743765","https://openalex.org/W1755193636","https://openalex.org/W1793885322","https://openalex.org/W1796329685","https://openalex.org/W1836291798","https://openalex.org/W1880262756","https://openalex.org/W1951269370","https://openalex.org/W1970516776","https://openalex.org/W1986386500","https://openalex.org/W1986398135","https://openalex.org/W1987947967","https://openalex.org/W1988931981","https://openalex.org/W1995875735","https://openalex.org/W1999912290","https://openalex.org/W2005422315","https://openalex.org/W2024030746","https://openalex.org/W2035716223","https://openalex.org/W2037603696","https://openalex.org/W2044434631","https://openalex.org/W2045638733","https://openalex.org/W2069140227","https://openalex.org/W2071736301","https://openalex.org/W2095296624","https://openalex.org/W2097106271","https://openalex.org/W2100873065","https://openalex.org/W2101210369","https://openalex.org/W2103318667","https://openalex.org/W2107434887","https://openalex.org/W2108126629","https://openalex.org/W2116266212","https://openalex.org/W2117805756","https://openalex.org/W2118020653","https://openalex.org/W2121940249","https://openalex.org/W2123982464","https://openalex.org/W2126502509","https://openalex.org/W2129706127","https://openalex.org/W2130127430","https://openalex.org/W2135437125","https://openalex.org/W2140613126","https://openalex.org/W2140735141","https://openalex.org/W2142151675","https://openalex.org/W2144949988","https://openalex.org/W2145296344","https://openalex.org/W2147880316","https://openalex.org/W2149041454","https://openalex.org/W2151398303","https://openalex.org/W2152183901","https://openalex.org/W2163915185","https://openalex.org/W2165612380","https://openalex.org/W2166418248","https://openalex.org/W2166706824","https://openalex.org/W2168625136","https://openalex.org/W2170654002","https://openalex.org/W2172251087","https://openalex.org/W2199803028","https://openalex.org/W2313512640","https://openalex.org/W2435251607","https://openalex.org/W2949496004","https://openalex.org/W2979401726","https://openalex.org/W3003709066","https://openalex.org/W3006084460","https://openalex.org/W4235264713","https://openalex.org/W4248426528","https://openalex.org/W4285719527","https://openalex.org/W6632223008","https://openalex.org/W6637993692","https://openalex.org/W6676317349","https://openalex.org/W6769430610","https://openalex.org/W6808511818"],"related_works":["https://openalex.org/W4386014872","https://openalex.org/W4361193986","https://openalex.org/W1847536016","https://openalex.org/W3149094754","https://openalex.org/W2114797768","https://openalex.org/W2380654781","https://openalex.org/W2176214140","https://openalex.org/W2516873349","https://openalex.org/W1990601549","https://openalex.org/W3202296815"],"abstract_inverted_index":{"Text":[0],"mining":[1,22],"refers":[2],"to":[3,29,42],"the":[4,20,30,48,60,66,79],"discovery":[5],"of":[6,32],"previously":[7],"unknown":[8],"knowledge":[9],"that":[10],"can":[11],"be":[12],"found":[13],"in":[14,37,65],"text":[15,21,81],"collections.":[16],"In":[17],"recent":[18],"years,":[19],"field":[23],"has":[24],"received":[25],"great":[26],"attention":[27],"due":[28],"abundance":[31],"textual":[33],"data.":[34],"A":[35],"researcher":[36],"this":[38],"area":[39],"is":[40],"requested":[41],"cope":[43],"with":[44,59],"issues":[45,57],"originating":[46],"from":[47],"natural":[49],"language":[50],"particularities.":[51],"This":[52],"survey":[53],"discusses":[54],"such":[55],"semantic":[56],"along":[58],"approaches":[61],"and":[62,75,86],"methodologies":[63],"proposed":[64],"existing":[67],"literature.":[68],"It":[69],"covers":[70],"syntactic":[71],"matters,":[72],"tokenization":[73],"concerns":[74],"it":[76],"focuses":[77],"on":[78],"different":[80],"representation":[82],"techniques,":[83],"categorisation":[84],"tasks":[85],"similarity":[87],"measures":[88],"suggested.":[89]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":16},{"year":2016,"cited_by_count":12},{"year":2015,"cited_by_count":14},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":10}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2016-06-24T00:00:00"}
