{"id":"https://openalex.org/W7099345969","doi":null,"title":"Proc. of the 27th European Conference on Information Retrieval. c\u25cbSpringer-Verlag On Compression-Based Text Classification","display_name":"Proc. of the 27th European Conference on Information Retrieval. c\u25cbSpringer-Verlag On Compression-Based Text Classification","publication_year":2012,"publication_date":"2012-03-15","ids":{"openalex":"https://openalex.org/W7099345969"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.214.6088","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.214.6088","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cis.poly.edu/hstein/pubs/ecir.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5048736402","display_name":"Yuval Marton","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuval Marton","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ning Wu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ning Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5039703362","display_name":"Lisa Hellerstein","orcid":"https://orcid.org/0000-0002-3743-7965","observed_orcids":["https://orcid.org/0000-0002-3743-7965"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lisa Hellerstein","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.55598485,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9574999809265137,"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":0.9574999809265137,"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/T11269","display_name":"Algorithms and Data Compression","score":0.033399999141693115,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.0015999999595806003,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/word-stems","display_name":"word stems","score":0.5040000081062317},{"id":"https://openalex.org/keywords/punctuation","display_name":"punctuation","score":0.8209999799728394},{"id":"https://openalex.org/keywords/english-text-classification","display_name":"English text classification","score":0.7360000014305115},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"feature extraction","score":0.34200000762939453}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7358999848365784},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6933000087738037},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.517799973487854},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.48019999265670776},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4767000079154968},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.4036000072956085},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.37290000915527344},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3400000035762787},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3181000053882599},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29510000348091125},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.214.6088","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.214.6088","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cis.poly.edu/hstein/pubs/ecir.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1953638699","https://openalex.org/W4385374404","https://openalex.org/W2075137335","https://openalex.org/W7096752494","https://openalex.org/W2914347887","https://openalex.org/W2233871464","https://openalex.org/W2171886309","https://openalex.org/W2957513783","https://openalex.org/W2330980273","https://openalex.org/W2141689816"],"abstract_inverted_index":{"Abstract.":[0],"Compression-based":[1],"text":[2,83,109],"classification":[3,47,84],"methods":[4,18,48,60,85,111],"are":[5,19,61,92],"easy":[6],"to":[7,26,74,96,101,112],"apply,":[8],"requiring":[9],"virtually":[10],"no":[11],"preprocessing":[12],"of":[13,31,68,71,80],"the":[14,24,66,76,99],"data.":[15],"Most":[16],"such":[17,34,59],"character-based,":[20],"and":[21,38,56,78],"thus":[22],"have":[23,49],"potential":[25],"automatically":[27],"capture":[28,102],"non-word":[29,103],"features":[30,39,106],"a":[32,69],"document,":[33],"as":[35,52],"punctuation,":[36],"wordstems,":[37],"spanning":[40],"more":[41,114],"than":[42],"one":[43],"word.":[44],"However,":[45],"compressionbased":[46],"drawbacks":[50],"(such":[51],"slow":[53],"running":[54],"time),":[55],"not":[57],"all":[58],"equally":[62],"effective.":[63],"We":[64],"present":[65],"results":[67],"number":[70],"experiments":[72,91],"designed":[73,95],"evaluate":[75],"effectiveness":[77],"behavior":[79],"different":[81],"compression-based":[82],"on":[86],"English":[87],"text.":[88],"Among":[89],"our":[90],"some":[93],"specifically":[94],"test":[97],"whether":[98],"ability":[100],"(including":[104],"super-word)":[105],"causes":[107],"character-based":[108],"compression":[110],"achieve":[113],"accurate":[115],"classification.":[116],"1":[117]},"counts_by_year":[],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2025-10-27T00:00:00"}