{"id":"https://openalex.org/W2112518893","doi":"https://doi.org/10.1109/iri.2007.4296660","title":"Comparative Analysis of Different Text Segmentation Algorithms on Arabic News Stories","display_name":"Comparative Analysis of Different Text Segmentation Algorithms on Arabic News Stories","publication_year":2007,"publication_date":"2007-08-01","ids":{"openalex":"https://openalex.org/W2112518893","doi":"https://doi.org/10.1109/iri.2007.4296660","mag":"2112518893"},"language":"en","primary_location":{"id":"doi:10.1109/iri.2007.4296660","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iri.2007.4296660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE International Conference on Information Reuse and Integration","raw_type":"proceedings-article"},"type":"conference-paper","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/A5028318124","display_name":"Michael A. El-Shayeb","orcid":null},"institutions":[{"id":"https://openalex.org/I145487455","display_name":"Cairo University","ror":"https://ror.org/03q21mh05","country_code":"EG","type":"education","lineage":["https://openalex.org/I145487455"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Michael A. El-Shayeb","raw_affiliation_strings":["Computer Science Department, Faculty of Computers and Information, Cairo University, Giza, Egypt","Cairo Univ., Cairo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Faculty of Computers and Information, Cairo University, Giza, Egypt","institution_ids":["https://openalex.org/I145487455"]},{"raw_affiliation_string":"Cairo Univ., Cairo","institution_ids":["https://openalex.org/I145487455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086805519","display_name":"Samhaa R. El-Beltagy","orcid":"https://orcid.org/0000-0002-5769-8054"},"institutions":[{"id":"https://openalex.org/I145487455","display_name":"Cairo University","ror":"https://ror.org/03q21mh05","country_code":"EG","type":"education","lineage":["https://openalex.org/I145487455"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Samhaa R. El-Beltagy","raw_affiliation_strings":["Computer Science Department, Faculty of Computers and Information, Cairo University, Giza, Egypt","Cairo Univ., Cairo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Faculty of Computers and Information, Cairo University, Giza, Egypt","institution_ids":["https://openalex.org/I145487455"]},{"raw_affiliation_string":"Cairo Univ., Cairo","institution_ids":["https://openalex.org/I145487455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058725522","display_name":"Ahmed Rafea","orcid":"https://orcid.org/0000-0001-8109-1845"},"institutions":[{"id":"https://openalex.org/I80693520","display_name":"American University in Cairo","ror":"https://ror.org/0176yqn58","country_code":"EG","type":"education","lineage":["https://openalex.org/I80693520"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Ahmed Rafea","raw_affiliation_strings":["Computer Science Department, American University, Cairo, Cairo, Egypt","Computer Science Department, American University, Cairo, Cairo, Egypt. rafea@aucegypt.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, American University, Cairo, Cairo, Egypt","institution_ids":["https://openalex.org/I80693520"]},{"raw_affiliation_string":"Computer Science Department, American University, Cairo, Cairo, Egypt. rafea@aucegypt.edu","institution_ids":["https://openalex.org/I80693520"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"23","issue":null,"first_page":"441","last_page":"446"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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":0.9983000159263611,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9959999918937683,"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/arabic","display_name":"Arabic","score":0.8093391060829163},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7973237633705139},{"id":"https://openalex.org/keywords/lagging","display_name":"Lagging","score":0.6805948615074158},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6776771545410156},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.64287269115448},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.6262569427490234},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6007950901985168},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5747262239456177},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5091566443443298},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4149775803089142},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34471914172172546},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.18363651633262634},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0980684757232666},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08667248487472534}],"concepts":[{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.8093391060829163},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7973237633705139},{"id":"https://openalex.org/C2776962539","wikidata":"https://www.wikidata.org/wiki/Q6472078","display_name":"Lagging","level":2,"score":0.6805948615074158},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6776771545410156},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.64287269115448},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.6262569427490234},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6007950901985168},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5747262239456177},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5091566443443298},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4149775803089142},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34471914172172546},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18363651633262634},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0980684757232666},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08667248487472534},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iri.2007.4296660","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iri.2007.4296660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE International Conference on Information Reuse and Integration","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1557074680","https://openalex.org/W1573514622","https://openalex.org/W1604285433","https://openalex.org/W1606942729","https://openalex.org/W1626945812","https://openalex.org/W1710422233","https://openalex.org/W1828401780","https://openalex.org/W1837399425","https://openalex.org/W1994448786","https://openalex.org/W2048978997","https://openalex.org/W2080179128","https://openalex.org/W2106918957","https://openalex.org/W2159083595","https://openalex.org/W2161775468","https://openalex.org/W3037715718","https://openalex.org/W4238205294","https://openalex.org/W6634065907","https://openalex.org/W6636413279","https://openalex.org/W6636660855","https://openalex.org/W6638575021","https://openalex.org/W6639001170","https://openalex.org/W6780672502"],"related_works":["https://openalex.org/W2135562825","https://openalex.org/W1522196789","https://openalex.org/W2978383222","https://openalex.org/W2172629291","https://openalex.org/W2380773642","https://openalex.org/W2384559435","https://openalex.org/W2337707338","https://openalex.org/W2058548953","https://openalex.org/W2785359773","https://openalex.org/W2362013696"],"abstract_inverted_index":{"The":[0,83],"task":[1,23],"of":[2,45,92,94,106,116,131],"text":[3,30,48],"segmentation":[4,31,49,126],"represents":[5],"an":[6,72],"important":[7],"step":[8],"in":[9,85,128,133],"many":[10],"applications":[11],"and":[12,78],"while":[13],"much":[14],"work":[15,28,84],"has":[16],"been":[17],"carried":[18],"out":[19],"to":[20,100,123],"address":[21],"this":[22,40,86],"for":[24,32],"the":[25,79,107,129],"English":[26],"language,":[27],"on":[29,51,64,71],"other":[33],"languages":[34],"is":[35,55],"still":[36],"lagging":[37],"behind.":[38],"In":[39],"paper":[41,87],"a":[42,90,114],"comparative":[43],"analysis":[44],"three":[46],"different":[47],"algorithms":[50,96],"Arabic":[52,65,73,134],"news":[53,66,75,136],"stories":[54],"presented.":[56],"To":[57],"assess":[58],"how":[59],"well":[60],"each":[61,68],"algorithm":[62],"works":[63],"stories,":[67],"was":[69,98],"applied":[70],"Reuters":[74],"story":[76],"dataset":[77],"results":[80,103],"were":[81,121],"compared.":[82],"also":[88,112],"describes":[89],"combination":[91],"two":[93],"these":[95],"that":[97,120],"found":[99,122],"produce":[101],"better":[102],"than":[104],"any":[105],"presented":[108],"individual":[109],"algorithms.":[110],"It":[111],"presents":[113],"set":[115],"error":[117],"reduction":[118],"filters":[119],"significantly":[124],"reduce":[125],"errors":[127],"detection":[130],"borders":[132],"based":[135],"stories.":[137]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
