{"id":"https://openalex.org/W2182051441","doi":"https://doi.org/10.1109/ic3.2015.7346657","title":"Leveraging probabilistic segmentation to document clustering","display_name":"Leveraging probabilistic segmentation to document clustering","publication_year":2015,"publication_date":"2015-08-01","ids":{"openalex":"https://openalex.org/W2182051441","doi":"https://doi.org/10.1109/ic3.2015.7346657","mag":"2182051441"},"language":"en","primary_location":{"id":"doi:10.1109/ic3.2015.7346657","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ic3.2015.7346657","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 Eighth International Conference on Contemporary Computing (IC3)","raw_type":"proceedings-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/A5047814632","display_name":"Arko Banerjee","orcid":"https://orcid.org/0000-0002-6432-9601"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Arko Banerjee","raw_affiliation_strings":["College of Engineering and Management, Kolaghat"],"affiliations":[{"raw_affiliation_string":"College of Engineering and Management, Kolaghat","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5047814632"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0940337,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"19","issue":null,"first_page":"82","last_page":"87"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9962000250816345,"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/document-clustering","display_name":"Document clustering","score":0.7644578218460083},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7541740536689758},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7279446125030518},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6110762357711792},{"id":"https://openalex.org/keywords/vector-space-model","display_name":"Vector space model","score":0.5917066335678101},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5515326857566833},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5270251035690308},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5045617818832397},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4890526235103607},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.45862218737602234},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3737780451774597},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3548586964607239},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34531891345977783}],"concepts":[{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.7644578218460083},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7541740536689758},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7279446125030518},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6110762357711792},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.5917066335678101},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5515326857566833},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5270251035690308},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5045617818832397},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4890526235103607},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45862218737602234},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3737780451774597},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3548586964607239},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34531891345977783},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ic3.2015.7346657","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ic3.2015.7346657","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 Eighth International Conference on Contemporary Computing (IC3)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W177043487","https://openalex.org/W1595656981","https://openalex.org/W1922658394","https://openalex.org/W1931602579","https://openalex.org/W1975946664","https://openalex.org/W2066680326","https://openalex.org/W2087962968","https://openalex.org/W2100958137","https://openalex.org/W2105686649","https://openalex.org/W2107887685","https://openalex.org/W2121947440","https://openalex.org/W2121996546","https://openalex.org/W2135611423","https://openalex.org/W2137763598","https://openalex.org/W2140156730","https://openalex.org/W4247619421","https://openalex.org/W4285719527","https://openalex.org/W6607108854","https://openalex.org/W6640134229","https://openalex.org/W6676180653"],"related_works":["https://openalex.org/W1500125366","https://openalex.org/W2348461053","https://openalex.org/W2551770406","https://openalex.org/W2137763598","https://openalex.org/W1557970708","https://openalex.org/W2611108488","https://openalex.org/W1575842006","https://openalex.org/W2150620883","https://openalex.org/W2029157577","https://openalex.org/W2798105344"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"a":[3,14,55,64],"novel":[4],"approach":[5],"to":[6,60],"document":[7,16,38,51,76],"clustering":[8,77],"has":[9],"been":[10],"introduced":[11],"by":[12],"defining":[13],"representative-based":[15],"similarity":[17,52],"model":[18,71],"that":[19,31,72],"performs":[20],"probabilistic":[21],"segmentation":[22],"of":[23,36,45,67,75],"documents":[24],"into":[25],"chunks.":[26],"The":[27,48],"frequently":[28],"occuring":[29],"chunks":[30],"are":[32],"considered":[33],"as":[34],"representatives":[35],"the":[37,61,68],"set,":[39],"may":[40],"represent":[41],"phrases":[42],"or":[43],"stem":[44],"true":[46],"words.":[47],"representative":[49],"based":[50],"model,":[53],"containing":[54],"term-document":[56],"matrix":[57],"with":[58],"respect":[59],"representatives,":[62],"is":[63],"compact":[65],"representation":[66],"vector":[69],"space":[70],"improves":[73],"quality":[74],"over":[78],"traditional":[79],"methods.":[80]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}