{"id":"https://openalex.org/W4406814904","doi":"https://doi.org/10.1145/3704289.3704294","title":"Clustering students\u2019 text form feedback data: comparison of eight vector space models","display_name":"Clustering students\u2019 text form feedback data: comparison of eight vector space models","publication_year":2024,"publication_date":"2024-09-24","ids":{"openalex":"https://openalex.org/W4406814904","doi":"https://doi.org/10.1145/3704289.3704294"},"language":"en","primary_location":{"id":"doi:10.1145/3704289.3704294","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3704289.3704294","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 7th International Conference on Big Data and Education","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3704289.3704294","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077299041","display_name":"Wilhelmiina H\u00e4m\u00e4l\u00e4inen","orcid":"https://orcid.org/0000-0002-3467-7509"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Wilhelmiina H\u00e4m\u00e4l\u00e4inen","raw_affiliation_strings":["Department of Computer Science, Aalto University, Espoo, Finland"],"raw_orcid":"https://orcid.org/0000-0002-3467-7509","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032252870","display_name":"Jan-Mikael Rybicki","orcid":"https://orcid.org/0000-0002-4112-5657"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Jan-Mikael Rybicki","raw_affiliation_strings":["Language Centre, Aalto University, Espoo, Finland"],"raw_orcid":"https://orcid.org/0000-0002-4112-5657","affiliations":[{"raw_affiliation_string":"Language Centre, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027596822","display_name":"Lauri Malmi","orcid":"https://orcid.org/0000-0003-1064-796X"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Lauri Malmi","raw_affiliation_strings":["Department of Computer Science, Aalto University, Espoo, Finland"],"raw_orcid":"https://orcid.org/0000-0003-1064-796X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006624933","display_name":"Alexander Jung","orcid":"https://orcid.org/0000-0001-7538-0990"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Alex Jung","raw_affiliation_strings":["Department of Computer Science, Aalto University, Espoo, Finland"],"raw_orcid":"https://orcid.org/0000-0001-7538-0990","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081705448","display_name":"Kerttu Pollari-Malmi","orcid":"https://orcid.org/0000-0003-2635-255X"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Kerttu Pollari-Malmi","raw_affiliation_strings":["Department of Computer Science, Aalto University, Espoo, Finland"],"raw_orcid":"https://orcid.org/0000-0003-2635-255X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5077299041"],"corresponding_institution_ids":["https://openalex.org/I9927081"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23487065,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"57","last_page":"64"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9919999837875366,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9919999837875366,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9815999865531921,"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/T10799","display_name":"Data Visualization and Analytics","score":0.9800000190734863,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.787528395652771},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7259084582328796},{"id":"https://openalex.org/keywords/vector-space-model","display_name":"Vector space model","score":0.5748103857040405},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.515796422958374},{"id":"https://openalex.org/keywords/vector-space","display_name":"Vector space","score":0.4635462164878845},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4344659745693207},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39627373218536377},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37203073501586914},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34341806173324585},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18832674622535706},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.07829546928405762}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.787528395652771},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7259084582328796},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.5748103857040405},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.515796422958374},{"id":"https://openalex.org/C13336665","wikidata":"https://www.wikidata.org/wiki/Q125977","display_name":"Vector space","level":2,"score":0.4635462164878845},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4344659745693207},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39627373218536377},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37203073501586914},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34341806173324585},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18832674622535706},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.07829546928405762},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3704289.3704294","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3704289.3704294","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 7th International Conference on Big Data and Education","raw_type":"proceedings-article"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/133843","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/1e277027-9192-4ef2-bd7c-8de874e59a35","pdf_url":null,"source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"publishedVersion"}],"best_oa_location":{"id":"doi:10.1145/3704289.3704294","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3704289.3704294","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 7th International Conference on Big Data and Education","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1614298861","https://openalex.org/W1987262936","https://openalex.org/W2015623780","https://openalex.org/W2027875450","https://openalex.org/W2097645701","https://openalex.org/W2144927428","https://openalex.org/W2165232124","https://openalex.org/W2171040110","https://openalex.org/W2797590686","https://openalex.org/W2910370510","https://openalex.org/W2997591727","https://openalex.org/W3157575185"],"related_works":["https://openalex.org/W2096728994","https://openalex.org/W2349139068","https://openalex.org/W1974406477","https://openalex.org/W3161401723","https://openalex.org/W1540114765","https://openalex.org/W105748137","https://openalex.org/W2391634343","https://openalex.org/W1966027089","https://openalex.org/W2362958218","https://openalex.org/W1883708690"],"abstract_inverted_index":{"Text-form":[0],"student":[1,76],"feedback":[2,18,77],"is":[3,19,63],"an":[4],"indispensable":[5],"source":[6],"of":[7,16,39,49,57,85,133,146],"information":[8],"for":[9,156],"all":[10],"university":[11],"lecturers.":[12],"Since":[13],"manual":[14],"analysis":[15],"such":[17],"laborious,":[20],"it":[21],"has":[22,87,116],"been":[23],"suggested":[24],"that":[25,82],"text":[26,40],"clustering":[27,41,93],"methods":[28],"could":[29,136],"be":[30,125,137],"used":[31],"to":[32],"automate":[33],"the":[34,37,45,83,92,134],"process.":[35],"However,":[36],"success":[38],"depends":[42],"heavily":[43],"on":[44,91,98],"vector":[46,59],"space":[47,60],"presentation":[48],"documents.":[50],"In":[51,111],"this":[52],"paper,":[53],"a":[54,88,117],"comprehensive":[55],"evaluation":[56],"eight":[58],"models":[61,96,108],"(VSMs)":[62],"presented":[64],"in":[65,72],"combination":[66],"with":[67,127,161],"different":[68],"linguistic":[69],"preprocessing":[70],"techniques":[71],"English":[73],"and":[74,100,122],"Finnish":[75],"data.":[78],"The":[79,95,130],"results":[80],"show":[81],"choice":[84],"VSM":[86],"strong":[89],"effect":[90],"performance.":[94],"based":[97],"short":[99],"long":[101],"character":[102],"n-grams":[103,152],"work":[104],"best,":[105],"while":[106,120],"word2vec":[107],"perform":[109],"worst.":[110],"general,":[112],"stop":[113],"word":[114,151],"removal":[115],"positive":[118],"effect,":[119],"stemming":[121],"lemmatization":[123],"may":[124],"detrimental":[126],"many":[128],"VSMs.":[129],"main":[131],"themes":[132],"data":[135],"well":[138,155],"identified":[139],"from":[140],"cluster":[141],"centroids.":[142],"An":[143],"alternative":[144],"approach":[145],"describing":[147],"clusters":[148],"by":[149],"frequent":[150],"worked":[153],"also":[154],"sufficiently":[157],"large,":[158],"distinct":[159],"classes":[160],"clear":[162],"keywords.":[163]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}