{"id":"https://openalex.org/W1978764270","doi":"https://doi.org/10.1145/2676723.2693630","title":"Focused Mining of University Course Descriptions from Highly Variable Sources (Abstract Only)","display_name":"Focused Mining of University Course Descriptions from Highly Variable Sources (Abstract Only)","publication_year":2015,"publication_date":"2015-02-24","ids":{"openalex":"https://openalex.org/W1978764270","doi":"https://doi.org/10.1145/2676723.2693630","mag":"1978764270"},"language":"en","primary_location":{"id":"doi:10.1145/2676723.2693630","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2676723.2693630","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th ACM Technical Symposium on Computer Science Education","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/A5087973101","display_name":"Thomas Effland","orcid":null},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Thomas D. Effland","raw_affiliation_strings":["State University of New York at Buffalo, Buffalo, NY, USA","State University of New York at Buffalo , Buffalo , NY , USA"],"affiliations":[{"raw_affiliation_string":"State University of New York at Buffalo, Buffalo, NY, USA","institution_ids":["https://openalex.org/I63190737"]},{"raw_affiliation_string":"State University of New York at Buffalo , Buffalo , NY , USA","institution_ids":["https://openalex.org/I63190737"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5087973101"],"corresponding_institution_ids":["https://openalex.org/I63190737"],"apc_list":null,"apc_paid":null,"fwci":0.7946,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.80528622,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"716","last_page":"716"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9990000128746033,"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/T11122","display_name":"Online Learning and Analytics","score":0.9416999816894531,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T10260","display_name":"Software Engineering Research","score":0.9204999804496765,"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/crawling","display_name":"Crawling","score":0.822553277015686},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.7785496711730957},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7741254568099976},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.7424497604370117},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6882769465446472},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.673883855342865},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.5643055438995361},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.5224006175994873},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.4980738162994385},{"id":"https://openalex.org/keywords/traverse","display_name":"Traverse","score":0.4712541401386261},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.4366302490234375},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.41809749603271484},{"id":"https://openalex.org/keywords/hyperlink","display_name":"Hyperlink","score":0.414273202419281},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4106175899505615},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3694528341293335},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3511340022087097},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.1364598572254181}],"concepts":[{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.822553277015686},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.7785496711730957},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7741254568099976},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.7424497604370117},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6882769465446472},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.673883855342865},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.5643055438995361},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.5224006175994873},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.4980738162994385},{"id":"https://openalex.org/C176809094","wikidata":"https://www.wikidata.org/wiki/Q15401496","display_name":"Traverse","level":2,"score":0.4712541401386261},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.4366302490234375},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.41809749603271484},{"id":"https://openalex.org/C30088001","wikidata":"https://www.wikidata.org/wiki/Q102014","display_name":"Hyperlink","level":3,"score":0.414273202419281},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4106175899505615},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3694528341293335},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3511340022087097},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.1364598572254181},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2676723.2693630","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2676723.2693630","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th ACM Technical Symposium on Computer Science Education","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15"}],"awards":[{"id":"https://openalex.org/G4554347537","display_name":null,"funder_award_id":"NSF-DUE-CCLI-0920335","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3119324922","https://openalex.org/W2352686120","https://openalex.org/W2372594123","https://openalex.org/W2358310581","https://openalex.org/W2026132847","https://openalex.org/W4385695127","https://openalex.org/W2137810919","https://openalex.org/W2964752624","https://openalex.org/W4255854114","https://openalex.org/W2026661369"],"abstract_inverted_index":{"Finding":[0],"topically":[1],"relevant":[2],"content":[3],"from":[4,63,85],"disparate":[5,64],"sources":[6],"on":[7],"the":[8,15,38,97,115],"Web":[9],"requires":[10],"robust":[11],"techniques":[12,94],"due":[13],"to":[14,30,46,55,95,103,131],"variability":[16],"of":[17,26,51,100,122],"sites.":[18],"A":[19],"focused":[20,52],"web":[21,39,86],"crawler":[22,27],"is":[23],"a":[24,48],"type":[25],"that":[28,73,113],"attempts":[29],"make":[31],"predictions":[32],"about":[33],"page":[34,117,127],"relevance":[35,120],"and":[36,57,118,129,137],"traverse":[37],"efficiently.":[40],"In":[41],"this":[42],"work,":[43],"we":[44],"attempt":[45],"design":[47],"novel":[49],"system":[50],"crawling":[53],"tailored":[54],"identifying":[56],"extracting":[58],"semantically":[59],"similar":[60],"topical":[61],"information":[62],"but":[65],"known":[66],"seed":[67],"domains":[68],"with":[69,141],"highly":[70],"variable":[71],"structure":[72],"do":[74],"not":[75],"reference":[76],"each":[77],"other.":[78],"We":[79,88,124],"first":[80],"extract":[81],"rich":[82],"predictive":[83],"features":[84],"pages.":[87],"then":[89],"utilize":[90],"Weakly-Supervised":[91],"Machine":[92],"Learning":[93],"predict":[96],"link":[98],"distance":[99],"current":[101,116],"pages":[102,105,136,140],"target":[104,139],"by":[106],"employing":[107],"two":[108],"separate":[109],"Random":[110],"Forest":[111],"classifiers":[112],"rank":[114],"potential":[119],"gain":[121],"hyper-links.":[123],"use":[125],"these":[126],"representations":[128],"rankings":[130],"efficiently":[132],"tunnel":[133],"through":[134],"irrelevant":[135],"reach":[138],"more":[142],"optimal":[143],"path":[144],"traversals.":[145]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}