{"id":"https://openalex.org/W2001797864","doi":"https://doi.org/10.5220/0005101803000307","title":"Web Content Classification based on Topic and Sentiment Analysis of Text","display_name":"Web Content Classification based on Topic and Sentiment Analysis of Text","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2001797864","doi":"https://doi.org/10.5220/0005101803000307","mag":"2001797864"},"language":"en","primary_location":{"id":"doi:10.5220/0005101803000307","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0005101803000307","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Knowledge Discovery and Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0005101803000307","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109309339","display_name":"Shuhua Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I198445264","display_name":"Arcada University of Applied Sciences","ror":"https://ror.org/02s466x84","country_code":"FI","type":"education","lineage":["https://openalex.org/I198445264"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Shuhua Liu","raw_affiliation_strings":["Arcada University of Applied Sciences, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arcada University of Applied Sciences, Finland","institution_ids":["https://openalex.org/I198445264"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029109348","display_name":"Thomas Forss","orcid":null},"institutions":[{"id":"https://openalex.org/I198445264","display_name":"Arcada University of Applied Sciences","ror":"https://ror.org/02s466x84","country_code":"FI","type":"education","lineage":["https://openalex.org/I198445264"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Thomas Forss","raw_affiliation_strings":["Arcada University of Applied Sciences, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arcada University of Applied Sciences, Finland","institution_ids":["https://openalex.org/I198445264"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.15570791,"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":"300","last_page":"307"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9941999912261963,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9941999912261963,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9854000210762024,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9800000190734863,"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/computer-science","display_name":"Computer science","score":0.793481707572937},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.5468997955322266},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5142214298248291},{"id":"https://openalex.org/keywords/web-content","display_name":"Web content","score":0.4901729226112366},{"id":"https://openalex.org/keywords/sentiment-analysis","display_name":"Sentiment analysis","score":0.45345330238342285},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41320565342903137},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3995201587677002},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34099507331848145},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.2833995223045349},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0612851083278656}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.793481707572937},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.5468997955322266},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5142214298248291},{"id":"https://openalex.org/C2776324614","wikidata":"https://www.wikidata.org/wiki/Q3948731","display_name":"Web content","level":3,"score":0.4901729226112366},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.45345330238342285},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41320565342903137},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3995201587677002},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34099507331848145},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.2833995223045349},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0612851083278656},{"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:10.5220/0005101803000307","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0005101803000307","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Knowledge Discovery and Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.5220/0005101803000307","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0005101803000307","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Knowledge Discovery and Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.75,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2548633793","https://openalex.org/W3089396779","https://openalex.org/W2596247554","https://openalex.org/W4301373556","https://openalex.org/W2464413305","https://openalex.org/W4249299808","https://openalex.org/W2163230867","https://openalex.org/W4307079979","https://openalex.org/W275430299","https://openalex.org/W1484163267"],"abstract_inverted_index":{"Automatic":[0],"classification":[1,166],"of":[2,23,29,35,46,107,124,186],"web":[3,36,47,87,108,144,174,187],"content":[4,31,67,145],"has":[5,41],"been":[6],"studied":[7],"extensively,":[8],"using":[9],"different":[10,16,20],"learning":[11],"methods":[12],"and":[13,32,55,68,97,104,118,160,181,190],"tools,":[14],"investigating":[15],"datasets":[17],"to":[18,60,101,143,183],"serve":[19],"purposes.":[21],"Most":[22],"the":[24,30,134,165,184],"studies":[25],"have":[26],"made":[27],"use":[28],"structural":[33,69],"features":[34,70,162],"pages.":[37,109],"However,":[38],"previous":[39],"experience":[40],"shown":[42],"that":[43,52,132],"certain":[44],"groups":[45],"pages,":[48],"such":[49],"as":[50],"those":[51],"contain":[53],"hatred":[54],"violence,":[56],"are":[57,71,163],"much":[58,140],"harder":[59],"classify":[61],"with":[62],"good":[63],"accuracy":[64],"when":[65,157],"both":[66],"already":[72],"taken":[73],"into":[74,89],"consideration.":[75],"In":[76],"this":[77],"study":[78,177],"we":[79],"present":[80],"a":[81],"new":[82],"approach":[83],"for":[84,172],"automatically":[85],"classifying":[86],"pages":[88],"pre-defined":[90],"topic":[91,103,117,158],"categories.":[92,175],"We":[93,110],"apply":[94],"text":[95],"summarization":[96],"sentiment":[98,105,119,135,161],"analysis":[99],"techniques":[100],"extract":[102],"indicators":[106],"then":[111],"build":[112],"classifiers":[113,150],"based":[114,149],"on":[115],"combined":[116],"features.":[120],"A":[121],"large":[122],"amount":[123],"experiments":[125],"were":[126],"carried":[127],"out.":[128],"Our":[129,176],"results":[130],"suggest":[131],"incorporating":[133],"dimension":[136],"can":[137],"indeed":[138],"bring":[139],"added":[141],"value":[142],"classification.":[146],"Topic":[147],"similarity":[148,159],"solely":[151],"did":[152],"not":[153],"perform":[154],"well,":[155],"but":[156],"combined,":[164],"model":[167],"performance":[168],"is":[169],"significantly":[170],"improved":[171],"many":[173],"offers":[178],"valuable":[179],"insights":[180],"inputs":[182],"development":[185],"detection":[188],"systems":[189],"Internet":[191],"safety":[192],"solutions.":[193]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}