{"id":"https://openalex.org/W3136290693","doi":"https://doi.org/10.1109/ccnc49032.2021.9369599","title":"Machine-Learning directed Article Detection on the Web using DOM and text-based features","display_name":"Machine-Learning directed Article Detection on the Web using DOM and text-based features","publication_year":2021,"publication_date":"2021-01-09","ids":{"openalex":"https://openalex.org/W3136290693","doi":"https://doi.org/10.1109/ccnc49032.2021.9369599","mag":"3136290693"},"language":"en","primary_location":{"id":"doi:10.1109/ccnc49032.2021.9369599","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccnc49032.2021.9369599","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 18th Annual Consumer Communications & Networking Conference (CCNC)","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/A5062353839","display_name":"Shobhit Mathur","orcid":"https://orcid.org/0000-0002-2470-960X"},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shobhit Mathur","raw_affiliation_strings":["Services PF R&D, Samsung R&D Institute-Bangalore,Bangalore,India,560037"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Services PF R&D, Samsung R&D Institute-Bangalore,Bangalore,India,560037","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082842803","display_name":"Pritam Nikam","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pritam Nikam","raw_affiliation_strings":["Services PF R&D, Samsung R&D Institute-Bangalore,Bangalore,India,560037"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Services PF R&D, Samsung R&D Institute-Bangalore,Bangalore,India,560037","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021286026","display_name":"Harshita Patidar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Harshita Patidar","raw_affiliation_strings":["Services PF R&D, Samsung R&D Institute-Bangalore,Bangalore,India,560037"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Services PF R&D, Samsung R&D Institute-Bangalore,Bangalore,India,560037","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044859234","display_name":"Rohan Gaikwad","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rohan Bapusaheb Gaikwad","raw_affiliation_strings":["Services PF R&D, Samsung R&D Institute-Bangalore,Bangalore,India,560037"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Services PF R&D, Samsung R&D Institute-Bangalore,Bangalore,India,560037","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010866188","display_name":"Preeti Narayan Nayak","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Preeti Narayan Nayak","raw_affiliation_strings":["Services PF R&D, Samsung R&D Institute-Bangalore,Bangalore,India,560037"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Services PF R&D, Samsung R&D Institute-Bangalore,Bangalore,India,560037","institution_ids":["https://openalex.org/I4210139030"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.138,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.82096908,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"39","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9995999932289124,"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":0.9995999932289124,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9921000003814697,"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":0.8353173732757568},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.8086119890213013},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.6703661680221558},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.517125129699707},{"id":"https://openalex.org/keywords/false-positive-paradox","display_name":"False positive paradox","score":0.46660682559013367},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4562479257583618},{"id":"https://openalex.org/keywords/web-content","display_name":"Web content","score":0.4254993796348572},{"id":"https://openalex.org/keywords/ajax","display_name":"Ajax","score":0.41649508476257324},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2535616457462311}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8353173732757568},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.8086119890213013},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.6703661680221558},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.517125129699707},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.46660682559013367},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4562479257583618},{"id":"https://openalex.org/C2776324614","wikidata":"https://www.wikidata.org/wiki/Q3948731","display_name":"Web content","level":3,"score":0.4254993796348572},{"id":"https://openalex.org/C504723692","wikidata":"https://www.wikidata.org/wiki/Q134471","display_name":"Ajax","level":3,"score":0.41649508476257324},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2535616457462311},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ccnc49032.2021.9369599","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccnc49032.2021.9369599","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 18th Annual Consumer Communications & Networking Conference (CCNC)","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":13,"referenced_works":["https://openalex.org/W261891563","https://openalex.org/W2096451472","https://openalex.org/W2120101509","https://openalex.org/W2168745915","https://openalex.org/W2295598076","https://openalex.org/W2600746833","https://openalex.org/W2793353489","https://openalex.org/W2946381043","https://openalex.org/W3005880794","https://openalex.org/W3011068143","https://openalex.org/W3102476541","https://openalex.org/W4230172233","https://openalex.org/W6749505818"],"related_works":["https://openalex.org/W2385195715","https://openalex.org/W2120359737","https://openalex.org/W2374659546","https://openalex.org/W1968997488","https://openalex.org/W2897171874","https://openalex.org/W1987716395","https://openalex.org/W2012575882","https://openalex.org/W2544674189","https://openalex.org/W2550808318","https://openalex.org/W4346570"],"abstract_inverted_index":{"Burgeoning":[0],"trend":[1],"of":[2,32,36,43,48,65,121,137,156,163,199,226,231],"digital":[3],"advertising":[4],"have":[5],"led":[6],"websites":[7],"to":[8,27,50,77,101,160,222],"embody":[9],"massive":[10],"irrelevant":[11],"content":[12,38,80,120,170],"such":[13],"as":[14],"page":[15,67,106,124,186],"navigation,":[16],"ads,":[17],"distractions,":[18],"promotional":[19],"videos":[20],"etc\u2025.":[21],"on":[22,133,166,203],"their":[23],"pages.":[24],"In":[25,158],"contrast":[26],"desktop,":[28],"limited":[29],"screen":[30],"space":[31],"mobile":[33],"carrying":[34],"variety":[35],"ineffectual":[37],"magnifies":[39],"the":[40,79,118,122,135,150,197,235,243,250],"visual":[41],"complexity":[42],"webpage":[44],"by":[45,68,112,125,141,180,242],"disrupting":[46],"focus":[47],"user":[49,76],"read":[51,78],"useful":[52],"content.":[53],"To":[54],"solve":[55],"this":[56,217],"issue,":[57],"Reader":[58],"mode":[59,202],"functionality":[60],"renders":[61],"a":[62,104,143,224,229],"clutter-free":[63],"version":[64],"web":[66,105,123,185,207,247],"stripping":[69],"out":[70],"all":[71,127],"insignificant":[72],"elements":[73],"and":[74,188,228],"letting":[75],"they":[81],"are":[82,239],"actually":[83],"interested":[84],"in.":[85],"Existing":[86],"implementation":[87],"in":[88,154,213,249],"our":[89,176],"browser":[90],"involves":[91],"2":[92],"modules":[93],"-":[94],"Article":[95,113],"Detection":[96],"module":[97,115],"that":[98,116,147],"runs":[99],"heuristics":[100,183],"detect":[102],"whether":[103],"is":[107,211],"article":[108,138],"or":[109],"not,":[110],"proceeded":[111],"Extraction":[114],"extracts":[117],"main":[119],"removing":[126],"unwanted":[128],"elements.":[129],"Our":[130,193],"paper":[131],"focusses":[132],"improving":[134],"accuracy":[136],"detection":[139],"logic":[140],"proposing":[142],"machine-learning":[144],"based":[145,246],"solution":[146,178],"significantly":[148],"surpasses":[149],"present":[151],"heuristic-based":[152],"model":[153],"terms":[155],"accuracy.":[157],"order":[159],"get":[161],"rid":[162],"false":[164],"positives":[165],"webpages":[167],"with":[168],"meaningless":[169],"like":[171],"product":[172],"descriptions,":[173],"we":[174,219],"extended":[175],"previous":[177],"[1]":[179],"incorporating":[181],"backward-elimination":[182],"for":[184],"title":[187],"extracting":[189],"strong":[190],"Boolean":[191],"predictors.":[192],"approach":[194],"also":[195],"solves":[196],"problem":[198],"detecting":[200],"reader":[201],"Google's":[204],"AMP":[205],"HTML":[206],"pages":[208],"where":[209],"main-content":[210],"rendered":[212],"an":[214],"iframe.":[215],"With":[216],"model,":[218],"were":[220],"able":[221],"achieve":[223],"precision":[225],"0.99":[227],"recall":[230],"0.94,":[232],"which":[233,238],"outperforms":[234],"state-of-the-art":[236],"techniques":[237],"being":[240],"used":[241],"major":[244],"Android":[245],"browsers":[248],"market":[251],"today.":[252]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}