{"id":"https://openalex.org/W2103623170","doi":"https://doi.org/10.1145/1390749.1390760","title":"A comparative study of statistical features of language in <i>blogs-vs-splogs</i>","display_name":"A comparative study of statistical features of language in <i>blogs-vs-splogs</i>","publication_year":2008,"publication_date":"2008-07-24","ids":{"openalex":"https://openalex.org/W2103623170","doi":"https://doi.org/10.1145/1390749.1390760","mag":"2103623170"},"language":"en","primary_location":{"id":"doi:10.1145/1390749.1390760","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390749.1390760","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the second workshop on Analytics for noisy unstructured text data","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/A5085653548","display_name":"Soumya Kanti Datta","orcid":"https://orcid.org/0000-0002-3209-0851"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Soumya Datta","raw_affiliation_strings":["Indian Institute of Technology, Kharagpur, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024219981","display_name":"Sudeshna Sarkar","orcid":"https://orcid.org/0000-0003-3439-4282"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sudeshna Sarkar","raw_affiliation_strings":["Indian Institute of Technology, Kharagpur, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5085653548"],"corresponding_institution_ids":["https://openalex.org/I145894827"],"apc_list":null,"apc_paid":null,"fwci":5.0759,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.95296611,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"63","last_page":"66"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9998000264167786,"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":0.9998000264167786,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9958999752998352,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9954000115394592,"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":0.8110146522521973},{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.616629958152771},{"id":"https://openalex.org/keywords/zipfs-law","display_name":"Zipf's law","score":0.5395772457122803},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5387542843818665},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5051766037940979},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.48890557885169983},{"id":"https://openalex.org/keywords/flagging","display_name":"Flagging","score":0.46505436301231384},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4601481556892395},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4305153489112854},{"id":"https://openalex.org/keywords/geolocation","display_name":"Geolocation","score":0.4190915822982788},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2895413637161255},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.23214399814605713},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07884025573730469}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8110146522521973},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.616629958152771},{"id":"https://openalex.org/C125932096","wikidata":"https://www.wikidata.org/wiki/Q205472","display_name":"Zipf's law","level":2,"score":0.5395772457122803},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5387542843818665},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5051766037940979},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.48890557885169983},{"id":"https://openalex.org/C2777548347","wikidata":"https://www.wikidata.org/wiki/Q5456937","display_name":"Flagging","level":2,"score":0.46505436301231384},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4601481556892395},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4305153489112854},{"id":"https://openalex.org/C22041718","wikidata":"https://www.wikidata.org/wiki/Q638949","display_name":"Geolocation","level":2,"score":0.4190915822982788},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2895413637161255},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.23214399814605713},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07884025573730469},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1390749.1390760","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390749.1390760","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the second workshop on Analytics for noisy unstructured text data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W106005634","https://openalex.org/W1574862351","https://openalex.org/W2042376691","https://openalex.org/W2146859361","https://openalex.org/W2470343719","https://openalex.org/W6604315852","https://openalex.org/W6720153818"],"related_works":["https://openalex.org/W2946613364","https://openalex.org/W2807886874","https://openalex.org/W1697346018","https://openalex.org/W2113326855","https://openalex.org/W4393527151","https://openalex.org/W611259847","https://openalex.org/W2354785495","https://openalex.org/W642986199","https://openalex.org/W2320858910","https://openalex.org/W174528541"],"abstract_inverted_index":{"Language":[0],"usage":[1],"in":[2,9],"Blogs":[3,34],"deviate":[4],"from":[5,17,75],"the":[6,15,38],"language":[7],"used":[8],"traditional":[10],"corpora":[11],"largely":[12],"due":[13],"to":[14,46,72,101],"noise":[16],"various":[18],"causes":[19],"like":[20,31],"spelling":[21],"errors,":[22],"grammatical":[23],"irregularity,":[24],"overuse":[25],"of":[26,40,64,81,96],"abbreviations":[27],"and":[28,53,90,103,110],"symbolic":[29],"characters":[30],"emoticons.":[32],"Spam":[33],"or":[35],"Splogs":[36],"comprise":[37],"subset":[39],"blogs,":[41],"which":[42,98],"are":[43,54,99],"usually":[44],"written":[45],"target":[47],"specific":[48],"audience":[49],"for":[50],"marketing":[51],"promotions":[52],"mostly":[55],"generated":[56],"by":[57],"software":[58],"that":[59],"readily":[60],"imitates":[61],"Zipfian":[62],"distribution":[63,80],"words.":[65],"Therefore":[66],"it":[67],"becomes":[68],"a":[69],"difficult":[70],"task":[71],"separate":[73],"splogs":[74,109],"non-splogs":[76],"using":[77],"only":[78],"frequentist":[79],"unigrams.":[82],"In":[83],"this":[84],"detailed":[85],"comparative":[86],"study":[87],"we":[88],"present":[89],"highlight":[91],"several":[92],"additional":[93],"statistical":[94],"features":[95],"language,":[97],"hard":[100],"imitate":[102],"serve":[104],"as":[105],"good":[106],"discriminator":[107],"between":[108],"blogs.":[111]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}