@inproceedings{ cas04,
  crossref = {www2004},
  author = {Davi {de Castro Reis} and Paulo B. Golgher and Altigran S. da Silva and Alberto H. F. Laender},
  title = {Automatic Web News Extraction Using Tree Edit Distance},
  pages = {502-601},
  uri = {http://www2004.org/proceedings/docs/1p502.pdf},
  abstract = {The Web poses itself as the largest data repository ever available in the history of humankind. Major efforts have been made in order to provide efficient access to relevant information within this huge repository of data. Although several techniques have been developed to the problem of Web data extraction, their use is still not spread, mostly because of the need for high human intervention and the low quality of the extraction results. In this paper, we present a domain-oriented approach to Web data extraction and discuss its application to automatically extracting news from Web sites. Our approach is based on a highly efficient tree structure analysis that produces very effective results. We have tested our approach with several important Brazilian on-line news sites and achieved very precise results, correctly extracting 87.71% of the news in a set of 4088 pages distributed among 35 different sites.}
}

{"_id":{"_str":"53ff72c27c90ec6e13001285"},"__v":0,"authorIDs":[],"author_short":["de Castro Reis, D.","Golgher, P.<nbsp>B.","da<nbsp>Silva, A.<nbsp>S.","Laender, A.<nbsp>H.<nbsp>F."],"bibbaseid":"decastroreis-golgher-danbspsilva-laender-automaticwebnewsextractionusingtreeeditdistance","bibdata":{"downloads":0,"role":"author","bibbaseid":"decastroreis-golgher-danbspsilva-laender-automaticwebnewsextractionusingtreeeditdistance","uri":"http://www2004.org/proceedings/docs/1p502.pdf","type":"inproceedings","title":"Automatic Web News Extraction Using Tree Edit Distance","pages":"502-601","key":"cas04","id":"cas04","crossref":"www2004","bibtype":"inproceedings","bibtex":"@inproceedings{ cas04,\n crossref = {www2004},\n author = {Davi {de Castro Reis} and Paulo B. Golgher and Altigran S. da Silva and Alberto H. F. Laender},\n title = {Automatic Web News Extraction Using Tree Edit Distance},\n pages = {502-601},\n uri = {http://www2004.org/proceedings/docs/1p502.pdf},\n abstract = {The Web poses itself as the largest data repository ever available in the history of humankind. Major efforts have been made in order to provide efficient access to relevant information within this huge repository of data. Although several techniques have been developed to the problem of Web data extraction, their use is still not spread, mostly because of the need for high human intervention and the low quality of the extraction results. In this paper, we present a domain-oriented approach to Web data extraction and discuss its application to automatically extracting news from Web sites. Our approach is based on a highly efficient tree structure analysis that produces very effective results. We have tested our approach with several important Brazilian on-line news sites and achieved very precise results, correctly extracting 87.71% of the news in a set of 4088 pages distributed among 35 different sites.}\n}","author_short":["de Castro Reis, D.","Golgher, P.<nbsp>B.","da<nbsp>Silva, A.<nbsp>S.","Laender, A.<nbsp>H.<nbsp>F."],"author":["de Castro Reis, Davi","Golgher, Paulo B.","da Silva, Altigran S.","Laender, Alberto H. F."],"abstract":"The Web poses itself as the largest data repository ever available in the history of humankind. Major efforts have been made in order to provide efficient access to relevant information within this huge repository of data. Although several techniques have been developed to the problem of Web data extraction, their use is still not spread, mostly because of the need for high human intervention and the low quality of the extraction results. In this paper, we present a domain-oriented approach to Web data extraction and discuss its application to automatically extracting news from Web sites. Our approach is based on a highly efficient tree structure analysis that produces very effective results. We have tested our approach with several important Brazilian on-line news sites and achieved very precise results, correctly extracting 87.71% of the news in a set of 4088 pages distributed among 35 different sites."},"bibtype":"inproceedings","biburl":"http://dret.net/biblio/dret.bib","creationDate":"2014-08-28T18:19:46.373Z","downloads":0,"keywords":[],"search_terms":["automatic","web","news","extraction","using","tree","edit","distance","de castro reis","golgher","da<nbsp>silva","laender"],"title":"Automatic Web News Extraction Using Tree Edit Distance","year":null,"dataSources":["mL7NKvaepNEWFcMvG"]}