{ "eprintid": "163", "rev_number": "4", "eprint_status": "archive", "dir": "disk0/00/00/01/63", "datestamp": "2009-04-06 19:13:40", "lastmod": "2009-04-07 14:03:04", "status_changed": "2009-04-06 19:13:40", "type": "conference_item", "metadata_visibility": "show", "item_issues_count": "0", "creators": { "item": { "name": { "family": "Kohlschütter", "given": "Christian" }, "id": "", "country": "", "affiliation": "Leibniz Universität Hannover" } }, "track": "Poster Session", "title": "A Densitometric Analysis of Web Template Content", "ispublished": "pub", "full_text_status": "public", "pres_type": "poster", "abstract": "What makes template content in the Web so special that we need to remove it? In this paper I present a large-scale aggregate analysis of textual Web content, corroborating statistical laws from the field of Quantitative Linguistics. I analyze the idiosyncrasy of template content compared to regular “full text” content and derive a simple yet suitable quantitative model.", "date": "2009-04", "pagerange": "1165-1165", "event_title": "18th International World Wide Web Conference", "event_location": "Madrid, Spain", "event_dates": "April 20th-24th, 2009", "event_type": "conference", "refereed": "TRUE", "documents": { "document": { "docid": "163", "rev_number": "4", "eprintid": "163", "pos": "1", "format": "application/pdf", "language": "en", "security": "public", "main": "p1165.pdf", "content": "published", "files": { "file": { "filename": "p1165.pdf", "filesize": "571465", "url": "http://www2009.eprints.org/163/1/p1165.pdf" } } } } }