Automatically assigned DDC number: 006312
Manually assigned DDC number: 006312
Number of references: 8
Title: Using Links for Classifying Web-pages
Subject: Using Links for Classifying Web-pages
Description: In this paper, we report on a systematic set of experiments that explore the utility of making use of such structural information. Our working hypothesis is that (at least in some domains) it is easier to classify hypertext pages using information provided on pages that point to a page instead of using information that is provided on the page itself. We present a set of experiments that confirm this hypothesis on a set of Web-pages that relate to Computer Science Departments.
Contributor: The Pennsylvania State University CiteSeer Archives
Publisher: unknown
Date: 1999-01-15
Pubyear: 1998
Format: ps
Identifier: http://citeseer.ist.psu.edu/153148.html
Source: ftp://ftp.ai.univie.ac.at/papers/oefai-tr-98-29.ps.gz
Language: en
Relation:
Relation:
Relation:
Relation:
Relation:
Relation:
Relation:
Relation:
Rights: unrestricted
<?xml version="1.0" encoding="UTF-8"?>
<references_metadata>
<rec ID="/54411.html" Type="inproceedings" CiteSeer_Book="Proc of the 12th International Conference on Machine Learning" CiteSeer_Volume="" Title="Fast Effective Rule Induction,">
<identifier Org="ISBN:0387333339" Paper_ID="/54411.html" Extracted="0387333339" DDC="006.312" Normalized_DDC="006312" Normalized_Weight="0.05555555555555555" />
<identifier Org="ISBN:0898715458" Paper_ID="/54411.html" Extracted="0898715458" DDC="006.3/12" Normalized_DDC="006312" Normalized_Weight="0.05555555555555555" />
<identifier Org="ISBN:1558603778" Paper_ID="/54411.html" Extracted="1558603778" DDC="006.3/1" Normalized_DDC="00631" Normalized_Weight="0.05555555555555555" />
<identifier Org="ISBN:1591404517" Paper_ID="/54411.html" Extracted="1591404517" DDC="006.3/3" Normalized_DDC="00633" Normalized_Weight="0.05555555555555555" />
<identifier Org="ISBN:1605660108" Paper_ID="/54411.html" Extracted="1605660108" DDC="005.74" Normalized_DDC="00574" Normalized_Weight="0.05555555555555555" />
<identifier Org="ISBN:1930708254" Paper_ID="/54411.html" Extracted="1930708254" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.05555555555555555" />
<identifier Org="ISBN:3540222189" Paper_ID="/54411.html" Extracted="3540222189" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.05555555555555555" />
<identifier Org="ISBN:3540231056" Paper_ID="/54411.html" Extracted="3540231056" DDC="006.3/1" Normalized_DDC="00631" Normalized_Weight="0.05555555555555555" />
<identifier Org="ISBN:3540236627" Paper_ID="/54411.html" Extracted="3540236627" DDC="005.75/8" Normalized_DDC="005758" Normalized_Weight="0.05555555555555555" />
<identifier Org="ISBN:3540265430" Paper_ID="/54411.html" Extracted="3540265430" DDC="006.3/12" Normalized_DDC="006312" Normalized_Weight="0.05555555555555555" />
<identifier Org="ISBN:3540287957" Paper_ID="/54411.html" Extracted="3540287957" DDC="519.5" Normalized_DDC="5195" Normalized_Weight="0.05555555555555555" />
<identifier Org="ISBN:3540403000" Paper_ID="/54411.html" Extracted="3540403000" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.05555555555555555" />
<identifier Org="ISBN:3540408134" Paper_ID="/54411.html" Extracted="3540408134" DDC="519.5" Normalized_DDC="5195" Normalized_Weight="0.05555555555555555" />
<identifier Org="ISBN:354041276X" Paper_ID="/54411.html" Extracted="354041276X" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.05555555555555555" />
<identifier Org="ISBN:3540425381" Paper_ID="/54411.html" Extracted="3540425381" DDC="005.1/15" Normalized_DDC="005115" Normalized_Weight="0.05555555555555555" />
<identifier Org="ISBN:3540430601" Paper_ID="/54411.html" Extracted="3540430601" DDC="519.5" Normalized_DDC="5195" Normalized_Weight="0.05555555555555555" />
<identifier Org="ISBN:3540667482" Paper_ID="/54411.html" Extracted="3540667482" DDC="006.3/1" Normalized_DDC="00631" Normalized_Weight="0.05555555555555555" />
<identifier Org="ISBN:3540681248" Paper_ID="/54411.html" Extracted="3540681248" />
<identifier Org="ISBN:902724992X" Paper_ID="/54411.html" Extracted="902724992X" DDC="006.3/5" Normalized_DDC="00635" Normalized_Weight="0.05555555555555555" />
</rec>
<rec ID="/56507.html" Type="inproceedings" CiteSeer_Book="AAAIIAAI Vol 1" CiteSeer_Volume="" Title="Learning Trees and Rules with Set-Valued Features,">
<identifier Org="ISBN:0124438814" Paper_ID="/56507.html" Extracted="0124438814" />
<identifier Org="ISBN:0262510987" Paper_ID="/56507.html" Extracted="0262510987" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.06666666666666667" />
<identifier Org="ISBN:1558607072" Paper_ID="/56507.html" Extracted="1558607072" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.06666666666666667" />
<identifier Org="ISBN:1558608699" Paper_ID="/56507.html" Extracted="1558608699" />
<identifier Org="ISBN:3540223703" Paper_ID="/56507.html" Extracted="3540223703" DDC="006.312" Normalized_DDC="006312" Normalized_Weight="0.06666666666666667" />
<identifier Org="ISBN:3540263195" Paper_ID="/56507.html" Extracted="3540263195" DDC="006.32" Normalized_DDC="00632" Normalized_Weight="0.06666666666666667" />
<identifier Org="ISBN:3540281770" Paper_ID="/56507.html" Extracted="3540281770" DDC="005.1/15" Normalized_DDC="005115" Normalized_Weight="0.06666666666666667" />
<identifier Org="ISBN:3540292306" Paper_ID="/56507.html" Extracted="3540292306" DDC="501" Normalized_DDC="501" Normalized_Weight="0.06666666666666667" />
<identifier Org="ISBN:3540298495" Paper_ID="/56507.html" Extracted="3540298495" DDC="621.392" Normalized_DDC="621392" Normalized_Weight="0.06666666666666667" />
<identifier Org="ISBN:3540404333" Paper_ID="/56507.html" Extracted="3540404333" DDC="006.3/33" Normalized_DDC="006333" Normalized_Weight="0.06666666666666667" />
<identifier Org="ISBN:3540418261" Paper_ID="/56507.html" Extracted="3540418261" />
<identifier Org="ISBN:3540420274" Paper_ID="/56507.html" Extracted="3540420274" DDC="006.3/1" Normalized_DDC="00631" Normalized_Weight="0.06666666666666667" />
<identifier Org="ISBN:3540633464" Paper_ID="/56507.html" Extracted="3540633464" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.06666666666666667" />
<identifier Org="ISBN:3540647384" Paper_ID="/56507.html" Extracted="3540647384" DDC="005.1/15" Normalized_DDC="005115" Normalized_Weight="0.06666666666666667" />
<identifier Org="ISBN:3540663320" Paper_ID="/56507.html" Extracted="3540663320" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.06666666666666667" />
<identifier Org="ISBN:3540672273" Paper_ID="/56507.html" Extracted="3540672273" DDC="005.74" Normalized_DDC="00574" Normalized_Weight="0.06666666666666667" />
<identifier Org="ISBN:354070938X" Paper_ID="/56507.html" Extracted="354070938X" DDC="005.52" Normalized_DDC="00552" Normalized_Weight="0.06666666666666667" />
<identifier Org="ISBN:3540717021" Paper_ID="/56507.html" Extracted="3540717021" />
<identifier Org="ISBN:3540749756" Paper_ID="/56507.html" Extracted="3540749756" DDC="005.74" Normalized_DDC="00574" Normalized_Weight="0.06666666666666667" />
<identifier Org="ISBN:9042012579" Paper_ID="/56507.html" Extracted="9042012579" />
</rec>
<rec ID="/90349.html" Type="misc" CiteSeer_Book="" CiteSeer_Volume="" Title="Using statistical and relational methods to characterize hyperlink paths,">
<identifier Org="ISBN:3540663320" Paper_ID="/90349.html" Extracted="3540663320" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="1.0" />
</rec>
<rec ID="/124233.html" Type="inproceedings" CiteSeer_Book="Proceedings of AAAI98 15th Conference of the American Association for Artificial Intelligence" CiteSeer_Volume="" Title="Learning to extract symbolic knowledge from the {W}orld {W}ide {W}eb," />
<rec ID="/9707.html" Type="misc" CiteSeer_Book="" CiteSeer_Volume="" Title="A Case Study in Using Linguistic Phrases for Text Categorization on the {WWW},">
<identifier Org="ISBN:0387244352" Paper_ID="/9707.html" Extracted="0387244352" DDC="006.3/12" Normalized_DDC="006312" Normalized_Weight="0.07692307692307693" />
<identifier Org="ISBN:0769507107" Paper_ID="/9707.html" Extracted="0769507107" />
<identifier Org="ISBN:0792373499" Paper_ID="/9707.html" Extracted="0792373499" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.07692307692307693" />
<identifier Org="ISBN:0792376560" Paper_ID="/9707.html" Extracted="0792376560" DDC="005.2/76" Normalized_DDC="005276" Normalized_Weight="0.07692307692307693" />
<identifier Org="ISBN:079237679X" Paper_ID="/9707.html" Extracted="079237679X" DDC="005" Normalized_DDC="005" Normalized_Weight="0.07692307692307693" />
<identifier Org="ISBN:0826491812" Paper_ID="/9707.html" Extracted="0826491812" DDC="418/.020285" Normalized_DDC="418020285" Normalized_Weight="0.07692307692307693" />
<identifier Org="ISBN:158113231X" Paper_ID="/9707.html" Extracted="158113231X" />
<identifier Org="ISBN:1600217001" Paper_ID="/9707.html" Extracted="1600217001" DDC="401/.410285" Normalized_DDC="401410285" Normalized_Weight="0.07692307692307693" />
<identifier Org="ISBN:1845640179" Paper_ID="/9707.html" Extracted="1845640179" DDC="005.74" Normalized_DDC="00574" Normalized_Weight="0.07692307692307693" />
<identifier Org="ISBN:3540211233" Paper_ID="/9707.html" Extracted="3540211233" DDC="006.3/2" Normalized_DDC="00632" Normalized_Weight="0.07692307692307693" />
<identifier Org="ISBN:3540213317" Paper_ID="/9707.html" Extracted="3540213317" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.07692307692307693" />
<identifier Org="ISBN:3540213821" Paper_ID="/9707.html" Extracted="3540213821" DDC="005.74" Normalized_DDC="00574" Normalized_Weight="0.07692307692307693" />
<identifier Org="ISBN:3540425365" Paper_ID="/9707.html" Extracted="3540425365" DDC="006.3/1" Normalized_DDC="00631" Normalized_Weight="0.07692307692307693" />
<identifier Org="ISBN:3540663320" Paper_ID="/9707.html" Extracted="3540663320" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.07692307692307693" />
<identifier Org="ISBN:3540673059" Paper_ID="/9707.html" Extracted="3540673059" DDC="006.3/2" Normalized_DDC="00632" Normalized_Weight="0.07692307692307693" />
</rec>
<rec ID="/98881.html" Type="inproceedings" CiteSeer_Book="AAAIIAAI Vol 2" CiteSeer_Volume="" Title="Automatically Generating Extraction Patterns from Untagged Text,">
<identifier Org="ISBN:026251091X" Paper_ID="/98881.html" Extracted="026251091X" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.0625" />
<identifier Org="ISBN:0387244352" Paper_ID="/98881.html" Extracted="0387244352" DDC="006.3/12" Normalized_DDC="006312" Normalized_Weight="0.0625" />
<identifier Org="ISBN:0387716122" Paper_ID="/98881.html" Extracted="0387716122" DDC="006.312" Normalized_DDC="006312" Normalized_Weight="0.0625" />
<identifier Org="ISBN:1402047444" Paper_ID="/98881.html" Extracted="1402047444" />
<identifier Org="ISBN:1599043734" Paper_ID="/98881.html" Extracted="1599043734" DDC="005.74" Normalized_DDC="00574" Normalized_Weight="0.0625" />
<identifier Org="ISBN:1860947832" Paper_ID="/98881.html" Extracted="1860947832" DDC="572.80285" Normalized_DDC="57280285" Normalized_Weight="0.0625" />
<identifier Org="ISBN:2874630829" Paper_ID="/98881.html" Extracted="2874630829" />
<identifier Org="ISBN:3540213821" Paper_ID="/98881.html" Extracted="3540213821" DDC="005.74" Normalized_DDC="00574" Normalized_Weight="0.0625" />
<identifier Org="ISBN:3540245235" Paper_ID="/98881.html" Extracted="3540245235" DDC="025.04" Normalized_DDC="02504" Normalized_Weight="0.0625" />
<identifier Org="ISBN:3540250700" Paper_ID="/98881.html" Extracted="3540250700" DDC="006.312" Normalized_DDC="006312" Normalized_Weight="0.0625" />
<identifier Org="ISBN:3540259996" Paper_ID="/98881.html" Extracted="3540259996" DDC="006.33" Normalized_DDC="00633" Normalized_Weight="0.0625" />
<identifier Org="ISBN:3540278311" Paper_ID="/98881.html" Extracted="3540278311" DDC="610.28563" Normalized_DDC="61028563" Normalized_Weight="0.0625" />
<identifier Org="ISBN:3540308504" Paper_ID="/98881.html" Extracted="3540308504" DDC="025.00285" Normalized_DDC="02500285" Normalized_Weight="0.0625" />
<identifier Org="ISBN:3540405798" Paper_ID="/98881.html" Extracted="3540405798" DDC="006.35" Normalized_DDC="00635" Normalized_Weight="0.0625" />
<identifier Org="ISBN:3540423583" Paper_ID="/98881.html" Extracted="3540423583" DDC="006.3/33" Normalized_DDC="006333" Normalized_Weight="0.0625" />
<identifier Org="ISBN:3540643834" Paper_ID="/98881.html" Extracted="3540643834" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.0625" />
<identifier Org="ISBN:3540676058" Paper_ID="/98881.html" Extracted="3540676058" DDC="006.3/5" Normalized_DDC="00635" Normalized_Weight="0.0625" />
<identifier Org="ISBN:3540681248" Paper_ID="/98881.html" Extracted="3540681248" />
<identifier Org="ISBN:3540686339" Paper_ID="/98881.html" Extracted="3540686339" />
<identifier Org="ISBN:9812388273" Paper_ID="/98881.html" Extracted="9812388273" DDC="006.3/2" Normalized_DDC="00632" Normalized_Weight="0.0625" />
</rec>
<rec ID="/40399.html" Type="article" CiteSeer_Book="Artificial Intelligence" CiteSeer_Volume="85" Title="An Empirical Study of Automated Dictionary Construction for Information Extraction in Three Domains,">
<identifier Org="ISBN:026251091X" Paper_ID="/40399.html" Extracted="026251091X" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.07142857142857142" />
<identifier Org="ISBN:0387244352" Paper_ID="/40399.html" Extracted="0387244352" DDC="006.3/12" Normalized_DDC="006312" Normalized_Weight="0.07142857142857142" />
<identifier Org="ISBN:0780372808" Paper_ID="/40399.html" Extracted="0780372808" DDC="629.8" Normalized_DDC="6298" Normalized_Weight="0.07142857142857142" />
<identifier Org="ISBN:0780383532" Paper_ID="/40399.html" Extracted="0780383532" DDC="003" Normalized_DDC="003" Normalized_Weight="0.07142857142857142" />
<identifier Org="ISBN:0792356853" Paper_ID="/40399.html" Extracted="0792356853" DDC="410/.285" Normalized_DDC="410285" Normalized_Weight="0.07142857142857142" />
<identifier Org="ISBN:1402005687" Paper_ID="/40399.html" Extracted="1402005687" DDC="003/.54" Normalized_DDC="00354" Normalized_Weight="0.07142857142857142" />
<identifier Org="ISBN:1577350839" Paper_ID="/40399.html" Extracted="1577350839" />
<identifier Org="ISBN:1581131348" Paper_ID="/40399.html" Extracted="1581131348" />
<identifier Org="ISBN:1599043734" Paper_ID="/40399.html" Extracted="1599043734" DDC="005.74" Normalized_DDC="00574" Normalized_Weight="0.07142857142857142" />
<identifier Org="ISBN:1599049902" Paper_ID="/40399.html" Extracted="1599049902" DDC="005.75/9" Normalized_DDC="005759" Normalized_Weight="0.07142857142857142" />
<identifier Org="ISBN:3540220046" Paper_ID="/40399.html" Extracted="3540220046" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.07142857142857142" />
<identifier Org="ISBN:3540419438" Paper_ID="/40399.html" Extracted="3540419438" DDC="006.3/5" Normalized_DDC="00635" Normalized_Weight="0.07142857142857142" />
<identifier Org="ISBN:3540609253" Paper_ID="/40399.html" Extracted="3540609253" DDC="006.3/5" Normalized_DDC="00635" Normalized_Weight="0.07142857142857142" />
<identifier Org="ISBN:3540660445" Paper_ID="/40399.html" Extracted="3540660445" DDC="006.3/31" Normalized_DDC="006331" Normalized_Weight="0.07142857142857142" />
<identifier Org="ISBN:3540676058" Paper_ID="/40399.html" Extracted="3540676058" DDC="006.3/5" Normalized_DDC="00635" Normalized_Weight="0.07142857142857142" />
<identifier Org="ISBN:9812388273" Paper_ID="/40399.html" Extracted="9812388273" DDC="006.3/2" Normalized_DDC="00632" Normalized_Weight="0.07142857142857142" />
</rec>
<rec ID="/98225.html" Type="inproceedings" CiteSeer_Book="Proceedings of ILP98 8th International Conference on Inductive Logic Programming" CiteSeer_Volume="" Title="Combining Statistical and Relational Methods for Learning in Hypertext Domains,">
<identifier Org="ISBN:0387244352" Paper_ID="/98225.html" Extracted="0387244352" DDC="006.3/12" Normalized_DDC="006312" Normalized_Weight="0.08333333333333333" />
<identifier Org="ISBN:0471731900" Paper_ID="/98225.html" Extracted="0471731900" DDC="005.74" Normalized_DDC="00574" Normalized_Weight="0.08333333333333333" />
<identifier Org="ISBN:0521836573" Paper_ID="/98225.html" Extracted="0521836573" DDC="005.74" Normalized_DDC="00574" Normalized_Weight="0.08333333333333333" />
<identifier Org="ISBN:1577350839" Paper_ID="/98225.html" Extracted="1577350839" />
<identifier Org="ISBN:1580533698" Paper_ID="/98225.html" Extracted="1580533698" DDC="005.8" Normalized_DDC="0058" Normalized_Weight="0.08333333333333333" />
<identifier Org="ISBN:1586035282" Paper_ID="/98225.html" Extracted="1586035282" DDC="005.74" Normalized_DDC="00574" Normalized_Weight="0.08333333333333333" />
<identifier Org="ISBN:1595931406" Paper_ID="/98225.html" Extracted="1595931406" />
<identifier Org="ISBN:3540202994" Paper_ID="/98225.html" Extracted="3540202994" DDC="005.74" Normalized_DDC="00574" Normalized_Weight="0.08333333333333333" />
<identifier Org="ISBN:3540225420" Paper_ID="/98225.html" Extracted="3540225420" DDC="371.334678" Normalized_DDC="371334678" Normalized_Weight="0.08333333333333333" />
<identifier Org="ISBN:3540343504" Paper_ID="/98225.html" Extracted="3540343504" DDC="006.312" Normalized_DDC="006312" Normalized_Weight="0.08333333333333333" />
<identifier Org="ISBN:3540416870" Paper_ID="/98225.html" Extracted="3540416870" />
<identifier Org="ISBN:3540439595" Paper_ID="/98225.html" Extracted="3540439595" />
<identifier Org="ISBN:3540647384" Paper_ID="/98225.html" Extracted="3540647384" DDC="005.1/15" Normalized_DDC="005115" Normalized_Weight="0.08333333333333333" />
<identifier Org="ISBN:3540661093" Paper_ID="/98225.html" Extracted="3540661093" />
<identifier Org="ISBN:3540663320" Paper_ID="/98225.html" Extracted="3540663320" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.08333333333333333" />
<identifier Org="ISBN:3540667482" Paper_ID="/98225.html" Extracted="3540667482" DDC="006.3/1" Normalized_DDC="00631" Normalized_Weight="0.08333333333333333" />
<identifier Org="ISBN:354067795X" Paper_ID="/98225.html" Extracted="354067795X" DDC="005.1/15" Normalized_DDC="005115" Normalized_Weight="0.08333333333333333" />
<identifier Org="ISBN:3540677976" Paper_ID="/98225.html" Extracted="3540677976" />
<identifier Org="ISBN:3540881913" Paper_ID="/98225.html" Extracted="3540881913" />
</rec>
<rec ID="SELF" Type="SELF" CiteSeer_Book="SELF" CiteSeer_Volume="SELF" Title="Using Links for Classifying Web-pages">
<identifier Org="ISBN:1581137044" Paper_ID="SELF" Extracted="1581137044" DDC="006.7" Normalized_DDC="0067" Normalized_Weight="0.3333333333333333" />
<identifier Org="ISBN:3540408088" Paper_ID="SELF" Extracted="3540408088" DDC="381/.142/028558" Normalized_DDC="381142028558" Normalized_Weight="0.3333333333333333" />
<identifier Org="ISBN:3540663320" Paper_ID="SELF" Extracted="3540663320" DDC="006.3" Normalized_DDC="0063" Normalized_Weight="0.3333333333333333" />
</rec>
</references_metadata>