%0 Conference Paper %1 GKB06 %A Geleijnse, Gijs %A Korst, Jan %A de Boer, Viktor %B Proc. of the ISWC2006 Workshop on Web Content Mining with Human Language Technologies %D 2006 %K WCMHLT2006 co-occurence datamining google linguistics %T Instance Classification using Co-Occurrences on the Web %U http://orestes.ii.uam.es/workshop/3.pdf %X We present a novel unsupervised approach to mapping artrelated instances (such as music artists and painters) to subjective categories like genre and style. We base our approach on co-occurrences of the two on the web, found with Google. The co-occurrences are found using three methods: by identifying the search engine counts, by analyzing Google excerpts found by querying patterns and by scanning full documents. Per instance, we use the same co-occurrence-based approach to find its nearest neighbors, i.e. the most related instances. These results can be combined in order to create a more reliable classification. We tested and compared the three methods on two different domains: mapping music artists to genres, and painters to art-styles. The results show that the use of related instances indeed improves the precision of the classification. Moreover, the methods with the lowest Google Complexity perform best.

@inproceedings{GKB06, abstract = {We present a novel unsupervised approach to mapping artrelated instances (such as music artists and painters) to subjective categories like genre and style. We base our approach on co-occurrences of the two on the web, found with Google. The co-occurrences are found using three methods: by identifying the search engine counts, by analyzing Google excerpts found by querying patterns and by scanning full documents. Per instance, we use the same co-occurrence-based approach to find its nearest neighbors, i.e. the most related instances. These results can be combined in order to create a more reliable classification. We tested and compared the three methods on two different domains: mapping music artists to genres, and painters to art-styles. The results show that the use of related instances indeed improves the precision of the classification. Moreover, the methods with the lowest Google Complexity perform best.}, added-at = {2007-09-16T02:41:17.000+0200}, author = {Geleijnse, Gijs and Korst, Jan and de Boer, Viktor}, biburl = {https://www.bibsonomy.org/bibtex/2027513ba40abf3789d6e8872fbe07287/siggi}, booktitle = {Proc. of the ISWC2006 Workshop on Web Content Mining with Human Language Technologies}, interhash = {e26e7cca0055f3042f172a70968aa724}, intrahash = {027513ba40abf3789d6e8872fbe07287}, keywords = {WCMHLT2006 co-occurence datamining google linguistics}, timestamp = {2007-09-16T02:41:17.000+0200}, title = {Instance Classification using Co-Occurrences on the Web}, url = {http://orestes.ii.uam.es/workshop/3.pdf}, year = 2006 }