A concept-based model for enhancing text categorization Export

@inproceedings{citeulike:1625532, abstract = {Most of text categorization techniques are based on word and/or phrase analysis of the text. Statistical analysis of a term frequency captures the importance of the term within a document only. However, two terms can have the same frequency in their documents, but one term contributes moreto the meaning of its sentences than the other term. Thus, the underlying model should indicate terms that capture these mantics of text. In this case, the model can capture terms that present the concepts of the sentence, which leads todiscover the topic of the document. A new concept-based model that analyzes terms on the sentence and document levels rather than the traditional analysis of document only is introduced. The concept-based model can effectively discriminate between non-important terms with respect to sentence semantics and terms which hold the concepts that represent the sentence meaning. The proposed model consists of concept-based statistical analyzer, conceptual ontological graph representation,and concept extractor. The term which contributes to the sentence semantics is assigned two different weights by the concept-based statistical analyzer and the conceptual ontological graph representation. These two weights are combined into a new weight. The concepts that have maximum combined weights are selected by the concept extractor. A set of experiments using the proposed concept-basedmodel on different datasets in text categorization is conducted. The experiments demonstrate the comparison between traditional weighting and the concept-based weighting obtained by the combined approach of the concept-based statistical analyzer and the conceptual ontological graph. The evaluation of results is relied on two quality measures, the Macro-averaged F1 and the Error rate. These quality measures are improved when the newly developed concept-based model is used to enhance the quality of the text categorization.}, address = {New York, NY, USA}, author = {Shehata, Shady and Karray, Fakhri and Kamel, Mohamed}, booktitle = {KDD '07: Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining}, citeulike-article-id = {1625532}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1281192.1281260}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1281192.1281260}, doi = {10.1145/1281192.1281260}, isbn = {9781595936097}, keywords = {categorization--automatic, text-categorization}, pages = {629--637}, posted-at = {2007-09-05 23:33:17}, priority = {3}, publisher = {ACM Press}, title = {A concept-based model for enhancing text categorization}, url = {http://dx.doi.org/10.1145/1281192.1281260}, year = {2007} }

TY - CONF ID - citeulike:1625532 L3 - citeulike-article-id:1625532 N2 - Most of text categorization techniques are based on word and/or phrase analysis of the text. Statistical analysis of a term frequency captures the importance of the term within a document only. However, two terms can have the same frequency in their documents, but one term contributes moreto the meaning of its sentences than the other term. Thus, the underlying model should indicate terms that capture these mantics of text. In this case, the model can capture terms that present the concepts of the sentence, which leads todiscover the topic of the document. A new concept-based model that analyzes terms on the sentence and document levels rather than the traditional analysis of document only is introduced. The concept-based model can effectively discriminate between non-important terms with respect to sentence semantics and terms which hold the concepts that represent the sentence meaning. The proposed model consists of concept-based statistical analyzer, conceptual ontological graph representation,and concept extractor. The term which contributes to the sentence semantics is assigned two different weights by the concept-based statistical analyzer and the conceptual ontological graph representation. These two weights are combined into a new weight. The concepts that have maximum combined weights are selected by the concept extractor. A set of experiments using the proposed concept-basedmodel on different datasets in text categorization is conducted. The experiments demonstrate the comparison between traditional weighting and the concept-based weighting obtained by the combined approach of the concept-based statistical analyzer and the conceptual ontological graph. The evaluation of results is relied on two quality measures, the Macro-averaged F1 and the Error rate. These quality measures are improved when the newly developed concept-based model is used to enhance the quality of the text categorization. SN - 9781595936097 AD - New York, NY, USA EP - 637 TI - A concept-based model for enhancing text categorization PB - ACM Press T2 - KDD '07: Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining SP - 629 KW - categorization--automatic KW - text-categorization AU - Shehata, Shady AU - Karray, Fakhri AU - Kamel, Mohamed PY - 2007/// UR - http://dx.doi.org/10.1145/1281192.1281260 ER -