Matches in SemOpenAlex for { <https://semopenalex.org/work/W2039492713> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W2039492713 endingPage "2281" @default.
- W2039492713 startingPage "2273" @default.
- W2039492713 abstract "In the previous paper (Ogura, H., Amano, H., & Kondo, M. (2009). Feature selection with a measure of deviations from Poisson in text categorization. Expert Systems with Applications, 36, 6826–6832.), we proposed a new metric, χP2, for selecting features in text classification which estimates term importance based on how largely the probability distribution of a considered term deviates from the standard Poisson distribution. In this study, to establish the validity and advantage of using χP2, we conducted experiments of automatic text classification on 20 NewsGroups data collection with binary setting. In the experiments, other three metrics for feature selection, i.e., Gini index, χ2 statistic and information gain, were also used for comparison. From the results, it was confirmed that χP2 and Gini index are much better than χ2 statistic and information gain in terms of F1 performance when they handle imbalanced data set. Furthermore, through another experiment in which the degree of imbalance in class distribution was explicitly controlled, we clarified that the origin of the superiority of χP2 and Gini index is their ability to pick up suitable negative features in imbalanced data set. The ability of these two metrics to select suitable negative features is explained based on the analysis of their limiting behaviors at some extreme cases." @default.
- W2039492713 created "2016-06-24" @default.
- W2039492713 creator A5023927893 @default.
- W2039492713 creator A5050533134 @default.
- W2039492713 creator A5079112781 @default.
- W2039492713 date "2010-03-15" @default.
- W2039492713 modified "2023-09-27" @default.
- W2039492713 title "Distinctive characteristics of a metric using deviations from Poisson for feature selection" @default.
- W2039492713 cites W140777655 @default.
- W2039492713 cites W1493526108 @default.
- W2039492713 cites W1540550673 @default.
- W2039492713 cites W1549887922 @default.
- W2039492713 cites W1565377632 @default.
- W2039492713 cites W1604792744 @default.
- W2039492713 cites W1999635750 @default.
- W2039492713 cites W2023450550 @default.
- W2039492713 cites W2053724458 @default.
- W2039492713 cites W2091669653 @default.
- W2039492713 cites W2109571154 @default.
- W2039492713 cites W2118020653 @default.
- W2039492713 cites W2151191523 @default.
- W2039492713 cites W2435251607 @default.
- W2039492713 cites W99763903 @default.
- W2039492713 cites W7626864 @default.
- W2039492713 doi "https://doi.org/10.1016/j.eswa.2009.07.045" @default.
- W2039492713 hasPublicationYear "2010" @default.
- W2039492713 type Work @default.
- W2039492713 sameAs 2039492713 @default.
- W2039492713 citedByCount "9" @default.
- W2039492713 countsByYear W20394927132012 @default.
- W2039492713 countsByYear W20394927132013 @default.
- W2039492713 countsByYear W20394927132014 @default.
- W2039492713 countsByYear W20394927132016 @default.
- W2039492713 countsByYear W20394927132018 @default.
- W2039492713 countsByYear W20394927132022 @default.
- W2039492713 countsByYear W20394927132023 @default.
- W2039492713 crossrefType "journal-article" @default.
- W2039492713 hasAuthorship W2039492713A5023927893 @default.
- W2039492713 hasAuthorship W2039492713A5050533134 @default.
- W2039492713 hasAuthorship W2039492713A5079112781 @default.
- W2039492713 hasConcept C100906024 @default.
- W2039492713 hasConcept C105795698 @default.
- W2039492713 hasConcept C124101348 @default.
- W2039492713 hasConcept C138885662 @default.
- W2039492713 hasConcept C148483581 @default.
- W2039492713 hasConcept C153180895 @default.
- W2039492713 hasConcept C154945302 @default.
- W2039492713 hasConcept C162324750 @default.
- W2039492713 hasConcept C176217482 @default.
- W2039492713 hasConcept C177264268 @default.
- W2039492713 hasConcept C199360897 @default.
- W2039492713 hasConcept C21547014 @default.
- W2039492713 hasConcept C2776401178 @default.
- W2039492713 hasConcept C33923547 @default.
- W2039492713 hasConcept C41008148 @default.
- W2039492713 hasConcept C41895202 @default.
- W2039492713 hasConcept C89128539 @default.
- W2039492713 hasConcept C94124525 @default.
- W2039492713 hasConceptScore W2039492713C100906024 @default.
- W2039492713 hasConceptScore W2039492713C105795698 @default.
- W2039492713 hasConceptScore W2039492713C124101348 @default.
- W2039492713 hasConceptScore W2039492713C138885662 @default.
- W2039492713 hasConceptScore W2039492713C148483581 @default.
- W2039492713 hasConceptScore W2039492713C153180895 @default.
- W2039492713 hasConceptScore W2039492713C154945302 @default.
- W2039492713 hasConceptScore W2039492713C162324750 @default.
- W2039492713 hasConceptScore W2039492713C176217482 @default.
- W2039492713 hasConceptScore W2039492713C177264268 @default.
- W2039492713 hasConceptScore W2039492713C199360897 @default.
- W2039492713 hasConceptScore W2039492713C21547014 @default.
- W2039492713 hasConceptScore W2039492713C2776401178 @default.
- W2039492713 hasConceptScore W2039492713C33923547 @default.
- W2039492713 hasConceptScore W2039492713C41008148 @default.
- W2039492713 hasConceptScore W2039492713C41895202 @default.
- W2039492713 hasConceptScore W2039492713C89128539 @default.
- W2039492713 hasConceptScore W2039492713C94124525 @default.
- W2039492713 hasIssue "3" @default.
- W2039492713 hasLocation W20394927131 @default.
- W2039492713 hasOpenAccess W2039492713 @default.
- W2039492713 hasPrimaryLocation W20394927131 @default.
- W2039492713 hasRelatedWork W2111353337 @default.
- W2039492713 hasRelatedWork W2363775966 @default.
- W2039492713 hasRelatedWork W2372127301 @default.
- W2039492713 hasRelatedWork W2374651319 @default.
- W2039492713 hasRelatedWork W2375828317 @default.
- W2039492713 hasRelatedWork W2386078281 @default.
- W2039492713 hasRelatedWork W2391010859 @default.
- W2039492713 hasRelatedWork W2889415370 @default.
- W2039492713 hasRelatedWork W4307883119 @default.
- W2039492713 hasRelatedWork W2345184372 @default.
- W2039492713 hasVolume "37" @default.
- W2039492713 isParatext "false" @default.
- W2039492713 isRetracted "false" @default.
- W2039492713 magId "2039492713" @default.
- W2039492713 workType "article" @default.