Boosting SpLSA for Text Classification

Simple item page
dc.catalogadorgrr
dc.contributor.authorHurtado, Julio
dc.contributor.authorMendoza, Marcelo
dc.contributor.authorNanculef, Ricardo
dc.date.accessioned2024-05-28T21:12:58Z
dc.date.available2024-05-28T21:12:58Z
dc.date.issued2017
dc.description.abstractText classification is a challenge in document labeling tasks such as spam filtering and sentiment analysis. Due to the descriptive richness of generative approaches such as probabilistic Latent Semantic Analysis (pLSA), documents are often modeled using these kind of strategies. Recently, a supervised extension of pLSA (spLSA [10]) has been proposed for human action recognition in the context of computer vision. In this paper we propose to extend spLSA to be used in text classification. We do this by introducing two extensions in spLSA: (a) Regularized spLSA, and (b) Label uncertainty in spLSA. We evaluate the proposal in spam filtering and sentiment analysis classification tasks. Experimental results show that spLSA outperforms pLSA in both tasks. In addition, our extensions favor fast convergence suggesting that the use of spLSA may reduce training time while achieving the same accuracy as more expensive methods such as sLDA or SVM.
dc.fuente.origenConveris
dc.identifier.converisid1
dc.identifier.doi10.1007/978-3-319-52277-7_18
dc.identifier.eissn1611-3349
dc.identifier.issn0302-9743
dc.identifier.scopusidSCOPUS_ID:2-s2.0-85013474291
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/85937
dc.identifier.wosidWOS:000418399200018
dc.language.isoen
dc.nota.accesosin adjunto
dc.pagina.final149
dc.pagina.inicio142
dc.relation.ispartofPROGRESS IN PATTERN RECOGNITION, IMAGE ANALYSIS, COMPUTER VISION, AND APPLICATIONS, CIARP 2016
dc.revistaLecture Notes in Computer Science
dc.rightsacceso abierto
dc.titleBoosting SpLSA for Text Classification
dc.typecomunicación de congreso
dc.volumen10125
sipa.trazabilidadConveris;20-07-2021
Files
Collections
Artículos de conferencia