Matches in SemOpenAlex for { <https://semopenalex.org/work/W4281785281> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W4281785281 endingPage "557" @default.
- W4281785281 startingPage "547" @default.
- W4281785281 abstract "Data imbalance in datasets is a common issue where the number of instances in one or more categories far exceeds the others, so is the case with the educational domain. Collecting feedback on a course on a large scale and the lack of publicly available datasets in this domain limits models’ performance, especially for deep neural network based models which are data hungry. A model trained on such an imbalanced dataset would naturally favor the majority class. However, the minority class could be critical for decision-making in prediction systems, and therefore it is usually desirable to train a model with equally high class-level accuracy. This paper addresses the data imbalance issue for the sentiment analysis of users’ opinions task on two educational feedback datasets utilizing synthetic text generation deep learning models. Two state-of-the-art text generation GAN models namely CatGAN and SentiGAN, are employed for synthesizing text used to balance the highly imbalanced datasets in this study. Particular emphasis is given to the diversity of synthetically generated samples for populating minority classes. Experimental results on highly imbalanced datasets show significant improvement in models’ performance on CR23K and CR100K after balancing with synthetic data for the sentiment classification task." @default.
- W4281785281 created "2022-06-13" @default.
- W4281785281 creator A5011104783 @default.
- W4281785281 creator A5044015235 @default.
- W4281785281 creator A5045728872 @default.
- W4281785281 creator A5052954560 @default.
- W4281785281 creator A5053152000 @default.
- W4281785281 date "2022-09-01" @default.
- W4281785281 modified "2023-10-01" @default.
- W4281785281 title "The impact of synthetic text generation for sentiment analysis using GAN based models" @default.
- W4281785281 cites W2808437126 @default.
- W4281785281 cites W2960680116 @default.
- W4281785281 cites W2963248348 @default.
- W4281785281 cites W2963456134 @default.
- W4281785281 cites W2964268978 @default.
- W4281785281 cites W2998123743 @default.
- W4281785281 cites W3017340784 @default.
- W4281785281 cites W3035269559 @default.
- W4281785281 cites W3047386186 @default.
- W4281785281 cites W3080996308 @default.
- W4281785281 cites W3090154305 @default.
- W4281785281 cites W3109345528 @default.
- W4281785281 cites W3120846044 @default.
- W4281785281 cites W3124821295 @default.
- W4281785281 cites W3135797089 @default.
- W4281785281 cites W3151498616 @default.
- W4281785281 cites W3159506165 @default.
- W4281785281 cites W3163548027 @default.
- W4281785281 cites W4226049555 @default.
- W4281785281 cites W4285288100 @default.
- W4281785281 doi "https://doi.org/10.1016/j.eij.2022.05.006" @default.
- W4281785281 hasPublicationYear "2022" @default.
- W4281785281 type Work @default.
- W4281785281 citedByCount "9" @default.
- W4281785281 countsByYear W42817852812023 @default.
- W4281785281 crossrefType "journal-article" @default.
- W4281785281 hasAuthorship W4281785281A5011104783 @default.
- W4281785281 hasAuthorship W4281785281A5044015235 @default.
- W4281785281 hasAuthorship W4281785281A5045728872 @default.
- W4281785281 hasAuthorship W4281785281A5052954560 @default.
- W4281785281 hasAuthorship W4281785281A5053152000 @default.
- W4281785281 hasBestOaLocation W42817852811 @default.
- W4281785281 hasConcept C108583219 @default.
- W4281785281 hasConcept C119857082 @default.
- W4281785281 hasConcept C124101348 @default.
- W4281785281 hasConcept C134306372 @default.
- W4281785281 hasConcept C154945302 @default.
- W4281785281 hasConcept C162324750 @default.
- W4281785281 hasConcept C187736073 @default.
- W4281785281 hasConcept C2777212361 @default.
- W4281785281 hasConcept C2780451532 @default.
- W4281785281 hasConcept C33923547 @default.
- W4281785281 hasConcept C36503486 @default.
- W4281785281 hasConcept C41008148 @default.
- W4281785281 hasConcept C66402592 @default.
- W4281785281 hasConceptScore W4281785281C108583219 @default.
- W4281785281 hasConceptScore W4281785281C119857082 @default.
- W4281785281 hasConceptScore W4281785281C124101348 @default.
- W4281785281 hasConceptScore W4281785281C134306372 @default.
- W4281785281 hasConceptScore W4281785281C154945302 @default.
- W4281785281 hasConceptScore W4281785281C162324750 @default.
- W4281785281 hasConceptScore W4281785281C187736073 @default.
- W4281785281 hasConceptScore W4281785281C2777212361 @default.
- W4281785281 hasConceptScore W4281785281C2780451532 @default.
- W4281785281 hasConceptScore W4281785281C33923547 @default.
- W4281785281 hasConceptScore W4281785281C36503486 @default.
- W4281785281 hasConceptScore W4281785281C41008148 @default.
- W4281785281 hasConceptScore W4281785281C66402592 @default.
- W4281785281 hasIssue "3" @default.
- W4281785281 hasLocation W42817852811 @default.
- W4281785281 hasLocation W42817852812 @default.
- W4281785281 hasLocation W42817852813 @default.
- W4281785281 hasOpenAccess W4281785281 @default.
- W4281785281 hasPrimaryLocation W42817852811 @default.
- W4281785281 hasRelatedWork W3014300295 @default.
- W4281785281 hasRelatedWork W3080191145 @default.
- W4281785281 hasRelatedWork W3192794374 @default.
- W4281785281 hasRelatedWork W4223943233 @default.
- W4281785281 hasRelatedWork W4225161397 @default.
- W4281785281 hasRelatedWork W4312200629 @default.
- W4281785281 hasRelatedWork W4360585206 @default.
- W4281785281 hasRelatedWork W4364306694 @default.
- W4281785281 hasRelatedWork W4380075502 @default.
- W4281785281 hasRelatedWork W4380086463 @default.
- W4281785281 hasVolume "23" @default.
- W4281785281 isParatext "false" @default.
- W4281785281 isRetracted "false" @default.
- W4281785281 workType "article" @default.