Matches in SemOpenAlex for { <https://semopenalex.org/work/W3003152172> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W3003152172 endingPage "319" @default.
- W3003152172 startingPage "311" @default.
- W3003152172 abstract "Traditional bag-of-words (BOW) draws advantage from distributional theory to represent document. The drawback of BOW is high dimensionality. However, this disadvantage has been solved by various dimensionality reduction techniques such as principal component analysis (PCA) or singular value decomposition (SVD). On the other hand, neural network-based approaches do not suffer from dimensionality problem. They can represent documents or words with shorter vectors. Especially, recurrent neural network (RNN) architectures have gained big attractions for short sequence representation. In this study, we compared traditional representation (BOW) with RNN-based architecture in terms of capability of solving sentiment problem. Traditional methods represent text with BOW approach and produce one-hot encoding. Further well-known linear machine learning algorithms such as logistic regression and Naive Bayes classifier could learn the decisive boundary in the data points. On the other hand, RNN-based models take text as a sequence of words and transform the sequence using hidden and recurrent states. At the end, the transformation finally represents input text with dense and short vector. On top of it, a final neural layer maps this dense and short representation to a sentiment of a list. We discussed our findings by conducting several experiments in depth. We comprehensively compared traditional representation and deep learning models by using a sentiment benchmark dataset of five different topics such as books and kitchen in Turkish language." @default.
- W3003152172 created "2020-01-30" @default.
- W3003152172 creator A5015457657 @default.
- W3003152172 date "2020-01-01" @default.
- W3003152172 modified "2023-09-25" @default.
- W3003152172 title "Comparing Deep Neural Networks to Traditional Models for Sentiment Analysis in Turkish Language" @default.
- W3003152172 cites W2058982198 @default.
- W3003152172 cites W2064675550 @default.
- W3003152172 cites W2107878631 @default.
- W3003152172 cites W2124388587 @default.
- W3003152172 cites W2160660844 @default.
- W3003152172 cites W2166706824 @default.
- W3003152172 cites W2250539671 @default.
- W3003152172 cites W2612769033 @default.
- W3003152172 cites W2963052942 @default.
- W3003152172 doi "https://doi.org/10.1007/978-981-15-1216-2_12" @default.
- W3003152172 hasPublicationYear "2020" @default.
- W3003152172 type Work @default.
- W3003152172 sameAs 3003152172 @default.
- W3003152172 citedByCount "10" @default.
- W3003152172 countsByYear W30031521722021 @default.
- W3003152172 countsByYear W30031521722022 @default.
- W3003152172 countsByYear W30031521722023 @default.
- W3003152172 crossrefType "book-chapter" @default.
- W3003152172 hasAuthorship W3003152172A5015457657 @default.
- W3003152172 hasConcept C108583219 @default.
- W3003152172 hasConcept C111030470 @default.
- W3003152172 hasConcept C119857082 @default.
- W3003152172 hasConcept C12267149 @default.
- W3003152172 hasConcept C13280743 @default.
- W3003152172 hasConcept C13672336 @default.
- W3003152172 hasConcept C147168706 @default.
- W3003152172 hasConcept C153180895 @default.
- W3003152172 hasConcept C154945302 @default.
- W3003152172 hasConcept C185798385 @default.
- W3003152172 hasConcept C205649164 @default.
- W3003152172 hasConcept C22789450 @default.
- W3003152172 hasConcept C41008148 @default.
- W3003152172 hasConcept C50644808 @default.
- W3003152172 hasConcept C52001869 @default.
- W3003152172 hasConcept C66402592 @default.
- W3003152172 hasConcept C70518039 @default.
- W3003152172 hasConceptScore W3003152172C108583219 @default.
- W3003152172 hasConceptScore W3003152172C111030470 @default.
- W3003152172 hasConceptScore W3003152172C119857082 @default.
- W3003152172 hasConceptScore W3003152172C12267149 @default.
- W3003152172 hasConceptScore W3003152172C13280743 @default.
- W3003152172 hasConceptScore W3003152172C13672336 @default.
- W3003152172 hasConceptScore W3003152172C147168706 @default.
- W3003152172 hasConceptScore W3003152172C153180895 @default.
- W3003152172 hasConceptScore W3003152172C154945302 @default.
- W3003152172 hasConceptScore W3003152172C185798385 @default.
- W3003152172 hasConceptScore W3003152172C205649164 @default.
- W3003152172 hasConceptScore W3003152172C22789450 @default.
- W3003152172 hasConceptScore W3003152172C41008148 @default.
- W3003152172 hasConceptScore W3003152172C50644808 @default.
- W3003152172 hasConceptScore W3003152172C52001869 @default.
- W3003152172 hasConceptScore W3003152172C66402592 @default.
- W3003152172 hasConceptScore W3003152172C70518039 @default.
- W3003152172 hasLocation W30031521721 @default.
- W3003152172 hasOpenAccess W3003152172 @default.
- W3003152172 hasPrimaryLocation W30031521721 @default.
- W3003152172 hasRelatedWork W2741836081 @default.
- W3003152172 hasRelatedWork W2803710604 @default.
- W3003152172 hasRelatedWork W3192794374 @default.
- W3003152172 hasRelatedWork W3213901898 @default.
- W3003152172 hasRelatedWork W4205958290 @default.
- W3003152172 hasRelatedWork W4254256218 @default.
- W3003152172 hasRelatedWork W4311106074 @default.
- W3003152172 hasRelatedWork W4327531511 @default.
- W3003152172 hasRelatedWork W4327831767 @default.
- W3003152172 hasRelatedWork W4362613237 @default.
- W3003152172 isParatext "false" @default.
- W3003152172 isRetracted "false" @default.
- W3003152172 magId "3003152172" @default.
- W3003152172 workType "book-chapter" @default.