Matches in SemOpenAlex for { <https://semopenalex.org/work/W2955300558> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W2955300558 abstract "Deep learning has recently revolutionised many fields of natural language processing but has not yet been applied to emotion recognition. Most recent studies of emotion recognition on tweets used simple classifiers on a combination of bag-of-words and human-engineered features. Hence, we worked on improving emotion-recognition algorithms using neural networks. To this end, we created three large emotion-labelled data sets corresponding to Ekman's, Plutchik's, and POMS's emotions by exploiting Twitter's popular self-annotation mechanism — hashtags. We compared the performance of bag-of-words and latent semantic indexing models with the performance of neural networks. We trained several word- and character-based, recurrent and convolutional neural networks. Further, we investigated the transferability of final hidden state representations of neural networks: how appropriate is the representation trained on one classification for recognising another one? Finally, we developed a single model for recognising all three emotion classifications from a shared representation.We show that neural networks can surpass traditional text classification approaches for emotion recognition. Recurrent neural network working directly on characters without any text preprocessing in a completely end-to-end fashion was the most successful architecture. Although models trained on single data sets have revealed poor transferability, we improved the generality of final hidden state representation in the unison model. When training the unison model, the standard training heuristic yielded unbalanced performance, due to the vast difference in data set sizes. However, the newly proposed training strategy produced a unison model with performance comparable to that of single models." @default.
- W2955300558 created "2019-07-12" @default.
- W2955300558 creator A5030928597 @default.
- W2955300558 date "2019-05-20" @default.
- W2955300558 modified "2023-09-27" @default.
- W2955300558 title "Emotion Recognition on Twitter Using Neural Networks" @default.
- W2955300558 hasPublicationYear "2019" @default.
- W2955300558 type Work @default.
- W2955300558 sameAs 2955300558 @default.
- W2955300558 citedByCount "0" @default.
- W2955300558 crossrefType "dissertation" @default.
- W2955300558 hasAuthorship W2955300558A5030928597 @default.
- W2955300558 hasConcept C108583219 @default.
- W2955300558 hasConcept C119857082 @default.
- W2955300558 hasConcept C121332964 @default.
- W2955300558 hasConcept C153180895 @default.
- W2955300558 hasConcept C154945302 @default.
- W2955300558 hasConcept C15744967 @default.
- W2955300558 hasConcept C173801870 @default.
- W2955300558 hasConcept C17744445 @default.
- W2955300558 hasConcept C199539241 @default.
- W2955300558 hasConcept C204321447 @default.
- W2955300558 hasConcept C24890656 @default.
- W2955300558 hasConcept C2776359362 @default.
- W2955300558 hasConcept C2780304638 @default.
- W2955300558 hasConcept C2780767217 @default.
- W2955300558 hasConcept C34736171 @default.
- W2955300558 hasConcept C41008148 @default.
- W2955300558 hasConcept C50644808 @default.
- W2955300558 hasConcept C542102704 @default.
- W2955300558 hasConcept C81363708 @default.
- W2955300558 hasConcept C94625758 @default.
- W2955300558 hasConceptScore W2955300558C108583219 @default.
- W2955300558 hasConceptScore W2955300558C119857082 @default.
- W2955300558 hasConceptScore W2955300558C121332964 @default.
- W2955300558 hasConceptScore W2955300558C153180895 @default.
- W2955300558 hasConceptScore W2955300558C154945302 @default.
- W2955300558 hasConceptScore W2955300558C15744967 @default.
- W2955300558 hasConceptScore W2955300558C173801870 @default.
- W2955300558 hasConceptScore W2955300558C17744445 @default.
- W2955300558 hasConceptScore W2955300558C199539241 @default.
- W2955300558 hasConceptScore W2955300558C204321447 @default.
- W2955300558 hasConceptScore W2955300558C24890656 @default.
- W2955300558 hasConceptScore W2955300558C2776359362 @default.
- W2955300558 hasConceptScore W2955300558C2780304638 @default.
- W2955300558 hasConceptScore W2955300558C2780767217 @default.
- W2955300558 hasConceptScore W2955300558C34736171 @default.
- W2955300558 hasConceptScore W2955300558C41008148 @default.
- W2955300558 hasConceptScore W2955300558C50644808 @default.
- W2955300558 hasConceptScore W2955300558C542102704 @default.
- W2955300558 hasConceptScore W2955300558C81363708 @default.
- W2955300558 hasConceptScore W2955300558C94625758 @default.
- W2955300558 hasLocation W29553005581 @default.
- W2955300558 hasOpenAccess W2955300558 @default.
- W2955300558 hasPrimaryLocation W29553005581 @default.
- W2955300558 hasRelatedWork W2741630455 @default.
- W2955300558 hasRelatedWork W2751675085 @default.
- W2955300558 hasRelatedWork W2788487042 @default.
- W2955300558 hasRelatedWork W2788824299 @default.
- W2955300558 hasRelatedWork W2885068312 @default.
- W2955300558 hasRelatedWork W2893051100 @default.
- W2955300558 hasRelatedWork W2921113485 @default.
- W2955300558 hasRelatedWork W2936485327 @default.
- W2955300558 hasRelatedWork W2983165789 @default.
- W2955300558 hasRelatedWork W3009344359 @default.
- W2955300558 hasRelatedWork W3012040005 @default.
- W2955300558 hasRelatedWork W3014989966 @default.
- W2955300558 hasRelatedWork W3035652936 @default.
- W2955300558 hasRelatedWork W3046460324 @default.
- W2955300558 hasRelatedWork W3085812513 @default.
- W2955300558 hasRelatedWork W3086923691 @default.
- W2955300558 hasRelatedWork W3097279572 @default.
- W2955300558 hasRelatedWork W3101124347 @default.
- W2955300558 hasRelatedWork W3194150877 @default.
- W2955300558 hasRelatedWork W3198516396 @default.
- W2955300558 isParatext "false" @default.
- W2955300558 isRetracted "false" @default.
- W2955300558 magId "2955300558" @default.
- W2955300558 workType "dissertation" @default.