FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312875997> ?p ?o ?g. }

• W4312875997 endingPage "129189" @default.
• W4312875997 startingPage "129176" @default.
• W4312875997 abstract "Depression detection from social media texts such as Tweets or Facebook comments could be very beneficial as early detection of depression may even avoid extreme consequences of long-term depression i.e. suicide. In this study, depression intensity classification is performed using a labeled Twitter dataset. Further, this study makes a detailed performance evaluation of four transformer-based pre-trained small language models, particularly those having less than 15 million tunable parameters i.e. Electra Small Generator (ESG), Electra Small Discriminator (ESD), XtremeDistil-L6 (XDL) and Albert Base V2 (ABV) for classification of depression intensity using Tweets. The models are fine-tuned to get the best performance by applying different hyperparameters. The models are tested by classification of depression intensity of labeled tweets for three label classes i.e. ’severe’, ’moderate’, and ’mild’ by downstream fine-tuning the parameters. Evaluation metrics such as accuracy, F1, precision, recall, and specificity are calculated to evaluate the performance of the models. Comparative analysis of these models is also done with a moderately larger model i.e. DistilBert which has 67 million tunable parameters for the same task with the same experimental settings. Results indicate that ESG outperforms all other models including DistilBert due to its better deep contextualized text representation as it gets the best F1 score of 89% with comparatively less training time. This study helps to achieve better classification performance of depression detection as well as to choose the best language model in terms of performance and less training time for Twitter-related downstream NLP tasks." @default.
• W4312875997 created "2023-01-05" @default.
• W4312875997 creator A5005731174 @default.
• W4312875997 creator A5053599078 @default.
• W4312875997 creator A5069021835 @default.
• W4312875997 creator A5073229186 @default.
• W4312875997 creator A5074629800 @default.
• W4312875997 creator A5087270783 @default.
• W4312875997 date "2022-01-01" @default.
• W4312875997 modified "2023-10-05" @default.
• W4312875997 title "Depression Classification From Tweets Using Small Deep Transfer Learning Language Models" @default.
• W4312875997 cites W1537829113 @default.
• W4312875997 cites W2068262947 @default.
• W4312875997 cites W2211796614 @default.
• W4312875997 cites W2413533038 @default.
• W4312875997 cites W2528658358 @default.
• W4312875997 cites W2613843855 @default.
• W4312875997 cites W2786026536 @default.
• W4312875997 cites W2802043748 @default.
• W4312875997 cites W2927148761 @default.
• W4312875997 cites W2946396904 @default.
• W4312875997 cites W2970454332 @default.
• W4312875997 cites W2987972786 @default.
• W4312875997 cites W3013908145 @default.
• W4312875997 cites W3023618320 @default.
• W4312875997 cites W3032158497 @default.
• W4312875997 cites W3033913896 @default.
• W4312875997 cites W3036832155 @default.
• W4312875997 cites W3039554467 @default.
• W4312875997 cites W3087974299 @default.
• W4312875997 cites W3098576111 @default.
• W4312875997 cites W3108841905 @default.
• W4312875997 cites W3114498488 @default.
• W4312875997 cites W3117866035 @default.
• W4312875997 cites W3120217483 @default.
• W4312875997 cites W3128585438 @default.
• W4312875997 cites W3129150560 @default.
• W4312875997 cites W3131775586 @default.
• W4312875997 cites W3136657289 @default.
• W4312875997 cites W3158216587 @default.
• W4312875997 cites W3167856512 @default.
• W4312875997 cites W3167958315 @default.
• W4312875997 cites W3174510164 @default.
• W4312875997 cites W3205067936 @default.
• W4312875997 cites W3211095765 @default.
• W4312875997 cites W4200046541 @default.
• W4312875997 cites W4210254834 @default.
• W4312875997 cites W4210455994 @default.
• W4312875997 cites W4220956908 @default.
• W4312875997 cites W4220967417 @default.
• W4312875997 cites W4224326655 @default.
• W4312875997 cites W4283812015 @default.
• W4312875997 doi "https://doi.org/10.1109/access.2022.3223049" @default.
• W4312875997 hasPublicationYear "2022" @default.
• W4312875997 type Work @default.
• W4312875997 citedByCount "2" @default.
• W4312875997 countsByYear W43128759972023 @default.
• W4312875997 crossrefType "journal-article" @default.
• W4312875997 hasAuthorship W4312875997A5005731174 @default.
• W4312875997 hasAuthorship W4312875997A5053599078 @default.
• W4312875997 hasAuthorship W4312875997A5069021835 @default.
• W4312875997 hasAuthorship W4312875997A5073229186 @default.
• W4312875997 hasAuthorship W4312875997A5074629800 @default.
• W4312875997 hasAuthorship W4312875997A5087270783 @default.
• W4312875997 hasBestOaLocation W43128759971 @default.
• W4312875997 hasConcept C100660578 @default.
• W4312875997 hasConcept C108583219 @default.
• W4312875997 hasConcept C119857082 @default.
• W4312875997 hasConcept C137293760 @default.
• W4312875997 hasConcept C148524875 @default.
• W4312875997 hasConcept C150899416 @default.
• W4312875997 hasConcept C154945302 @default.
• W4312875997 hasConcept C15744967 @default.
• W4312875997 hasConcept C180747234 @default.
• W4312875997 hasConcept C204321447 @default.
• W4312875997 hasConcept C2779803651 @default.
• W4312875997 hasConcept C41008148 @default.
• W4312875997 hasConcept C66402592 @default.
• W4312875997 hasConcept C76155785 @default.
• W4312875997 hasConcept C8642999 @default.
• W4312875997 hasConcept C94915269 @default.
• W4312875997 hasConceptScore W4312875997C100660578 @default.
• W4312875997 hasConceptScore W4312875997C108583219 @default.
• W4312875997 hasConceptScore W4312875997C119857082 @default.
• W4312875997 hasConceptScore W4312875997C137293760 @default.
• W4312875997 hasConceptScore W4312875997C148524875 @default.
• W4312875997 hasConceptScore W4312875997C150899416 @default.
• W4312875997 hasConceptScore W4312875997C154945302 @default.
• W4312875997 hasConceptScore W4312875997C15744967 @default.
• W4312875997 hasConceptScore W4312875997C180747234 @default.
• W4312875997 hasConceptScore W4312875997C204321447 @default.
• W4312875997 hasConceptScore W4312875997C2779803651 @default.
• W4312875997 hasConceptScore W4312875997C41008148 @default.
• W4312875997 hasConceptScore W4312875997C66402592 @default.
• W4312875997 hasConceptScore W4312875997C76155785 @default.
• W4312875997 hasConceptScore W4312875997C8642999 @default.
• W4312875997 hasConceptScore W4312875997C94915269 @default.
• W4312875997 hasLocation W43128759971 @default.

• next