Matches in SemOpenAlex for { <https://semopenalex.org/work/W3108724972> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W3108724972 abstract "Exponential growths of social media and micro-blogging sites not only provide platforms for empowering freedom of expressions and individual voices, but also enables people to express anti-social behavior like online harassment, cyberbul-lying, and hate speech. Numerous works have been proposed to utilize these data for social and anti-social behavior analysis, document characterization, and sentiment analysis by predicting the contexts mostly for highly resourced languages like English. However, some languages are under-resources, e.g., South Asian languages like Bengali, Tamil, Assamese, Malayalam, that lack of computational resources for natural language processing. In this paper <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>1</sup> , we provide several classification benchmarks for Bengali, an under-resourced language. We prepared three datasets of expressing hate, commonly used topics, and opinions for hate speech detection, document classification, and sentiment analysis. We built the largest Bengali word embedding models to date based on 250 million articles, which we call BengFastText. We perform three experiments, covering document classification, sentiment analysis, and hate speech detection. We incorporate word embeddings into a Multichannel Convolutional-LSTM (MC-LSTM) network for predicting different types of hate speech, document classification, and sentiment analysis. Experiments demonstrate that BengFastText can capture the semantics of words from respective contexts correctly. Evaluations against several baseline embedding models, e.g., Word2Vec and GloVe yield up to 92.30%, 82.25%, and 90.45% F1-scores in case of document classification, sentiment analysis, and hate speech detection, respectively during 5-fold cross-validation tests." @default.
- W3108724972 created "2020-12-07" @default.
- W3108724972 creator A5011466629 @default.
- W3108724972 creator A5024482506 @default.
- W3108724972 creator A5036503167 @default.
- W3108724972 creator A5041317183 @default.
- W3108724972 date "2020-10-01" @default.
- W3108724972 modified "2023-09-30" @default.
- W3108724972 title "Classification Benchmarks for Under-resourced Bengali Language based on Multichannel Convolutional-LSTM Network" @default.
- W3108724972 cites W2091746061 @default.
- W3108724972 cites W2100714283 @default.
- W3108724972 cites W2250539671 @default.
- W3108724972 cites W2285811659 @default.
- W3108724972 cites W2473555522 @default.
- W3108724972 cites W2493916176 @default.
- W3108724972 cites W2591259438 @default.
- W3108724972 cites W2591264712 @default.
- W3108724972 cites W2595653137 @default.
- W3108724972 cites W2611912747 @default.
- W3108724972 cites W2740382415 @default.
- W3108724972 cites W2794585602 @default.
- W3108724972 cites W2800708042 @default.
- W3108724972 cites W2806872289 @default.
- W3108724972 cites W2887782043 @default.
- W3108724972 cites W2945808722 @default.
- W3108724972 cites W2954264738 @default.
- W3108724972 cites W3018024187 @default.
- W3108724972 cites W3019581400 @default.
- W3108724972 cites W68293321 @default.
- W3108724972 doi "https://doi.org/10.1109/dsaa49011.2020.00053" @default.
- W3108724972 hasPublicationYear "2020" @default.
- W3108724972 type Work @default.
- W3108724972 sameAs 3108724972 @default.
- W3108724972 citedByCount "19" @default.
- W3108724972 countsByYear W31087249722021 @default.
- W3108724972 countsByYear W31087249722022 @default.
- W3108724972 countsByYear W31087249722023 @default.
- W3108724972 crossrefType "proceedings-article" @default.
- W3108724972 hasAuthorship W3108724972A5011466629 @default.
- W3108724972 hasAuthorship W3108724972A5024482506 @default.
- W3108724972 hasAuthorship W3108724972A5036503167 @default.
- W3108724972 hasAuthorship W3108724972A5041317183 @default.
- W3108724972 hasBestOaLocation W31087249723 @default.
- W3108724972 hasConcept C123406163 @default.
- W3108724972 hasConcept C136764020 @default.
- W3108724972 hasConcept C137546455 @default.
- W3108724972 hasConcept C138885662 @default.
- W3108724972 hasConcept C154945302 @default.
- W3108724972 hasConcept C176982825 @default.
- W3108724972 hasConcept C19235068 @default.
- W3108724972 hasConcept C204321447 @default.
- W3108724972 hasConcept C2776461190 @default.
- W3108724972 hasConcept C2777462759 @default.
- W3108724972 hasConcept C2777834912 @default.
- W3108724972 hasConcept C28490314 @default.
- W3108724972 hasConcept C41008148 @default.
- W3108724972 hasConcept C41608201 @default.
- W3108724972 hasConcept C41895202 @default.
- W3108724972 hasConcept C518677369 @default.
- W3108724972 hasConcept C66402592 @default.
- W3108724972 hasConcept C90805587 @default.
- W3108724972 hasConceptScore W3108724972C123406163 @default.
- W3108724972 hasConceptScore W3108724972C136764020 @default.
- W3108724972 hasConceptScore W3108724972C137546455 @default.
- W3108724972 hasConceptScore W3108724972C138885662 @default.
- W3108724972 hasConceptScore W3108724972C154945302 @default.
- W3108724972 hasConceptScore W3108724972C176982825 @default.
- W3108724972 hasConceptScore W3108724972C19235068 @default.
- W3108724972 hasConceptScore W3108724972C204321447 @default.
- W3108724972 hasConceptScore W3108724972C2776461190 @default.
- W3108724972 hasConceptScore W3108724972C2777462759 @default.
- W3108724972 hasConceptScore W3108724972C2777834912 @default.
- W3108724972 hasConceptScore W3108724972C28490314 @default.
- W3108724972 hasConceptScore W3108724972C41008148 @default.
- W3108724972 hasConceptScore W3108724972C41608201 @default.
- W3108724972 hasConceptScore W3108724972C41895202 @default.
- W3108724972 hasConceptScore W3108724972C518677369 @default.
- W3108724972 hasConceptScore W3108724972C66402592 @default.
- W3108724972 hasConceptScore W3108724972C90805587 @default.
- W3108724972 hasLocation W31087249721 @default.
- W3108724972 hasLocation W31087249722 @default.
- W3108724972 hasLocation W31087249723 @default.
- W3108724972 hasOpenAccess W3108724972 @default.
- W3108724972 hasPrimaryLocation W31087249721 @default.
- W3108724972 hasRelatedWork W2591546050 @default.
- W3108724972 hasRelatedWork W2938810646 @default.
- W3108724972 hasRelatedWork W3017052291 @default.
- W3108724972 hasRelatedWork W3036348210 @default.
- W3108724972 hasRelatedWork W3128570734 @default.
- W3108724972 hasRelatedWork W4287363563 @default.
- W3108724972 hasRelatedWork W4287815772 @default.
- W3108724972 hasRelatedWork W4306877294 @default.
- W3108724972 hasRelatedWork W4319988551 @default.
- W3108724972 hasRelatedWork W4362557444 @default.
- W3108724972 isParatext "false" @default.
- W3108724972 isRetracted "false" @default.
- W3108724972 magId "3108724972" @default.
- W3108724972 workType "article" @default.