FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4382404085> ?p ?o ?g. }

• W4382404085 abstract "During the past years, we have seen a steady increase in the number of social networks worldwide. Among them, Twitter has consolidated its position as one of the most influential social platforms, with Brazilian Portuguese speakers holding the fifth position in the number of users. Due to the informal linguistic style of tweets, the discovery of information in such an environment poses a challenge to Natural Language Processing (NLP) tasks such as sentiment analysis. In this work, we state sentiment analysis as a binary (positive and negative) and multiclass (positive, negative, and neutral) classification task at the Portuguese-written tweet level. Following a feature extraction approach, embeddings are initially gathered for a tweet and then given as input to learning a classifier. This study was designed to evaluate the effectiveness of different word representations, from the original pre-trained language model to continued pre-training strategies, to improve the predictive performance of sentiment classification, using three different classifier algorithms and eight Portuguese tweets datasets. Because of the lack of a language model specific to Brazilian Portuguese tweets, we have expanded our evaluation to consider six different embeddings: fastText, GloVe, Word2Vec, BERT-multilingual (mBERT), BERTweet, and BERTimbau. The experiments showed that embeddings trained from scratch solely using the target Portuguese language, BERTimbau, outperform the static representations, fastText, GloVe, and Word2Vec, and the Transformer-based models BERT multilingual and BERTweet. In addition, we show that extracting the contextualized embedding without any adjustment to the pre-trained language model is the best approach for most datasets." @default.
• W4382404085 created "2023-06-29" @default.
• W4382404085 creator A5045549996 @default.
• W4382404085 creator A5051287860 @default.
• W4382404085 creator A5057541548 @default.
• W4382404085 creator A5061481927 @default.
• W4382404085 creator A5078146915 @default.
• W4382404085 date "2023-06-28" @default.
• W4382404085 modified "2023-10-05" @default.
• W4382404085 title "Sentiment analysis in Portuguese tweets: an evaluation of diverse word representation models" @default.
• W4382404085 cites W1505786308 @default.
• W4382404085 cites W195726863 @default.
• W4382404085 cites W1970464092 @default.
• W4382404085 cites W1992205670 @default.
• W4382404085 cites W2021891520 @default.
• W4382404085 cites W2040467972 @default.
• W4382404085 cites W2049434052 @default.
• W4382404085 cites W2066180975 @default.
• W4382404085 cites W2079224581 @default.
• W4382404085 cites W2080672283 @default.
• W4382404085 cites W2084046180 @default.
• W4382404085 cites W2099813784 @default.
• W4382404085 cites W2121879602 @default.
• W4382404085 cites W2204520100 @default.
• W4382404085 cites W2250539671 @default.
• W4382404085 cites W2250879510 @default.
• W4382404085 cites W2267835966 @default.
• W4382404085 cites W2289507780 @default.
• W4382404085 cites W2341298806 @default.
• W4382404085 cites W2475024326 @default.
• W4382404085 cites W2479861293 @default.
• W4382404085 cites W2493916176 @default.
• W4382404085 cites W2504814044 @default.
• W4382404085 cites W2509750308 @default.
• W4382404085 cites W2529691835 @default.
• W4382404085 cites W2550663623 @default.
• W4382404085 cites W2618584523 @default.
• W4382404085 cites W2740093185 @default.
• W4382404085 cites W2769280420 @default.
• W4382404085 cites W2772803004 @default.
• W4382404085 cites W2888163711 @default.
• W4382404085 cites W2888435257 @default.
• W4382404085 cites W2888443133 @default.
• W4382404085 cites W2890117297 @default.
• W4382404085 cites W2894475507 @default.
• W4382404085 cites W2923534230 @default.
• W4382404085 cites W2947114307 @default.
• W4382404085 cites W2963120507 @default.
• W4382404085 cites W2963341956 @default.
• W4382404085 cites W2963809228 @default.
• W4382404085 cites W2970641574 @default.
• W4382404085 cites W2971475926 @default.
• W4382404085 cites W2979826702 @default.
• W4382404085 cites W2980481399 @default.
• W4382404085 cites W2986154550 @default.
• W4382404085 cites W2987294427 @default.
• W4382404085 cites W2988702593 @default.
• W4382404085 cites W3002034200 @default.
• W4382404085 cites W3007326938 @default.
• W4382404085 cites W3023092508 @default.
• W4382404085 cites W3024459502 @default.
• W4382404085 cites W3034238904 @default.
• W4382404085 cites W3036466189 @default.
• W4382404085 cites W3037032032 @default.
• W4382404085 cites W3038033387 @default.
• W4382404085 cites W3082523222 @default.
• W4382404085 cites W3094561931 @default.
• W4382404085 cites W3096266342 @default.
• W4382404085 cites W3097373293 @default.
• W4382404085 cites W3097603371 @default.
• W4382404085 cites W3104186312 @default.
• W4382404085 cites W3114950584 @default.
• W4382404085 cites W3117864197 @default.
• W4382404085 cites W3121269699 @default.
• W4382404085 cites W3128381090 @default.
• W4382404085 cites W3133702157 @default.
• W4382404085 cites W3150290404 @default.
• W4382404085 cites W3157526402 @default.
• W4382404085 cites W4211036025 @default.
• W4382404085 cites W4236531915 @default.
• W4382404085 cites W4309197929 @default.
• W4382404085 cites W4319989526 @default.
• W4382404085 doi "https://doi.org/10.1007/s10579-023-09661-4" @default.
• W4382404085 hasPublicationYear "2023" @default.
• W4382404085 type Work @default.
• W4382404085 citedByCount "0" @default.
• W4382404085 crossrefType "journal-article" @default.
• W4382404085 hasAuthorship W4382404085A5045549996 @default.
• W4382404085 hasAuthorship W4382404085A5051287860 @default.
• W4382404085 hasAuthorship W4382404085A5057541548 @default.
• W4382404085 hasAuthorship W4382404085A5061481927 @default.
• W4382404085 hasAuthorship W4382404085A5078146915 @default.
• W4382404085 hasConcept C136764020 @default.
• W4382404085 hasConcept C137293760 @default.
• W4382404085 hasConcept C138885662 @default.
• W4382404085 hasConcept C154945302 @default.
• W4382404085 hasConcept C204321447 @default.
• W4382404085 hasConcept C2776461190 @default.
• W4382404085 hasConcept C2777462759 @default.
• W4382404085 hasConcept C35219183 @default.

• next