Matches in SemOpenAlex for { <https://semopenalex.org/work/W3177332149> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W3177332149 abstract "Abstract Tweets mentioning medications are valuable for efforts in digital epidemiology to supplement traditional methods of monitoring public health. A major obstacle, however, is to differentiate them from the large majority of tweets on other topics posted in a user’s timeline: solving the infamous ‘needle in a haystack’ problem. While deep learning models have significantly improved classification, their performance and inference processing time remain low on extremely imbalanced corpora where the tweets of interest are less than 1% of all tweets. In this study, we empirically evaluate under-sampling, fine-tuning, and filtering heuristics to train such classifiers. Using a corpus of 212 Twitter timelines (181,607 tweets with only 0.2% tweets mentioning a medication), our results show that combining these heuristics is necessary to impact the classifier’s performance. In our intrinsic evaluation, a classifier based on a lexicon and a BERT-base neural network achieved a 0.838 F1-score, a score similar to the ones of the best existing classifier, but it processed the corpus 28 times faster - a positive result, since processing speed is still a roadblock to deploying classifiers on large cohorts of Twitter users needed for pharmacovigilance. In our extrinsic evaluation, our classifier helped a labeler to extract the spans of medications more accurately and achieved a 0.76 Strict F1-score. To the best of our knowledge, this is the first evaluation of medications extraction in Twitter timelines and it establishes the first benchmark for future studies." @default.
- W3177332149 created "2021-07-05" @default.
- W3177332149 creator A5022014033 @default.
- W3177332149 creator A5040948702 @default.
- W3177332149 creator A5043998239 @default.
- W3177332149 creator A5068908108 @default.
- W3177332149 date "2021-02-12" @default.
- W3177332149 modified "2023-10-16" @default.
- W3177332149 title "Addressing Extreme Imbalance for Detecting Medications Mentioned in Twitter User Timelines" @default.
- W3177332149 cites W2078638446 @default.
- W3177332149 cites W2252278997 @default.
- W3177332149 cites W2556166063 @default.
- W3177332149 cites W2562319768 @default.
- W3177332149 cites W2736989773 @default.
- W3177332149 cites W2754000910 @default.
- W3177332149 cites W2953902152 @default.
- W3177332149 cites W2955854688 @default.
- W3177332149 cites W2976193469 @default.
- W3177332149 cites W4243367342 @default.
- W3177332149 doi "https://doi.org/10.1101/2021.02.09.21251453" @default.
- W3177332149 hasPublicationYear "2021" @default.
- W3177332149 type Work @default.
- W3177332149 sameAs 3177332149 @default.
- W3177332149 citedByCount "0" @default.
- W3177332149 crossrefType "posted-content" @default.
- W3177332149 hasAuthorship W3177332149A5022014033 @default.
- W3177332149 hasAuthorship W3177332149A5040948702 @default.
- W3177332149 hasAuthorship W3177332149A5043998239 @default.
- W3177332149 hasAuthorship W3177332149A5068908108 @default.
- W3177332149 hasBestOaLocation W31773321491 @default.
- W3177332149 hasConcept C105795698 @default.
- W3177332149 hasConcept C111919701 @default.
- W3177332149 hasConcept C119857082 @default.
- W3177332149 hasConcept C127705205 @default.
- W3177332149 hasConcept C136764020 @default.
- W3177332149 hasConcept C148524875 @default.
- W3177332149 hasConcept C154945302 @default.
- W3177332149 hasConcept C204321447 @default.
- W3177332149 hasConcept C23123220 @default.
- W3177332149 hasConcept C2776214188 @default.
- W3177332149 hasConcept C2778121359 @default.
- W3177332149 hasConcept C33923547 @default.
- W3177332149 hasConcept C41008148 @default.
- W3177332149 hasConcept C4438859 @default.
- W3177332149 hasConcept C518677369 @default.
- W3177332149 hasConcept C95623464 @default.
- W3177332149 hasConceptScore W3177332149C105795698 @default.
- W3177332149 hasConceptScore W3177332149C111919701 @default.
- W3177332149 hasConceptScore W3177332149C119857082 @default.
- W3177332149 hasConceptScore W3177332149C127705205 @default.
- W3177332149 hasConceptScore W3177332149C136764020 @default.
- W3177332149 hasConceptScore W3177332149C148524875 @default.
- W3177332149 hasConceptScore W3177332149C154945302 @default.
- W3177332149 hasConceptScore W3177332149C204321447 @default.
- W3177332149 hasConceptScore W3177332149C23123220 @default.
- W3177332149 hasConceptScore W3177332149C2776214188 @default.
- W3177332149 hasConceptScore W3177332149C2778121359 @default.
- W3177332149 hasConceptScore W3177332149C33923547 @default.
- W3177332149 hasConceptScore W3177332149C41008148 @default.
- W3177332149 hasConceptScore W3177332149C4438859 @default.
- W3177332149 hasConceptScore W3177332149C518677369 @default.
- W3177332149 hasConceptScore W3177332149C95623464 @default.
- W3177332149 hasLocation W31773321491 @default.
- W3177332149 hasOpenAccess W3177332149 @default.
- W3177332149 hasPrimaryLocation W31773321491 @default.
- W3177332149 hasRelatedWork W150602506 @default.
- W3177332149 hasRelatedWork W1529136209 @default.
- W3177332149 hasRelatedWork W2921012827 @default.
- W3177332149 hasRelatedWork W2961085424 @default.
- W3177332149 hasRelatedWork W2963058055 @default.
- W3177332149 hasRelatedWork W3027466640 @default.
- W3177332149 hasRelatedWork W3107474891 @default.
- W3177332149 hasRelatedWork W3200179079 @default.
- W3177332149 hasRelatedWork W4249229055 @default.
- W3177332149 hasRelatedWork W187725963 @default.
- W3177332149 isParatext "false" @default.
- W3177332149 isRetracted "false" @default.
- W3177332149 magId "3177332149" @default.
- W3177332149 workType "article" @default.