Matches in SemOpenAlex for { <https://semopenalex.org/work/W4311438709> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W4311438709 abstract "Social media has become an important data source for event analysis. When collecting this type of data, most contain no useful information to a target event. Thus, it is essential to filter out those noisy data at the earliest opportunity for a human expert to perform further inspection. Most existing solutions for event filtering rely on fully supervised methods for training. However, in many real-world scenarios, having access to large number of labeled samples is not possible. To deal with a few labeled sample training problem for event filtering, we propose a graph-based few-shot learning pipeline. We also release the Brazilian Protest Dataset to test our method. To the best of our knowledge, this dataset is the first of its kind in event filtering that focuses on protests in multi-modal social media data, with most of the text in Portuguese. Our experimental results show that our proposed pipeline has comparable performance with only a few labeled samples (60) compared with a fully labeled dataset (3100). To facilitate the research community, we make our dataset and code available at https://github.com/jdnascim/7Set-AL." @default.
- W4311438709 created "2022-12-26" @default.
- W4311438709 creator A5009587198 @default.
- W4311438709 creator A5028108090 @default.
- W4311438709 creator A5041566313 @default.
- W4311438709 creator A5075721951 @default.
- W4311438709 date "2022-12-12" @default.
- W4311438709 modified "2023-10-01" @default.
- W4311438709 title "Few-shot Learning for Multi-modal Social Media Event Filtering" @default.
- W4311438709 cites W2953722276 @default.
- W4311438709 cites W2962907576 @default.
- W4311438709 cites W2970641574 @default.
- W4311438709 cites W2982083293 @default.
- W4311438709 cites W2984353870 @default.
- W4311438709 cites W2999678654 @default.
- W4311438709 cites W3099215402 @default.
- W4311438709 cites W3106188259 @default.
- W4311438709 cites W3123441716 @default.
- W4311438709 cites W3162766389 @default.
- W4311438709 cites W4226320713 @default.
- W4311438709 doi "https://doi.org/10.1109/wifs55849.2022.9975429" @default.
- W4311438709 hasPublicationYear "2022" @default.
- W4311438709 type Work @default.
- W4311438709 citedByCount "0" @default.
- W4311438709 crossrefType "proceedings-article" @default.
- W4311438709 hasAuthorship W4311438709A5009587198 @default.
- W4311438709 hasAuthorship W4311438709A5028108090 @default.
- W4311438709 hasAuthorship W4311438709A5041566313 @default.
- W4311438709 hasAuthorship W4311438709A5075721951 @default.
- W4311438709 hasBestOaLocation W43114387092 @default.
- W4311438709 hasConcept C106131492 @default.
- W4311438709 hasConcept C111919701 @default.
- W4311438709 hasConcept C119857082 @default.
- W4311438709 hasConcept C121332964 @default.
- W4311438709 hasConcept C124101348 @default.
- W4311438709 hasConcept C132525143 @default.
- W4311438709 hasConcept C136764020 @default.
- W4311438709 hasConcept C154945302 @default.
- W4311438709 hasConcept C177264268 @default.
- W4311438709 hasConcept C185592680 @default.
- W4311438709 hasConcept C188027245 @default.
- W4311438709 hasConcept C199360897 @default.
- W4311438709 hasConcept C2776145971 @default.
- W4311438709 hasConcept C2776760102 @default.
- W4311438709 hasConcept C2779662365 @default.
- W4311438709 hasConcept C31972630 @default.
- W4311438709 hasConcept C41008148 @default.
- W4311438709 hasConcept C43126263 @default.
- W4311438709 hasConcept C43521106 @default.
- W4311438709 hasConcept C518677369 @default.
- W4311438709 hasConcept C62520636 @default.
- W4311438709 hasConcept C71139939 @default.
- W4311438709 hasConcept C80444323 @default.
- W4311438709 hasConceptScore W4311438709C106131492 @default.
- W4311438709 hasConceptScore W4311438709C111919701 @default.
- W4311438709 hasConceptScore W4311438709C119857082 @default.
- W4311438709 hasConceptScore W4311438709C121332964 @default.
- W4311438709 hasConceptScore W4311438709C124101348 @default.
- W4311438709 hasConceptScore W4311438709C132525143 @default.
- W4311438709 hasConceptScore W4311438709C136764020 @default.
- W4311438709 hasConceptScore W4311438709C154945302 @default.
- W4311438709 hasConceptScore W4311438709C177264268 @default.
- W4311438709 hasConceptScore W4311438709C185592680 @default.
- W4311438709 hasConceptScore W4311438709C188027245 @default.
- W4311438709 hasConceptScore W4311438709C199360897 @default.
- W4311438709 hasConceptScore W4311438709C2776145971 @default.
- W4311438709 hasConceptScore W4311438709C2776760102 @default.
- W4311438709 hasConceptScore W4311438709C2779662365 @default.
- W4311438709 hasConceptScore W4311438709C31972630 @default.
- W4311438709 hasConceptScore W4311438709C41008148 @default.
- W4311438709 hasConceptScore W4311438709C43126263 @default.
- W4311438709 hasConceptScore W4311438709C43521106 @default.
- W4311438709 hasConceptScore W4311438709C518677369 @default.
- W4311438709 hasConceptScore W4311438709C62520636 @default.
- W4311438709 hasConceptScore W4311438709C71139939 @default.
- W4311438709 hasConceptScore W4311438709C80444323 @default.
- W4311438709 hasLocation W43114387091 @default.
- W4311438709 hasLocation W43114387092 @default.
- W4311438709 hasOpenAccess W4311438709 @default.
- W4311438709 hasPrimaryLocation W43114387091 @default.
- W4311438709 hasRelatedWork W2068834169 @default.
- W4311438709 hasRelatedWork W2136010533 @default.
- W4311438709 hasRelatedWork W2366828174 @default.
- W4311438709 hasRelatedWork W2737894786 @default.
- W4311438709 hasRelatedWork W2752124967 @default.
- W4311438709 hasRelatedWork W3006459298 @default.
- W4311438709 hasRelatedWork W3033962221 @default.
- W4311438709 hasRelatedWork W3214605075 @default.
- W4311438709 hasRelatedWork W4281610068 @default.
- W4311438709 hasRelatedWork W4310562105 @default.
- W4311438709 isParatext "false" @default.
- W4311438709 isRetracted "false" @default.
- W4311438709 workType "article" @default.