Matches in SemOpenAlex for { <https://semopenalex.org/work/W4319880325> ?p ?o ?g. }
- W4319880325 endingPage "e0281309" @default.
- W4319880325 startingPage "e0281309" @default.
- W4319880325 abstract "Automatic facial coding (AFC) is a promising new research tool to efficiently analyze emotional facial expressions. AFC is based on machine learning procedures to infer emotion categorization from facial movements (i.e., Action Units). State-of-the-art AFC accurately classifies intense and prototypical facial expressions, whereas it is less accurate for non-prototypical and less intense facial expressions. A potential reason might be that AFC is typically trained with standardized and prototypical facial expression inventories. Because AFC would be useful to analyze less prototypical research material as well, we set out to determine the role of prototypicality in the training material. We trained established machine learning algorithms either with standardized expressions from widely used research inventories or with unstandardized emotional facial expressions obtained in a typical laboratory setting and tested them on identical or cross-over material. All machine learning models' accuracies were comparable when trained and tested with held-out dataset from the same dataset (acc. = [83.4% to 92.5%]). Strikingly, we found a substantial drop in accuracies for models trained with the highly prototypical standardized dataset when tested in the unstandardized dataset (acc. = [52.8%; 69.8%]). However, when they were trained with unstandardized expressions and tested with standardized datasets, accuracies held up (acc. = [82.7%; 92.5%]). These findings demonstrate a strong impact of the training material's prototypicality on AFC's ability to classify emotional faces. Because AFC would be useful for analyzing emotional facial expressions in research or even naturalistic scenarios, future developments should include more naturalistic facial expressions for training. This approach will improve the generalizability of AFC to encode more naturalistic facial expressions and increase robustness for future applications of this promising technology." @default.
- W4319880325 created "2023-02-11" @default.
- W4319880325 creator A5012676088 @default.
- W4319880325 creator A5014178839 @default.
- W4319880325 creator A5014446519 @default.
- W4319880325 creator A5017703092 @default.
- W4319880325 date "2023-02-10" @default.
- W4319880325 modified "2023-10-14" @default.
- W4319880325 title "Training machine learning algorithms for automatic facial coding: The role of emotional facial expressions’ prototypicality" @default.
- W4319880325 cites W1577666996 @default.
- W4319880325 cites W1789579346 @default.
- W4319880325 cites W1817040532 @default.
- W4319880325 cites W1831050183 @default.
- W4319880325 cites W1966868984 @default.
- W4319880325 cites W1975436731 @default.
- W4319880325 cites W1975911018 @default.
- W4319880325 cites W1987708005 @default.
- W4319880325 cites W1992047701 @default.
- W4319880325 cites W2000673252 @default.
- W4319880325 cites W2001315093 @default.
- W4319880325 cites W2001846736 @default.
- W4319880325 cites W2007431552 @default.
- W4319880325 cites W2012945211 @default.
- W4319880325 cites W2045472600 @default.
- W4319880325 cites W2051297709 @default.
- W4319880325 cites W2058495746 @default.
- W4319880325 cites W2091081265 @default.
- W4319880325 cites W2125874614 @default.
- W4319880325 cites W2126567360 @default.
- W4319880325 cites W2134249892 @default.
- W4319880325 cites W2137591261 @default.
- W4319880325 cites W2138521251 @default.
- W4319880325 cites W2141007997 @default.
- W4319880325 cites W2150283722 @default.
- W4319880325 cites W2493062450 @default.
- W4319880325 cites W2606759888 @default.
- W4319880325 cites W2626982410 @default.
- W4319880325 cites W2775666429 @default.
- W4319880325 cites W2789019232 @default.
- W4319880325 cites W2790776461 @default.
- W4319880325 cites W2792191740 @default.
- W4319880325 cites W2795870269 @default.
- W4319880325 cites W2808103905 @default.
- W4319880325 cites W2894904399 @default.
- W4319880325 cites W2911964244 @default.
- W4319880325 cites W2912483755 @default.
- W4319880325 cites W2913821117 @default.
- W4319880325 cites W2980594093 @default.
- W4319880325 cites W2986002983 @default.
- W4319880325 cites W3020447069 @default.
- W4319880325 cites W3036549612 @default.
- W4319880325 cites W3097096317 @default.
- W4319880325 cites W3137049019 @default.
- W4319880325 cites W3158068891 @default.
- W4319880325 cites W3216279502 @default.
- W4319880325 cites W4210470241 @default.
- W4319880325 cites W4212883601 @default.
- W4319880325 cites W4214852121 @default.
- W4319880325 cites W4237464733 @default.
- W4319880325 cites W4255190871 @default.
- W4319880325 cites W4281254423 @default.
- W4319880325 cites W429766147 @default.
- W4319880325 doi "https://doi.org/10.1371/journal.pone.0281309" @default.
- W4319880325 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36763694" @default.
- W4319880325 hasPublicationYear "2023" @default.
- W4319880325 type Work @default.
- W4319880325 citedByCount "2" @default.
- W4319880325 countsByYear W43198803252023 @default.
- W4319880325 crossrefType "journal-article" @default.
- W4319880325 hasAuthorship W4319880325A5012676088 @default.
- W4319880325 hasAuthorship W4319880325A5014178839 @default.
- W4319880325 hasAuthorship W4319880325A5014446519 @default.
- W4319880325 hasAuthorship W4319880325A5017703092 @default.
- W4319880325 hasBestOaLocation W43198803251 @default.
- W4319880325 hasConcept C105795698 @default.
- W4319880325 hasConcept C119857082 @default.
- W4319880325 hasConcept C153180895 @default.
- W4319880325 hasConcept C154945302 @default.
- W4319880325 hasConcept C179518139 @default.
- W4319880325 hasConcept C195704467 @default.
- W4319880325 hasConcept C2777438025 @default.
- W4319880325 hasConcept C33923547 @default.
- W4319880325 hasConcept C40346341 @default.
- W4319880325 hasConcept C41008148 @default.
- W4319880325 hasConcept C94124525 @default.
- W4319880325 hasConceptScore W4319880325C105795698 @default.
- W4319880325 hasConceptScore W4319880325C119857082 @default.
- W4319880325 hasConceptScore W4319880325C153180895 @default.
- W4319880325 hasConceptScore W4319880325C154945302 @default.
- W4319880325 hasConceptScore W4319880325C179518139 @default.
- W4319880325 hasConceptScore W4319880325C195704467 @default.
- W4319880325 hasConceptScore W4319880325C2777438025 @default.
- W4319880325 hasConceptScore W4319880325C33923547 @default.
- W4319880325 hasConceptScore W4319880325C40346341 @default.
- W4319880325 hasConceptScore W4319880325C41008148 @default.
- W4319880325 hasConceptScore W4319880325C94124525 @default.
- W4319880325 hasFunder F4320324159 @default.
- W4319880325 hasIssue "2" @default.