Quantifying the efficacy of an automated facial coding software using videos of parents
IntroductionThis work explores the use of an automated facial coding software - FaceReader - as an alternative and/or complementary method to manual coding.MethodsWe used videos of parents (fathers, n = 36; mothers, n = 29) taken from the Avon Longitudinal Study of Parents and Children. The videos—o...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-07-01
|
| Series: | Frontiers in Psychology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpsyg.2023.1223806/full |
| _version_ | 1797768488138309632 |
|---|---|
| author | R. Burgess I. Culpin I. Culpin I. Costantini H. Bould H. Bould H. Bould I. Nabney R. M. Pearson R. M. Pearson |
| author_facet | R. Burgess I. Culpin I. Culpin I. Costantini H. Bould H. Bould H. Bould I. Nabney R. M. Pearson R. M. Pearson |
| author_sort | R. Burgess |
| collection | DOAJ |
| description | IntroductionThis work explores the use of an automated facial coding software - FaceReader - as an alternative and/or complementary method to manual coding.MethodsWe used videos of parents (fathers, n = 36; mothers, n = 29) taken from the Avon Longitudinal Study of Parents and Children. The videos—obtained during real-life parent-infant interactions in the home—were coded both manually (using an existing coding scheme) and by FaceReader. We established a correspondence between the manual and automated coding categories - namely Positive, Neutral, Negative, and Surprise - before contingency tables were employed to examine the software’s detection rate and quantify the agreement between manual and automated coding. By employing binary logistic regression, we examined the predictive potential of FaceReader outputs in determining manually classified facial expressions. An interaction term was used to investigate the impact of gender on our models, seeking to estimate its influence on the predictive accuracy.ResultsWe found that the automated facial detection rate was low (25.2% for fathers, 24.6% for mothers) compared to manual coding, and discuss some potential explanations for this (e.g., poor lighting and facial occlusion). Our logistic regression analyses found that Surprise and Positive expressions had strong predictive capabilities, whilst Negative expressions performed poorly. Mothers’ faces were more important for predicting Positive and Neutral expressions, whilst fathers’ faces were more important in predicting Negative and Surprise expressions.DiscussionWe discuss the implications of our findings in the context of future automated facial coding studies, and we emphasise the need to consider gender-specific influences in automated facial coding research. |
| first_indexed | 2024-03-12T20:54:22Z |
| format | Article |
| id | doaj.art-757e9da855474610af5223bae2065dcc |
| institution | Directory Open Access Journal |
| issn | 1664-1078 |
| language | English |
| last_indexed | 2024-03-12T20:54:22Z |
| publishDate | 2023-07-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Psychology |
| spelling | doaj.art-757e9da855474610af5223bae2065dcc2023-07-31T21:32:43ZengFrontiers Media S.A.Frontiers in Psychology1664-10782023-07-011410.3389/fpsyg.2023.12238061223806Quantifying the efficacy of an automated facial coding software using videos of parentsR. Burgess0I. Culpin1I. Culpin2I. Costantini3H. Bould4H. Bould5H. Bould6I. Nabney7R. M. Pearson8R. M. Pearson9The Digital Health Engineering Group, Merchant Venturers Building, University of Bristol, Bristol, United KingdomThe Centre for Academic Mental Health, Bristol Medical School, Bristol, United KingdomFlorence Nightingale Faculty of Nursing, Midwifery and Palliative Care, King’s College London, London, United KingdomThe Centre for Academic Mental Health, Bristol Medical School, Bristol, United KingdomThe Centre for Academic Mental Health, Bristol Medical School, Bristol, United KingdomThe Medical Research Council Integrative Epidemiology Unit, University of Bristol, Bristol, United KingdomThe Gloucestershire Health and Care NHS Foundation Trust, Gloucester, United KingdomThe Digital Health Engineering Group, Merchant Venturers Building, University of Bristol, Bristol, United KingdomThe Centre for Academic Mental Health, Bristol Medical School, Bristol, United KingdomThe Department of Psychology, Manchester Metropolitan University, Manchester, United KingdomIntroductionThis work explores the use of an automated facial coding software - FaceReader - as an alternative and/or complementary method to manual coding.MethodsWe used videos of parents (fathers, n = 36; mothers, n = 29) taken from the Avon Longitudinal Study of Parents and Children. The videos—obtained during real-life parent-infant interactions in the home—were coded both manually (using an existing coding scheme) and by FaceReader. We established a correspondence between the manual and automated coding categories - namely Positive, Neutral, Negative, and Surprise - before contingency tables were employed to examine the software’s detection rate and quantify the agreement between manual and automated coding. By employing binary logistic regression, we examined the predictive potential of FaceReader outputs in determining manually classified facial expressions. An interaction term was used to investigate the impact of gender on our models, seeking to estimate its influence on the predictive accuracy.ResultsWe found that the automated facial detection rate was low (25.2% for fathers, 24.6% for mothers) compared to manual coding, and discuss some potential explanations for this (e.g., poor lighting and facial occlusion). Our logistic regression analyses found that Surprise and Positive expressions had strong predictive capabilities, whilst Negative expressions performed poorly. Mothers’ faces were more important for predicting Positive and Neutral expressions, whilst fathers’ faces were more important in predicting Negative and Surprise expressions.DiscussionWe discuss the implications of our findings in the context of future automated facial coding studies, and we emphasise the need to consider gender-specific influences in automated facial coding research.https://www.frontiersin.org/articles/10.3389/fpsyg.2023.1223806/fullautomated facial codingFaceReaderfacial expressionsparentingALSPAC |
| spellingShingle | R. Burgess I. Culpin I. Culpin I. Costantini H. Bould H. Bould H. Bould I. Nabney R. M. Pearson R. M. Pearson Quantifying the efficacy of an automated facial coding software using videos of parents Frontiers in Psychology automated facial coding FaceReader facial expressions parenting ALSPAC |
| title | Quantifying the efficacy of an automated facial coding software using videos of parents |
| title_full | Quantifying the efficacy of an automated facial coding software using videos of parents |
| title_fullStr | Quantifying the efficacy of an automated facial coding software using videos of parents |
| title_full_unstemmed | Quantifying the efficacy of an automated facial coding software using videos of parents |
| title_short | Quantifying the efficacy of an automated facial coding software using videos of parents |
| title_sort | quantifying the efficacy of an automated facial coding software using videos of parents |
| topic | automated facial coding FaceReader facial expressions parenting ALSPAC |
| url | https://www.frontiersin.org/articles/10.3389/fpsyg.2023.1223806/full |
| work_keys_str_mv | AT rburgess quantifyingtheefficacyofanautomatedfacialcodingsoftwareusingvideosofparents AT iculpin quantifyingtheefficacyofanautomatedfacialcodingsoftwareusingvideosofparents AT iculpin quantifyingtheefficacyofanautomatedfacialcodingsoftwareusingvideosofparents AT icostantini quantifyingtheefficacyofanautomatedfacialcodingsoftwareusingvideosofparents AT hbould quantifyingtheefficacyofanautomatedfacialcodingsoftwareusingvideosofparents AT hbould quantifyingtheefficacyofanautomatedfacialcodingsoftwareusingvideosofparents AT hbould quantifyingtheefficacyofanautomatedfacialcodingsoftwareusingvideosofparents AT inabney quantifyingtheefficacyofanautomatedfacialcodingsoftwareusingvideosofparents AT rmpearson quantifyingtheefficacyofanautomatedfacialcodingsoftwareusingvideosofparents AT rmpearson quantifyingtheefficacyofanautomatedfacialcodingsoftwareusingvideosofparents |