| Title |
Facial expression analysis with AFFDEX and FACET: A validation study
|
|---|---|
| Published in |
Behavior Research Methods, December 2017
|
| DOI | 10.3758/s13428-017-0996-1 |
| Pubmed ID | |
| Authors |
Sabrina Stöckli, Michael Schulte-Mecklenbeck, Stefan Borer, Andrea C. Samson |
| Abstract |
The goal of this study was to validate AFFDEX and FACET, two algorithms classifying emotions from facial expressions, in iMotions's software suite. In Study 1, pictures of standardized emotional facial expressions from three databases, the Warsaw Set of Emotional Facial Expression Pictures (WSEFEP), the Amsterdam Dynamic Facial Expression Set (ADFES), and the Radboud Faces Database (RaFD), were classified with both modules. Accuracy (Matching Scores) was computed to assess and compare the classification quality. Results show a large variance in accuracy across emotions and databases, with a performance advantage for FACET over AFFDEX. In Study 2, 110 participants' facial expressions were measured while being exposed to emotionally evocative pictures from the International Affective Picture System (IAPS), the Geneva Affective Picture Database (GAPED) and the Radboud Faces Database (RaFD). Accuracy again differed for distinct emotions, and FACET performed better. Overall, iMotions can achieve acceptable accuracy for standardized pictures of prototypical (vs. natural) facial expressions, but performs worse for more natural facial expressions. We discuss potential sources for limited validity and suggest research directions in the broader context of emotion research. |
X Demographics
The data shown below were collected from the profiles of 4 X users who shared this research output. Click here to find out more about how the information was compiled.
Geographical breakdown
| Country | Count | As % |
|---|---|---|
| Switzerland | 1 | 25% |
| Japan | 1 | 25% |
| Unknown | 2 | 50% |
Demographic breakdown
| Type | Count | As % |
|---|---|---|
| Scientists | 1 | 25% |
| Science communicators (journalists, bloggers, editors) | 1 | 25% |
| Practitioners (doctors, other healthcare professionals) | 1 | 25% |
| Members of the public | 1 | 25% |
Mendeley readers
The data shown below were compiled from readership statistics for 276 Mendeley readers of this research output. Click here to see the associated Mendeley record.
Geographical breakdown
| Country | Count | As % |
|---|---|---|
| Unknown | 276 | 100% |
Demographic breakdown
| Readers by professional status | Count | As % |
|---|---|---|
| Student > Master | 51 | 18% |
| Student > Ph. D. Student | 39 | 14% |
| Researcher | 33 | 12% |
| Student > Bachelor | 26 | 9% |
| Student > Doctoral Student | 14 | 5% |
| Other | 39 | 14% |
| Unknown | 74 | 27% |
| Readers by discipline | Count | As % |
|---|---|---|
| Psychology | 58 | 21% |
| Computer Science | 33 | 12% |
| Engineering | 18 | 7% |
| Neuroscience | 14 | 5% |
| Business, Management and Accounting | 11 | 4% |
| Other | 53 | 19% |
| Unknown | 89 | 32% |
Attention Score in Context
This research output has an Altmetric Attention Score of 3. This is our high-level measure of the quality and quantity of online attention that it has received. This Attention Score, as well as the ranking and number of research outputs shown below, was calculated when the research output was last mentioned on 21 August 2021.
All research outputs
#14,920,631
of 25,382,440 outputs
Outputs from Behavior Research Methods
#1,326
of 2,526 outputs
Outputs of similar age
#225,474
of 446,047 outputs
Outputs of similar age from Behavior Research Methods
#16
of 35 outputs
Altmetric has tracked 25,382,440 research outputs across all sources so far. This one is in the 40th percentile – i.e., 40% of other outputs scored the same or lower than it.
So far Altmetric has tracked 2,526 research outputs from this source. They typically receive more attention than average, with a mean Attention Score of 8.2. This one is in the 46th percentile – i.e., 46% of its peers scored the same or lower than it.
Older research outputs will score higher simply because they've had more time to accumulate mentions. To account for age we can compare this Altmetric Attention Score to the 446,047 tracked outputs that were published within six weeks on either side of this one in any source. This one is in the 48th percentile – i.e., 48% of its contemporaries scored the same or lower than it.
We're also able to compare this research output to 35 others from the same source and published within six weeks on either side of this one. This one has gotten more attention than average, scoring higher than 51% of its contemporaries.