Micro-Expression
A micro-expression is a very brief facial movement; duration definitions vary between researchers.
Duration and research history
Paul Ekman Group describes micro-expressions as lasting half a second or less. Its page also mentions durations as short as one twenty-fifth of a second. Definitions vary between researchers, so state the definition used in any review protocol. Do not replace that qualification with a single supposedly universal duration range.
Haggard and Isaacs reviewed filmed psychotherapy sessions at slowed playback in their 1966 work. Their chapter discussed very brief expressions under the term micromomentary facial expressions. That historical reference does not establish a diagnostic or deception-detection use for current software.
A research position, not an established reading of feelings
Paul Ekman Group's position is that micro-expressions can reveal concealed emotion. Present that as the organization's position, not a conclusion about an individual clip. Barrett's review and Jack's cultural findings challenge simple mappings between facial configurations and emotion. A short duration does not remove those interpretive limits.
Reviewing a brief event
A proposed review protocol should define an event's beginning and end before clips are compared. Ask reviewers to record a visible change separately from their interpretation of it. Keep uncertain timing and unanswered questions in the record. Revisit the surrounding footage rather than treating a brief event as a self-contained explanation.
Describe movement before interpreting it
FACS describes visible movement through anatomically based Action Units, rather than assigning a person's feelings. Intensity runs from A, meaning trace, to E, meaning maximum. Codes can also distinguish right, left, unilateral, or asymmetric movement. Action descriptors are separate from Action Units. For a review project, define the observation and intensity rule before comparing clips.
The Mental Edge review boundary
Mental Edge surfaces observable expression and movement signals from recorded video for contextual human review. Frame-by-frame scores are associated with seven expression categories, not verified inner states. Use a time-coded signal to revisit the footage and ask an open question. Do not use these outputs for hiring, promotion, diagnosis, deception detection, threat assessment, student scoring, or surveillance.
Review expression signals in context
Mental Edge provides time-coded expression signals from recorded video for human review, not proof of feelings or intent.
Start a free trial