Graphics Reference
In-Depth Information
the opposite team. An important challenge for artificial intelligence
researchers in the 21st century is in creating socially intelligent robots
and computers, able to recognize, predict and analyze verbal and
nonverbal dynamics during face-to-face communication. This will not
only open up new avenues for human-computer interactions but create
new computational tools for social and behavior researchers—software
able to automatically analyze human social and nonverbal behaviors,
and extract important interaction patterns.
Human face-to-face communication is a little like a dance, in
that participants continuously adjust their behaviors based on verbal
and nonverbal behaviors from other participants. We identify four
important types of dynamics during social interactions:
Behavioral dynamic:
A first relevant dynamic in human
communication is the dynamic of each specific behavior. For
example, a smile has its own dynamic in the sense that the
speed of the onset and offset can change its meaning (e.g., fake
smile versus real smile). This is also true about words when
pronounced to emphasize their importance. The behavioral
dynamic needs to be correctly represented when modeling social
interactions.
Multimodal dynamic:
Even when observing participants
individually, the interpretation of their behaviors is a multimodal
problem in that both verbal and nonverbal messages are necessary
to a complete understanding of human behaviors. Multimodal
dynamics represent this influence and relationship between the
different channels of information such as language, prosody
and gestures. Modeling the multimodal dynamics is challenging
since gestures may not always be synchronized with speech and
the communicative signals may have different granularity (e.g.,
linguistic signals are interpreted at the word level while prosodic
information varies much faster).
Interpersonal dynamic:
The verbal and nonverbal messages from
one participant are better interpreted when put into context with
the concurrent and previous messages from other participants.
For example, a smile may be interpreted as an acknowledgement
if the speaker just looked back at the listener and paused while
it could be interpreted as a signal of empathy if the speaker just
confessed something personal. Interpersonal dynamics represent
this influence and relationship between multiple sources (e.g.,
participants). This dynamic is referred as micro-dynamic by
sociologists (Hawley, 1950).
Search WWH ::
Custom Search