Differences

This shows you the differences between two versions of the page.

--- models_of_social_intelligence [2009-01-09 17:28] – davegriffiths
+++ models_of_social_intelligence [2009-01-13 12:17] – davegriffiths
@@ Line 1: / Line 1: @@
-====Models of Social Intelligence====
+======Models of Social Intelligence======
 Part of [[Project Lirec]]: Notes (and bits pasted) from Deliverable 5.1
@@ Line 5: / Line 5: @@
 An understanding of social intelligence is needed for creating agents capable of long term companionship with humans.
-===Social Intelligence in Humans===
+=====Social Intelligence in Humans=====
   * Begins in childhood with attachment and love for caregivers
@@ Line 13: / Line 13: @@
 A long term companion needs to apply the same strategies for creating and maintaining relationships if it's to be effective.
-===Emotions and personality===
+=====Emotions and personality=====
 Emotions and personality need to be expressed for people to gain an empathic relation with an agent.
@@ Line 22: / Line 22: @@
 Companions need to have a consistent personality to maintain long term relationships.
-===Theory of mind===
+=====Theory of mind=====
 A theory of mind is a model of a users emotional state, gained by measuring affective state from sensor input. In this way an agent return an empathic relationship with a human. Such a model must include a users:
@@ Line 32: / Line 32: @@
   * Personality
-===Memory and Adaptation===
+=====Memory and Adaptation=====
 A companion needs to adapt and evolve based on past experiences.
 To some extent adapt to a users personality in order to match better.
-====Socially intelligent agents====
+======Socially intelligent agents======
 Human intelligence includes:
@@ Line 49: / Line 49: @@
 ***The expectation of social interaction of an agent depends on it's form, a human form is more natural, but also creates very high expectations - which are not currently possible.***
-===Castelfranchi's ontology for social interaction===
+=====Castelfranchi's ontology for social interaction=====
   - Goal oriented agents: the action the agent takes in the world (in other words, its behaviour) is aimed at producing some result.
@@ Line 74: / Line 74: @@
   *   Emphasize commonalities and de-emphasize differences, to increase solidarity and rapport.
-===Social Power===
+=====Social Power=====
-* The influence of a social agent on a person
+  * The influence of a social agent on a person
-* Social agent = another person, social role, norm or group
+  * Social agent = another person, social role, norm or group
-* Social power can be resisted
+  * Social power can be resisted
-===Social Attraction===
+=====Social Attraction=====
   * Affective ties of one person or agent with others
@@ Line 87: / Line 87: @@
   * But they are often balanced
-===Heider's Balance Theory===
+=====Heider's Balance Theory=====
 http://en.wikipedia.org/wiki/Balance_theory
@@ Line 99: / Line 99: @@
 The theory states that people tend to avoid unstable cognitive configurations.
-====Existing Socially Intelligent Agents====
+======Examples of Socially Intelligent Agents======
-Embodied conversational agents
+Embodied conversational agents - these use face to face conversations in an attempt to simplify human/computer communication.
+**REA**: The automated real estate agent: http://www.media.mit.edu/gnl/projects/humanoid/
+Attempts to sell people houses, keeps a track of //task talk// and //small talk//, and can interleave them.
+**Laura & FitTrack**: An exercise advisor designed to explore long term relationships. Tested with 100 people, users with the relationship building features added were "more likely" to continue using the system. http://www.ccs.neu.edu/home/bickmore/publications/CACM04.pdf
+**Avatar Arena**: Multi characters interacting with each other on the user's behalf:
+http://www.ltg.ed.ac.uk/magicster/deliverables/rist.pdf
+**2SGD Model**: Agents for interacting with groups:
+http://gaips.inesc-id.pt/gaips/shared/docs/prada-iva2005.pdf
+=======Social Robots======
+Sociable physical robots
+**Kismet**: Animatronic head which responds to people's actions, and capable of "proto conversation" through babbling: http://www.ai.mit.edu/projects/humanoid-robotics-group/kismet/
+**Valerie the roboceptionist**: http://www.msnbc.msn.com/id/4306856
+======Emotions and personality in Social Agents======
+(Moffat, 1997) states, “personality is the name we give to (an agent’s) reactions tendencies that are consistent over situations and time”.
+=====Computational models of emotions=====
+**EMA**: http://projects.ict.usc.edu/vhumans/2007/Presentation/EMAnop.pdf
+**FAtiMA**: Used in Fear Not! (is this part of ION?)
+  * Events + Emotions -> Appraisal
+  * Appraisal based on
+    * Goals
+    * Standards
+    * Attitudes
+  * Emotions have intensity - attenuated in time
+  * Mood - overall state of emotions
+  * Mood also affects emotions
+  * Emotional threshold - characters resistence to an emotion type
+  * Decay rate - How fast an emotion disappears
+    = personality
+  * Event or action -> Knowledge base update
+  *          -> emotion -> autobiographic memory
+**PSI**
+Needs/drives:
+  * food
+  * water
+  * physical integrity
+  * sexuality
+  * affiliation (social need)
+  * certainty and competence
+Needs given weights, Reactive level/Deliberate level - more goal oriented
+======Theory of Mind in Social Agents======
+The ability to infer mental states in others that are not directly observable.