Ma. Mercedes T. Rodrigo

utterlypanoramicΑσφάλεια

30 Νοε 2013 (πριν από 3 χρόνια και 10 μήνες)

67 εμφανίσεις

Introduction to the Ateneo’s
Affective Computing Group

Ma. Mercedes T. Rodrigo, Ph.D.

Associate Professor

Department of Information Systems and Computer Science


20 November 2010

Workshop on Affective Computing and Intelligent Interaction

Affective computing



Computing that relates to, arises from or
deliberately influences emotion





-

Picard, 1997,
Affective Computing

Affective computing


Emotion recognition


Emotion expression


Intelligent response to emotion


Significance: Towards more humane
interfaces

How can we enable computers to better serve
people’s needs
--
adapting to you, vs. treating
you like some fictionalized ideal user, and
recognizing that humans are powerfully
influenced by emotion, even when they are
not showing any emotion?






-

Picard, 2003

Aplusix, Scatterplot, Ecolab, BlueJ, etc.

Student
Interaction
Logs

Observation
Logs

Analysis


Affect detectors


Behavior detectors


Novice programmer errors


Interventions


Intelligent agents


Improved error
messages

Biometrics Logs

Aplusix, Scatterplot, Ecolab, BlueJ, etc.

Student
Interaction
Logs

Observation
Logs

Analysis


Affect detectors


Behavior detectors


Novice programmer errors


Interventions


Intelligent agents


Improved error
messages

Biometrics Logs

Methods: Aplusix

Methods: Ecolab / MEcolab

Methods: Cognitive Tutor

Methods: BlueJ

Methods: The Incredible Machine

Methods: Math Blaster

Biometrics instruments

Biometrics instruments

Biometrics instruments

Aplusix, Scatterplot, Ecolab, BlueJ, etc.

Student
Interaction
Logs

Observation
Logs

Analysis


Affect detectors


Behavior detectors


Novice programmer errors


Interventions


Intelligent agents


Improved error
messages

Biometrics
Logs

Sample Log: Aplusix

%;ACTIONS;#Date=1/16/2007#Heure=14:57:59;#TypeProbleme=TpbDevelopp
er

0;0.0;structure;();0;();();();();();();

1;0.0;enonce;();0;
-
7x(7x{@^[2]}
-
7x+4);();(devant);rien;;N1;

2;5.1;placerCurseur;();0;
-
7x(7x{@^[2]}
-
7x+4);();(0 2 derriere);rien;;N1;

3;0.8;dupliquer;();1;
-
7x(7x{@^[2]}
-
7x+4);();(0 2 derriere);rien;V1;N1;

4;1.9;selection;();1;
-
7x(7x{@^[2]}
-
7x+4);();rien;();V1;N1;

5;5.3;
-
;();1;7x(7x{@^[2]}
-
7x+4);();rien;();V0;N0;

6;1.5;BackSpace;();1;?;();(dedans);rien;V
-
;N
-
;

7;2.0;
-
;();1;
-
?;();(0 dedans);rien;V
-
;N
-
;

8;3.7;4;();1;
-
4;();(0 0 derriere);rien;V0;S0;

9;0.2;9;();1;
-
49;();(0 1 derriere);rien;V0;S0;

10;2.7;x;();1;
-
49x;();(0 1 derriere);rien;V0;S0;

11;1.3;{@^[?]};();1;
-
49x{@^[?]};();(0 1 1 dedans);rien;V
-
;N
-
;

Sample Log: Ecolab

New Activity Toolbar Button

Click

0





6

Activity

1

6

Activity Chosen:

Food 4

6

Suggested Help

0

6

Suggested Challenge

1

6

Challenge Accepted

1

8

View

Web change

13

View

Web change

14

View

Web change

14

Action

Show

19


Sample Log: Scatterplot Tutor

*000:03:781 READY

.

*000:59:503 APPLY
-
ACTION

WINDOW; ALGEBRA
-
2
-
TRANSLATOR::VARIABLE
-
TYPE
-
MODEL,

CONTEXT; SPLOT
-
DB
-
C
-
0
-
10
-
0
-
10,

SELECTIONS; (|var
-
1val
-
1|),

ACTION; SUBSTITUTE
-
TEXT
-
INTO
-
BLANK,

INPUT; ("Numerical"),

.

*000:59:503 UPDATE
-
P
-
KNOW

META; META
-
VALUING
-
NUM
-
FEATURES,

PRODUCTION; (CHOOSE
-
VAR
-
TYPE
-
NUM MIDSCH
-
VARIABLE
-
TYPING),

SUCCESS?; T,

P
-
KNOW; 0.33333333333333326,

..

Sample Log: Brainfingers

[Header V2035]

7/31/2009 7:49:05 PM

UserFile

= C:
\
Nia Data
\
\
__20090731194905.usr

[Data]

Sample,Event,GlanceMagJs,GlanceDirJs,A1Js,A2Js,A3Js,B1Js,B2Js,B3Js,MuscleJs

1,0,0.1,0.065,0.0195,0.20775,
-
1.165867E
-
07,0.5815,0.5311,0.6048,0.6782,0.7665,0.7074,0

1,0,
-
0.029,
-
0.122,0.021,0.2056,
-
1.165867E
-
07,0.5774,0.5251,0.5892,0.6723,0.7598,0.7125,0

1,0,0.015,
-
0.167,0.0205,0.203625,
-
1.165867E
-
07,0.5743,0.5187,0.5737,0.6683,0.7534,0.7157,0

1,0,
-
0.0595,
-
0.1555,0.0205,0.20165,
-
1.165867E
-
07,0.573,0.5118,0.5596,0.6656,0.7468,0.7159,0

1,0,
-
0.285,
-
0.163,0.0205,0.199625,
-
1.165867E
-
07,0.5733,0.5043,0.5477,0.6622,0.7398,0.7168,0

1,0,
-
0.3665,
-
0.206,0.022,0.197625,
-
1.165867E
-
07,0.5745,0.4966,0.5371,0.6567,0.7321,0.7221,0

1,0,
-
0.125,
-
0.158,0.0225,0.195675,
-
1.165867E
-
07,0.5772,0.4885,0.5268,0.6483,0.7242,0.7262,0


Aplusix, Scatterplot, Ecolab, BlueJ, etc.

Student
Interaction
Logs

Observation
Logs

Analysis


Affect detectors


Behavior detectors


Novice programmer errors


Interventions


Intelligent agents


Improved error
messages

Biometrics Logs

Affective states


Boredom


Confusion


Delight


Frustration


Flow


Neutrality


Surprise

Behaviors


On task


On task giving and receiving answers


Other on task conversation


Off
-
task solitary


Off
-
task conversation


Inactive


Gaming the system

Aplusix, Scatterplot, Ecolab, BlueJ, etc.

Student
Interaction
Logs

Observation
Logs

Analysis


Affect detectors


Behavior detectors


Novice programmer errors


Interventions


Intelligent agents


Improved error
messages

Biometrics Logs

Analysis techniques


Statistical methods


Data mining techniques

Analysis methods


Clean the data


Define the different features


Distill new features


Define desired range of values


Select an appropriate statistical test or data
mining algorithm


Validate the findings

Findings


Persistence of affective states


Regardless of software, boredom tends to persist


Affect and behavior detection


Students who attempt the most difficult problems experience flow the
most


Students who try the lowest levels experience more boredom and
confusion.


Students who take the longest time in solving the problems
experience confusion the most


Students who take the shortest time experience confusion the least.


Students who use the most number of steps to solve a problem
experience confusion and boredom the most.


Students who take the least number of steps experience more flow.

Aplusix, Scatterplot, Ecolab, BlueJ, etc.

Student
Interaction
Logs

Observation
Logs

Analysis


Affect detectors


Behavior detectors


Novice programmer errors


Interventions


Intelligent agents


Improved error
messages

Biometrics Logs

Example

Aplusix, Scatterplot, Ecolab, BlueJ, etc.

Student
Interaction
Logs

Observation
Logs

Analysis


Affect detectors


Behavior detectors


Novice programmer errors


Interventions


Intelligent agents


Improved error
messages

Biometrics Logs

Closing the loop


Integrate the models with the software



We’re getting there…

This is a huge undertaking


2 PhD students


6 MS CS students


1 MA Ed ITI student


9 BS CS students


6 international collaborators

Funded by DOST since 2007


5 grants so far


Over P4.2 million

Publications


7 journal publications (2 ISI)


8 strictly
-
reviewed conference papers


21 other conference papers and presentations

Thank you