Professional Documents
Culture Documents
Guide:
Dr. N.N. Pise
Co - Guide:
Dr. M.V. Bedekar
Submitted By:
Taranpreet Singh Saini
601016
MIT, Pune
OUTLINE
Web Mining
User Profiling
Flow Psychology
Emotions
Contrasting of Emotions
Categorization of Emotions
Affective Haptics
Affective Computing
Emotion Detection From Keyboard & Mouse
Literature Survey
Working Groups
Datasets
Tools for Affective Computing
Mathematical Modelling
Proof of Concept
Screenshots
Future Scope
Conclusion
References
Publications
MIT, Pune
INTRODUCTION
MIT, Pune
Web Mining
Web mining - is the application of data mining techniques to
MIT, Pune
Web Browsers
A web browser (commonly referred to as a browser) is a
MIT, Pune
MIT, Pune
User Profiling
A user profile is a visual display of personal data associated
MIT, Pune
FLOW PSYCHOLOGY
MIT, Pune
Flow Psychology
It is the mental state of operation in which a person performing
MIT, Pune
10
Flow Psychology
Psychology focuses on three broad divisions : Affect, Behavior
MIT, Pune
11
MIT, Pune
EMOTIONS
12
MIT, Pune
13
Emotions
Emotion, in everyday speech, is any relatively brief conscious
MIT, Pune
14
Emotions (Cont.)
Moods are diffuse affective states that generally last for much
longer durations than emotions and are also usually less intense
than emotions.
Affect is an encompassing term, used to describe the topics of
MIT, Pune
15
MIT, Pune
16
MIT, Pune
17
Contrasting of Emotions
The three key criteria used include mental experiences that:
Have a strongly motivating subjective quality like pleasure or
pain;
Are in response to some event or object that is either real or
imagined;
Motivate particular kinds of behaviour.
18
MIT, Pune
Future Appraisal
Event-Related
Self-Appraisal
Social
Cathected
Positive Emotions
Negative Emotions
Interest, curiosity
Alarm, panic
Surprise, amusement
Indifference, familiarity,
habituation
Hope
Fear
Gratitude, thankfulness
Anger, rage
Sorrow, grief
Relief
Frustration, disappointment
Generosity
Sympathy
Love
Cruelty
Hate
MIT, Pune
19
Categorization of Emotions
HUMAINE's proposal for EARL (Emotion Annotation and
Representation Language)
Parrott's Emotions by Groups
Plutchiks Wheel of Emotions
MIT, Pune
20
MIT, Pune
21
MIT, Pune
AFFECTIVE HAPTICS
22
MIT, Pune
23
Affective Haptics
Affective haptics is the emerging area of research which focuses
on the study and design of devices and systems that can elicit,
enhance, or influence the emotional state of a human by means
of sense of touch.
Four basic haptic (tactile) channels governing our emotions can
be distinguished:
(1) physiological changes (e.g., heart beat rate, body
temperature, etc.)
(2) physical stimulation (e.g., tickling)
(3) social touch (e.g., hug, handshake)
(4) emotional haptic design (e.g., shape of device, material,
texture)
MIT, Pune
24
MIT, Pune
AFFECTIVE COMPUTING
25
MIT, Pune
26
Affective Computing
Affective computing is the study and development of systems
MIT, Pune
27
Rosalind Picard
MIT, Pune
28
MIT, Pune
Potential Applications
E-Learning
E-Therapy
Robotics Buddy Devices, Digital Pets
Driver Monitoring (Car Monitoring) Driver Emotions
TV Commercials, Audio Visual
Autism
29
MIT, Pune
30
MIT, Pune
31
MIT, Pune
LITERATURE SURVEY
32
MIT, Pune
33
PANAS Questionnaire
This scale consists of a number of words that describe different
MIT, Pune
34
PANAS Questionnaire
Scoring Instructions
Positive Affect Score: Add the scores on items 1, 3, 5, 9, 10,
MIT, Pune
PANAS Questionnaire
35
36
MIT, Pune
Literature Survey
Sr.
No.
Description
Outcome
1.
2.
3.
4.
5.
In this paper author explained about the affective Affective computing is way to achieve
computing and how it is related with emotions.
high level of AI. After the study of
human's emotions, they have discuss
affective computing's different aspects.
MIT, Pune
37
Literature Survey
6.
7.
8.
9.
10.
MIT, Pune
Working Groups
Massachusetts Institute of Technology
Media Lab
Available: http://affect.media.mit.edu/
University of Cambridge
38
MIT, Pune
39
Available: https://www.mendeley.com/groups/1185081/affective-computing-in-learning/
Interaction Design Foundation
Affective Computing
Available: https://www.interaction-design.org/literature/book/the-encyclopedia-ofhuman-computer-interaction-2nd-ed/affective-computing
TECFA Education and Technologies
MIT, Pune
40
Datasets Available
Computer Vision Lab, ETH Zurich
Over a period of many years during the 1990s, a large group of psychologists all over
the world collected data in the ISEAR project, directed by Klaus R. Scherer and Harald
Wallbott.
Eight Emotion Sentics Data
This was the first data set generated as part of the MIT Affective Computing Group's
research. The data set consists of measurements of four physiological signals and eight
affective states, taken once a day, in a session lasting around 25 minutes, for over
twenty days of recordings from an individual trying to keep every other aspect of the
measurements constant.
MIT, Pune
41
Datasets Available
DEAP Dataset
A dataset for emotion analysis using EEG, physiological and video signals.
LIRIS - ACCEDE
This dataset consists of 242 facial videos (168,359 frames) recorded in real
world conditions.
MIT, Pune
42
DESCRIPTION
DEVELOPED BY
PAYED/OPEN
Massachusetts Institute of
Technology
OPEN
2.
Massachusetts Institute of
Technology
OPEN
3.
Massachusetts Institute of
Technology
OPEN
Massachusetts Institute of
Technology
OPEN
1.
4.
TOOL NAME
ACUME
Attention Meter
MIT, Pune
43
TOOL NAME
DESCRIPTION
DEVELOPED BY
PAYED/OPEN
Audio Upload
Massachusetts Institute of
Technology
OPEN
Mood Meter
Massachusetts Institute of
Technology
7.
Physioboard
Massachusetts Institute of
Technology
OPEN
8.
Massachusetts Institute of
Technology
OPEN
5.
6.
OPEN- Used
only in MIT
College
MIT, Pune
PROBLEM FORMULATION
44
MIT, Pune
45
Problem Formulation
A user interacts with computer.
We can capture attributes like typing speed, mouse clicks and
sensors.
Then we have mapping functions that will map attributes to
emotions.
At the end, we will have the state of user (emotion).
MIT, Pune
46
Mathematical Modelling
The system is defined by the tuple, S, such that,
user U changes),
F = Functions which map I to O, through Ic inputs to Oc outputs.
MIT, Pune
U = {U1,U2,U3,,UN}
Let W be the set of webpage's viewed by a particular user
W= {W1,W2,W3,,WN}
Let UB be the browser behavior of a user.
UB = {MB, KB}
Where , MB =Mouse Behavior , KB = Keyboard Behavior
Now, MB = {MLC, MRc, MS, MM}
where
MLC = Mouse Left Click = { STM,BM,SM,F/B,SE,PM}
MRc = Mouse Right Click = { CM,PAM }
MM = Mouse Movements = { VM,H0VM,HIM,HM}
MS = Mouse Scrolls = { VSM,HSM}
Thus,
MB = {VM,H0VM,HIM,HM,BM,SM,F/B,SE,PM,STM,CM,PAM,VSM,HSM}
47
48
MIT, Pune
Where
KM = Keyboard Movements = { VK,HK,T}.
KS = Keyboard Shortcuts = { BK,SK,SLR,CA,CK,PAK,PK }.
KT = Keyboard Typing Speed = {kTS }
Thus,
KB = {BK,SK,SLR,CA,CK,PAK,PK,VK,HK,T, kTS }
Thus,
UB = {VM, H0VM, HIM, HM, BM, SM, F/B, SE, PM, STM, CM, PAM, VSM, HSM, BK, SK, SLR, CA, CK, PAK,
V
Vertical Mouse Movement
H
Mouse Horizontal
PK, VK, HK, T }
Scroll
M
where
SM
H0VM
Mouse Hover
BK
Keyboard Bookmark
HIM
HM
SK
HSM
BM
Mouse Highlight
Horizontal Mouse
Movement
Mouse Bookmark
BK
Keyboard Save
Mouse Horizontal
Scroll
Keyboard Bookmark
SM
F/B
SE
PM
STM
CM
PAM
Mouse Save
Forward And Backward
Send Email
Mouse Print
Mouse Select Text
Mouse copy
Mouse Paste
SLR
CA
CK
PAK
PK
VK
HK
Shift Left/Right
Control All
Keyboard Copy
Keyboard Paste
Keyboard Print
Keyboard Vertical
Keyboard Horizontal
VSM
TK
Keyboard Trace
MIT, Pune
49
UB = 1
(MB,KB) = 1
=>UB = (VM,H0VM,HIM,HM,BM,SM,F/B,SE,PM,STM,CM,PAM,VSM,HSM,BK,SK,SLR,CA,CK,PAK,PK,
VK,HK,T ) = 1
Condition 2
MB = {MLC, MRc, MS, MM} = 1
Since,
MLC = Mouse Left Click = { STM,BM,SM,F/B,SE,PM}
MRc = Mouse Right Click = { CM,PAM }.
MS = Mouse Scrolls = { VSM,HSM}
MM = Mouse Movements = { VM,H0VM,HIM,HM}
=> MB = {VM,H0VM,HIM,HM,BM,SM,F/B,SE,PM,STM,CM,PAM,VSM,HSM} = 1
Condition 3
KB = {KM,KS, kTS } = 1
Since,
KM = Keyboard Movements = { VK,HK,T} KS = Keyboard Shortcuts = { BK,SK,SLR,CA,CK,PAK,PK }
=>KB = {BK,SK,SLR,CA,CK,PAK,PK,VK,HK,T} = 1
MIT, Pune
50
MIT, Pune
51
MIT, Pune
52
MIT, Pune
PROOF OF CONCEPT
53
MIT, Pune
Proof of Concept
Detecting Users Web Activities
Time Spent on Web Page - User Engagement
User Click Behaviour
Copying Text From Web Page
Mouse Movements on Web Page
Amount and Speed of Scrolling on Web Page
Number of Time a Web Page is Visited
User Behaviour Based on Age and Gender
Most Number of Files Viewed
54
MIT, Pune
Proof of Concept
Mouse and Keyboard Using Sensors
Heart Beat Sensor
Force Sensor
Temperature Sensor
Bluetooth Module
55
MIT, Pune
Schematic Diagram
56
MIT, Pune
PCB Diagram
57
MIT, Pune
Sensor Snapshot
58
MIT, Pune
RESULTS
59
MIT, Pune
Survey Results
60
MIT, Pune
Survey Results
61
MIT, Pune
Survey Results
62
MIT, Pune
63
User Engagement
Data
MIT, Pune
64
MIT, Pune
65
MIT, Pune
66
MIT, Pune
67
MIT, Pune
68
MIT, Pune
69
MIT, Pune
70
MIT, Pune
71
Conclusion
At present, there is big hype in computer science and especially
MIT, Pune
72
MIT, Pune
73
MIT, Pune
74
MIT, Pune
75
MIT, Pune
76
Publications
Analysing Human Feelings by Affective Computing - Survey
MIT, Pune
77
Publications
Inferring Emotional State of a User by User Profiling
MIT, Pune
78
References
R. Picard, "Affective Computing: From Laughter to IEEE", IEEE Transaction Affective Computing, vol. 1, no. 1, pp. 11-
17, 2010.
Hamm, C. Kohler, R. Gur and R. Verma, "Automated Facial Action Coding System for dynamic analysis of facial
expressions in neuropsychiatric disorders", Journal of Neuroscience Methods, vol. 200, no. 2, pp. 237-256, 2011.
"Which emotions can commonly be visually identified by seeing the...Researchgate.net, 2016. [Online]. Available:
https://www.researchgate.net/post/Which_emotions_can_commonly_be_visually_identified_by_seeing_the_speakers_fac
e_and_which_emotions_can_be_interpreted_by_listening_to_person_speech.
Edward Shen, " Affective Computing A Note of Paper Survey, 2004.
L. Shen, M. Wang, and R. Shen, Affective e-Learning: Using emotional data to improve learning in pervasive learning
environment related work and the pervasive e-learning platform, Educational Technology and Society, vol. 12, pp. 176
189, 2009.
"Digital pet", Wikipedia, 2016. [Online]. Available: https://en.wikipedia.org/wiki/Digital_pet.
"MIT Media Lab: Affective Computing Group", Affect.media.mit.edu, 2016. [Online]. Available:
http://affect.media.mit.edu/projects.php?id=4394.
C. Said, N. Sebe and A. Todorov, "Structural resemblance to emotional expressions predicts evaluation of emotionally
neutral faces": Correction to Said, Sebe, and Todorov (2009)." Emotion, vol. 9, no. 4, pp. 509-509, 2009.
MIT, Pune
79
References
M. Murgia, "Affective computing: How 'emotional machines' are about to take over our lives", The Telegraph, 2016. [Online]. Available:
http://www.telegraph.co.uk/technology/2016/01/21/affective-computing-how-emotional-machines-are-about-to-take-ove/.
D. Jennifer, Affective Computing, Emotional Development and Autism, 1st edition, 2014.
D. Tsetserukou and A. Neviarouskaya, "Emotion Telepresence: Emotion Augmentation through Affective Haptics and Visual Stimuli", Journal of Physics:
system, International Journal of Physics Science, vol. 4, no. 1, pp. 1621, 2009.
C. D. Manning and H. Schtze, Foundations of Natural Language Processing, Reading, pp. 678, 2000.
P. K. Abhishek Kumar Chauhan, Moving Object Tracking using Gaussian Mixture Model and Optical Flow, vol. 3, no. 4, pp. 243246, 2013.
D. K. Srivastava, L. Bhambhu, and B. Cet, Data classification using support vector machine, Journal of Theoretical and Applied Information Technology,
2010.
M. S. and W. P, Research Paper on Basic of Artificial Neural Network, International Journal of Recent Innovation Trends Computer Communication, vol.
MIT, Pune
80
References
P. Sharma and A. P. R. Bhartiya, Implementation of Decision Tree Algorithm to Analysis the Performance, Int. J. Adv. Res. Computer
Communication. Eng., vol. 1, no. 10, pp. 861864, 2012.
F. Park, The Hierarchical Hidden Markov Model : Analysis and Applications, vol. 62, pp. 4162, 1998.
P. Rane, M. Mhatre and L. Kurup, Study of a Home Robot: JIBO, International Journal of Engineering Research & Technology (IJERT),
2014.
Hamm, C. Kohler, R. Gur and R. Verma, "Automated Facial Action Coding System for dynamic analysis of facial expressions in
neuropsychiatric disorders", Journal of Neuroscience Methods, vol. 200, no. 2, pp. 237-256, 2011.
"Affective Computing Market by Technology & Software 2020| MarketsandMarkets", Marketsandmarkets.com, 2016. [Online]. Available:
http://www.marketsandmarkets.com/Market-Reports/affective-computing-market-130730395.html.
"Gartner's 2015 Hype Cycle for Emerging Technologies Identifies the Computing Innovations That Organizations Should Monitor",
Gartner.com, 2016. [Online]. Available: http://www.gartner.com/newsroom/id/3114217.
MIT, Pune
81
References
Russell, J. (1980). A circumplex model of affect. Journal of Personality and Social Psychology. http://doi.org/10.1037/h0077714
Quazi, M. T. (2012). Human Emotion Recognition Using Smart Sensors a Thesis submitted in fulfilment of the Master of Engineering in,
122.
Systems, B. (2014). Emotional State Recognition via Physiological Measurements and Processing, (805), 15.
Maehr, W. (2005). eMotion: Estimation of Users Emotional State by Mouse Motions, 159.
Kolakowska, A. (2013). A review of emotion recognition methods based on keystroke dynamics and mouse movements. 2013 6th
International Conference on Human System Interactions, HSI 2013, 548555. http://doi.org/10.1109/HSI.2013.6577879
Hernandez, J., Paredes, P., Roseway, A., and Czerwinski, M. (2014). Under pressure. The 32nd Annual ACM Conference, 5160. Retrieved
from http://dl.acm.org/citation.cfm?doid=2556288.2557165%0Apapers3://publication/doi/10.1145/2556288.2557165
Lee, H., Choi, Y. S., Lee, S., and Park, I. P. (2012). Towards unobtrusive emotion recognition for affective social communication. 2012
IEEE Consumer Communications and Networking Conference, CCNC2012, 260264. http://doi.org/10.1109/CCNC.2012.6181098
Khanna, P., Sasikumar, M., and Mumbai, K. N. (2010). Recognizing Emotions from Keyboard Stroke Pattern. International Journal of
Computer Applications, 11(9), 9758887. http://doi.org/10.5120/1614-2170
Epp, C., Lippold, M., and Mandryk, R. L. (2011). Identifying emotional states using keystroke dynamics. Proceedings of the 2011 Annual
Conference on Human Factors in Computing Systems - CHI 11, 715724. http://doi.org/10.1145/1978942.1979046
Salmeron-majadas, S., Santos, O. C., and Boticario, J. (2014). Exploring indicators from keyboard and mouse interactions to predict the
user affective state. Proceedings of the 7th International Conference on Educational Data Mining (EDM), 365366.
Solanki, R., and Shukla, P. (2014). Estimation of the Users Emotional State by Keystroke Dynamics. International Journal of Computer
Applications, 94(13), 2123. Retrieved from http://lsia.fi.uba.ar/papers/solanki14.pdf
Watson, D., Clark, L. a, and Tellegen, A. (1988). Development and validation of brief measures of positive and negative affect: the PANAS
scales. Journal of Personality and Social Psychology, 54(6), 106370. http://doi.org/10.1037/0022-3514.54.6.1063
THANK YOU
MIT, Pune
82