en
0.25
0.5
0.75
1.25
1.5
1.75
2
Analyzing Text and Social Network Data with Probabilistic Models
Published on Oct 29, 20125194 Views
Exploring and understanding large text and social network data sets is of increasing interest across multiple fields, in computer science, social science, history, medicine, and more. This talk will p
Related categories
Chapter list
Analyzing Text and Social Network Data with Probablistic Models00:00
Acknowledgements00:06
ECML/PKDD-2002 - 100:27
ECML/PKDD-2002 - 200:48
Facebook01:15
Email data02:24
Email Network03:14
Pennsylvania Gazette03:32
Common Themes - 104:37
Common Themes - 205:12
Modeling with Latent Variables05:42
Statistical Latent Variable Models08:17
Outline09:43
Multinomial Distributions on Words10:29
Multinomial Model for Words11:38
Plate Diagram12:23
Multinomials = Topics12:25
Mutliple Word Distributions13:06
Mixture Model Clustering13:43
Topic Model14:29
Clusters v. Topics - 115:15
Clusters v. Topics - 215:42
Clusters v. Topics - 315:55
Topic Models16:06
Topics as Matrix Factorization - 116:32
Topics as Matrix Factorization - 217:09
History17:50
What Do We Need to Learn?19:09
Imagine If the z´s Were Known19:55
Learning Algorithm - 120:35
Learning Algorithm - 220:47
Learning Algorithm - 321:28
Example: Topics from DNA Microarray Literature21:55
Technology v. Application Topics - 123:26
Technology v. Application Topics - 224:13
Pennsylvania Gazette Data25:03
Enron Email Topics26:00
"Personal" Topics ...27:50
Political Topics28:14
Extensions28:39
Combining Prior Knowledge and Learned Topics29:27
MultiLabel Document Data Sets - 130:07
MultiLabel Document Data Sets - 230:55
MultiLabel Document Data Sets - 331:41
Applying Topic Models to Multilabel Classification - 132:37
Applying Topic Models to Multilabel Classification - 234:19
Applying Topic Models to Multilabel Classification - 335:02
Applying Topic Models to Multilabel Classification - 435:43
Applying Topic Models to Multilabel Classification - 536:32
Applying Topic Models to Multilabel Classification - 637:07
Applying Topic Models to Multilabel Classification - 737:30
Combinig Human-Defined Concepts and Topics38:30
Tagging Documents with Concepts - 139:22
Tagging Documents with Concepts - 239:44
Mapping a Document to a Thesaurus40:09
Thesauri Produce Better Topic Models - 141:07
Thesauri Produce Better Topic Models - 241:44
Modeling Social Network Data41:59
Static Network Data42:24
Email Contact Network43:57
Data44:19
Latent Variable Models for Static Networks44:47
Example: The Latent Space Model - 146:06
Example: The Latent Space Model - 246:45
Example: The Latent Space Model - 348:15
Example: The Latent Space Model - 449:28
Example: Relational Topic Model49:41
Example: Stohastic Block Model - 150:50
Example: Stohastic Block Model - 251:39
Example: Stohastic Block Model - 351:44
A Unified View ... - 152:46
A Unified View ... - 253:29
A Unified View ... - 353:33
A Unified View ... - 453:47
Examples - 153:56
Examples - 254:09
Examples - 354:36
Examples - 454:55
Examples - 555:08
Examples - 655:10
Dynamic Networks: Discrete Time55:41
Latent Variable Models for Dynamic Networks56:33
Dynamic Latent Binary Feature Model56:58
Dynamic Networks. Continuous Time57:44
Modeling Relational Event Data59:17
Relational Event Model - 159:59
Relational Event Model - 201:01:24
Application: Classroom Dynamics01:02:14
Application: Personal Email Management - 101:02:29
Application: Personal Email Management - 201:02:59
Concluding Comments01:04:08
Time Complexity of Learning Algorithms - 101:04:14
Time Complexity of Learning Algorithms - 201:04:34
Additional Aspects01:05:18
Summary01:06:02