Extracting Social Events for Learning Better Information Diffusion Models thumbnail
Pause
Mute
Subtitles
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Extracting Social Events for Learning Better Information Diffusion Models

Published on Sep 27, 20136261 Views

Learning of the information diffusion model is a fundamental problem in the study of information diffusion in social networks. Existing approaches learn the diffusion models from events in social netw

Related categories

Chapter list

Extracting Social Events for Learning Better Information Diffusion Models00:00
Highlights00:18
Information diffusion model and events!00:55
Learning information diffusion model from events - 102:05
Learning information diffusion model from events - 202:28
Learning information diffusion model from events - 302:34
Learning information diffusion model from events - 403:11
Social Influence vs. External Influence03:47
Challenge 1: How do we define the sources of influence?04:40
Challenge 2: Inference dependency06:26
Definitions: data stream, event, and actions07:10
The Latent Action Diffusion Path (LADP) Model08:04
The LADP Model - 109:08
The LADP Model - 209:37
EM-based inference algorithm10:20
Experiment Setup10:52
Twitter semi-synthetic Dataset - 111:57
Twitter semi-synthetic Dataset - 212:04
Twitter semi-synthetic Dataset - 413:45
Twitter network14:11
DBLP Datasets14:56
Inferred socially-sourced portion15:10
Case study: two events in Twitter UIC community16:40
Conclusion17:11