en
0.25
0.5
0.75
1.25
1.5
1.75
2
Who to Follow and Why: Link Prediction with Explanations
Published on Oct 07, 20142793 Views
User recommender systems are a key component in any on-line social networking platform: they help the users growing their network faster, thus driving engagement and loyalty. In this paper we study
Related categories
Chapter list
Who to Follow and Why: Link Prediction with Explanations00:00
Motivation00:00
Modeling socio-topical relationships - 101:16
Modeling socio-topical relationships - 201:29
Modeling socio-topical relationships - 301:41
Modeling socio-topical relationships - 402:09
Modeling socio-topical relationships - 502:48
Latent factor modeling of socio-topical relationships - 103:07
Latent factor modeling of socio-topical relationships - 203:50
Latent factor modeling of socio-topical relationships - 304:32
Latent factor modeling of socio-topical relationships - 404:57
Latent factor modeling of socio-topical relationships - 505:30
WTFW: Generative model06:01
Link prediction09:05
Link labeling and explanations09:57
Evaluation10:59
Accuracy on link prediction - 111:22
Accuracy on link prediction - 211:48
Link labeling12:02
Anecdotal evidence12:28
Conclusion and future work13:19
Thank you!14:06