Presentation is loading. Please wait.

Presentation is loading. Please wait.

Understanding Online Social Network Usage from a Network Perspective F. Schneider et al (T-Labs, AT&T) Internet Measurement Conference 2009 Networking.

Similar presentations


Presentation on theme: "Understanding Online Social Network Usage from a Network Perspective F. Schneider et al (T-Labs, AT&T) Internet Measurement Conference 2009 Networking."— Presentation transcript:

1 Understanding Online Social Network Usage from a Network Perspective F. Schneider et al (T-Labs, AT&T) Internet Measurement Conference 2009 Networking Journal Club 26th Feb 2010

2 Outline 1.Introduction 2.OSN features 3.Data set 4.Methodology 5.Feature Popularity 6.OSN Session Characteristics 7.Dynamic within OSN Sessions 1

3 Introduction  OSN: Half a billion users  Facebook adds over 377,000 users every day  Interesting: For ISPs (transport data and provide connectivity) For OSN service providers (develop and operate scalable systems) For researchers and developers (indentify trends and improve designs) 2

4 Introduction  Objectives: Which features of OSN are popular and capture the users attention? What is the impact of OSNs on the network? What needs to be considered whe designing future OSNs? Is the user’s behavior homogeneous? 3

5 OSN features  Profiles, friends, photos, videos, messaging, groups… third-party applications  Example: 4

6 OSN features  Active (user’s clicks) vs. Indirect (auto triggered, e.g. ajax, javascripts, images…)  Using of other locations/servers 5

7 Data set  6 http header traces  2 ISPs  20,000 DSL users: 2500(6000) use OSN.  DAG cards  4 OSNs: Facebook, StudiVZ, Hi5, LinkedIn 6

8 Methodology  Extract OSN session clickstream  To do this, they need to be able to know OSN traffic: manual traces  With manual traces: Site names Cookies HTTPS (or not) Handshakes Signatures and patterns 7

9 Methodology 8

10 Lessons Learned (manual traces)  Reverse-engineering user interactions with OSNs from HTTP traces is non-trivial  Major bottleneck: manual traces for validation and classification of the rr-pairs  Number of patterns for each OSN is large (253, 218, 206 and 299).  OSN restructures => new patterns  HTTPS  Tamper Data plug-in for Firefox very useful 9

11 Feature popularity  Which OSN features are more fascinating? Does it depend on OSN?  ISP needs to care as it might impact bandwidth demand  OSN needs to care as it might impact server resources 10

12 Active requests/All requests 11

13 Across time/Profiles access 12

14 Bytes per session/Duration 13 Heavy-tailed distribution: Weibull Session size between 200KB and 10MB High Variability: mean of about 40 min More than 10% last longer than 1 hour Peak between 5 sec and 2 min

15 Dynamics 14

16 Summary  Reconstruct OSN clickstreams from HTTP header traces from passive monitoring.  Methodology for identifying OSN sessions and user actions within the OSN.  Indentify the features that are important to the users.  Generate workloads for evaluating novel OSNs. 15


Download ppt "Understanding Online Social Network Usage from a Network Perspective F. Schneider et al (T-Labs, AT&T) Internet Measurement Conference 2009 Networking."

Similar presentations


Ads by Google