Location-Based Social Networks Yu Zheng and Xing Xie Microsoft Research Asia Chapter 8 and 9 of the...

40
Location-Based Social Networks Yu Zheng and Xing Xie Microsoft Research Asia Chapter 8 and 9 of the book Computing with Spatial Trajectories

Transcript of Location-Based Social Networks Yu Zheng and Xing Xie Microsoft Research Asia Chapter 8 and 9 of the...

Page 1: Location-Based Social Networks Yu Zheng and Xing Xie Microsoft Research Asia Chapter 8 and 9 of the book Computing with Spatial Trajectories.

Location-Based Social Networks

Yu Zheng and Xing Xie

Microsoft Research Asia

Chapter 8 and 9 of the bookComputing with Spatial Trajectories

Page 2: Location-Based Social Networks Yu Zheng and Xing Xie Microsoft Research Asia Chapter 8 and 9 of the book Computing with Spatial Trajectories.

Outline • Chapter 8 (Location-based social networks: Users)

– Concepts, definition, and research philosophy – Modeling user location history– Computing user similarity based on location history– Friend recommendation and community discovery

• Chapter 9 (Location-based social networks: Locations)– Generic travel recommendations

• Mining interesting locations and travel sequences• Trip planning and itinerary recommendation • Location-activity recommendation

– Personalized travel recommendation• User-based collaborative filtering• Item-based collaborative filtering• Open challenges

Page 3: Location-Based Social Networks Yu Zheng and Xing Xie Microsoft Research Asia Chapter 8 and 9 of the book Computing with Spatial Trajectories.

Social Networks

“A social network is a social structure made up of individuals connected by one or more specific types of

interdependency, such as friendship, common interests, and shared knowledge.”

3

Page 4: Location-Based Social Networks Yu Zheng and Xing Xie Microsoft Research Asia Chapter 8 and 9 of the book Computing with Spatial Trajectories.

Social Networking Services

A social networking service builds on and reflects the real-life social networks among people through online platforms such as a website, providing ways for users to share ideas, activities, events, and interests over the Internet.

4

Page 5: Location-Based Social Networks Yu Zheng and Xing Xie Microsoft Research Asia Chapter 8 and 9 of the book Computing with Spatial Trajectories.

Locations

Location-acquisition technologiesOutdoor: GPS, GSM, CDMA, …Indoor: Wi-Fi, RFID, supersonic, …

Representation of locationsAbsolute (latitude-longitude coordinates)Relative (100 meters north of the Space Needle) Symbolic (home, office, or shopping mall)

Forms of locationsPoint locationsRegions Trajectories

5

Page 6: Location-Based Social Networks Yu Zheng and Xing Xie Microsoft Research Asia Chapter 8 and 9 of the book Computing with Spatial Trajectories.

Locations + Social Networks

Add a new dimension to social networksGeo-tagged user-generated media: texts, photos, and videos, etc.Recording location history of users

Location is a new object in the networkBridging the gap between the virtual and physical worlds

Sharing real-world experiences onlineConsume online information in the physical world

6

Page 7: Location-Based Social Networks Yu Zheng and Xing Xie Microsoft Research Asia Chapter 8 and 9 of the book Computing with Spatial Trajectories.

Examples

7

Physical world

Virtual world

Sharing &Understanding

Generating &Consuming

Inte

racti

ons

Page 8: Location-Based Social Networks Yu Zheng and Xing Xie Microsoft Research Asia Chapter 8 and 9 of the book Computing with Spatial Trajectories.

Location-Based Social Networks

8

Sharing

Understanding

Sharing Geo-tagged mediaVirtual Physical worlds

UnderstandingUser interests/preferencesLocation propertyUser-user, location-location, user-location correlations

Locations

Social networks

Locations An new dimension: Geo-tagAn new object

Social networksExpanding social structuresRecommendations

UsersLocationsmedia

Page 9: Location-Based Social Networks Yu Zheng and Xing Xie Microsoft Research Asia Chapter 8 and 9 of the book Computing with Spatial Trajectories.

Data + Intelligence

Third Party Services

Microsoft Services

Scenarios - Sharing

Page 10: Location-Based Social Networks Yu Zheng and Xing Xie Microsoft Research Asia Chapter 8 and 9 of the book Computing with Spatial Trajectories.

Data + Intelligence

Third Party Services

Microsoft Services

Data Information Knowledge Intelligence

Scenarios - Understanding

Page 11: Location-Based Social Networks Yu Zheng and Xing Xie Microsoft Research Asia Chapter 8 and 9 of the book Computing with Spatial Trajectories.

Location-Based Social Networks (LBSN)

11

not only mean adding a location to an existing social network so that people in the social structure can share location-embedded information, but also consists of the new social structure made up of individuals connected by the interdependency derived from their locations in the physical world as well as their location-tagged media content

Here, the physical location consists of the instant location of an individual at a given timestamp and the location history that an individual has accumulated in a certain period. The interdependency includes not only that two persons co-occur in the same physical location or share similar location histories but also the knowledge, e.g., common interests, behavior, and activities, inferred from an individual’s location (history) and location-tagged data.

From Book “Computing With Spatial Trajectories”

Page 12: Location-Based Social Networks Yu Zheng and Xing Xie Microsoft Research Asia Chapter 8 and 9 of the book Computing with Spatial Trajectories.

Categories of LBSN Services

Geo-tagged-media-based

Point-location-driven

Trajectory-centric

12

Geo-

LBSN Services Focus Real-time Information

Geo-tagged-media-based Media Normal Poor

Point-location-driven Point location Instant Normal

Trajectory-centric Trajectory Relatively Slow Rich

Page 13: Location-Based Social Networks Yu Zheng and Xing Xie Microsoft Research Asia Chapter 8 and 9 of the book Computing with Spatial Trajectories.

Locations

Research Philosophy

13

Use

r-L

ocat

ion

Gra

ph

Users

Trajectories

User Graph

User Correlation

Location Graph

Location Correlation

Location-tagged user-generated content

Page 14: Location-Based Social Networks Yu Zheng and Xing Xie Microsoft Research Asia Chapter 8 and 9 of the book Computing with Spatial Trajectories.

Research Philosophy

SharingMaking sense of the dataEffective and efficient information retrieval……

14

Page 15: Location-Based Social Networks Yu Zheng and Xing Xie Microsoft Research Asia Chapter 8 and 9 of the book Computing with Spatial Trajectories.

15

Replay

Share

Replay travel experiences on a map with a GPS trajectory

Page 17: Location-Based Social Networks Yu Zheng and Xing Xie Microsoft Research Asia Chapter 8 and 9 of the book Computing with Spatial Trajectories.

Research Philosophy

UnderstandingUnderstanding usersUnderstanding locationsUnderstanding events

17

User Graph

Location Graph

Page 18: Location-Based Social Networks Yu Zheng and Xing Xie Microsoft Research Asia Chapter 8 and 9 of the book Computing with Spatial Trajectories.

Understanding Users (Chapter 8)

18

User similarity/link prediction

Experts/Influencers detection

Community Discovery

Page 19: Location-Based Social Networks Yu Zheng and Xing Xie Microsoft Research Asia Chapter 8 and 9 of the book Computing with Spatial Trajectories.

Understanding Locations (Chapter 9)

Generic recommendationMost interesting locations and travel routes/sequencesItinerary planningLocation-activity recommenders

Personalized recommendationLocation recommendations

User-based collaborative filtering modelItem-based collaborative filtering model

Open challenges

19

Page 20: Location-Based Social Networks Yu Zheng and Xing Xie Microsoft Research Asia Chapter 8 and 9 of the book Computing with Spatial Trajectories.

Understanding Events

Anomaly Crowd Behavioral Patterns

20

Page 21: Location-Based Social Networks Yu Zheng and Xing Xie Microsoft Research Asia Chapter 8 and 9 of the book Computing with Spatial Trajectories.

Mining User Similarity Based on Location History

21

Page 22: Location-Based Social Networks Yu Zheng and Xing Xie Microsoft Research Asia Chapter 8 and 9 of the book Computing with Spatial Trajectories.

22Grouping users in terms of the similarity between their location histories, and conduct personalized location recommendations.

GIS ‘08/Trans. On the Web

Page 23: Location-Based Social Networks Yu Zheng and Xing Xie Microsoft Research Asia Chapter 8 and 9 of the book Computing with Spatial Trajectories.

23

GPS trajectories

Geo-Location history

User similarity

Cinema 2 Museum 1

Coffee 3

Semantic Location history

Model user location historyGeographic spacesSemantic spaces

Mining User Similarity Based on Location History

Page 24: Location-Based Social Networks Yu Zheng and Xing Xie Microsoft Research Asia Chapter 8 and 9 of the book Computing with Spatial Trajectories.

Mining User Similarity Based on Location History

Computing user similarityHierarchical propertiesSequential propertiesPopularity of a location

24Stands for a stay point SStands for a stay point cluster cij

{C }High

Low

Shared Hierarchical Framework

c10

c20 c21

c30 c31 c32 c33 c34

A B2

C4

S1

A B D C

D0.5

E5

E

F2

2 4 0.5 2

1 2 3 4 5

F2

G2

2

6

0.5 1 1

1 0.5 2 3.5 1

S2

7

,

Page 25: Location-Based Social Networks Yu Zheng and Xing Xie Microsoft Research Asia Chapter 8 and 9 of the book Computing with Spatial Trajectories.

Layer 1

Layer 2

Layer 3

G3

G1

G2

a

e

c

A

B

3. Individual graph building

GPS Logs of User 1

GPS Logs of User 2

GPS Logs of User n

GPS Logs of User i

GPS Logs of User i+1

GPS Logs of User n-1

Stands for a stay point SStands for a stay point cluster cij

{C }High

Low

Shared Hierarchical Framework

c10

c20 c21

c30 c31 c32 c33 c34

Layer 1

Layer 2

Layer 3

G3

G1

G2High

Low

a bd

e

A

B

GPS Logs of User 1

GPS Logs of User 2

1. Stay point detection

2. Hierarchical clustering

Page 26: Location-Based Social Networks Yu Zheng and Xing Xie Microsoft Research Asia Chapter 8 and 9 of the book Computing with Spatial Trajectories.

Friend and Location Recommendation

26

Similar Users Retrieval

User taste inferring

L1, L2, …., Lnu1 u2..

un

x1, x2, …, xny1, y2, …, yn

.

.z1, z2, …, zn

Location Candidates DiscoveringRanking Locations

Page 27: Location-Based Social Networks Yu Zheng and Xing Xie Microsoft Research Asia Chapter 8 and 9 of the book Computing with Spatial Trajectories.

Mining interesting locations and travel sequences from GPS trajectories

27

Page 28: Location-Based Social Networks Yu Zheng and Xing Xie Microsoft Research Asia Chapter 8 and 9 of the book Computing with Spatial Trajectories.

28Mining interesting locations, travel sequences, and travel experts from user-generated travel routes

Page 29: Location-Based Social Networks Yu Zheng and Xing Xie Microsoft Research Asia Chapter 8 and 9 of the book Computing with Spatial Trajectories.

29

Users: Hub nodes

Locations: Authority nodes

The HITS-based inference model

Page 30: Location-Based Social Networks Yu Zheng and Xing Xie Microsoft Research Asia Chapter 8 and 9 of the book Computing with Spatial Trajectories.

Location-Activity Recommendation

Page 31: Location-Based Social Networks Yu Zheng and Xing Xie Microsoft Research Asia Chapter 8 and 9 of the book Computing with Spatial Trajectories.

31

Goal: To Answer 2 Typical Questions

A recommended location

Recommended activity list

Recommended location list

Location query

Activity query

Q2: where should I go if I want to do something?

(Location recommendation given activity query)

Q1: what can I do there if I visit some place?

(Activity recommendation given location query)

Page 32: Location-Based Social Networks Yu Zheng and Xing Xie Microsoft Research Asia Chapter 8 and 9 of the book Computing with Spatial Trajectories.

Problem

Data sparseness (<0.6% entries are filled)

32

Activities

Locations5 ? ?

? 1 ?

1 ? 6

Forbidden City

Tourism Exhibition Shopping

Bird’s Nest

Zhongguancun

?

Page 33: Location-Based Social Networks Yu Zheng and Xing Xie Microsoft Research Asia Chapter 8 and 9 of the book Computing with Spatial Trajectories.

33

Solution• Collaborative filtering with collective matrix factorization

– Low rank approximation, by minimizing

where U, V and W are the low-dimensional representations for the locations, activities and location features, respectively. I is an indicatory matrix.

Loc

atio

ns

Features Activities

X = UVTY = UWT Z = VVTU V

Activities

Loc

atio

ns

Act

ivit

ies

Page 34: Location-Based Social Networks Yu Zheng and Xing Xie Microsoft Research Asia Chapter 8 and 9 of the book Computing with Spatial Trajectories.

Locations

Research Philosophy

34

Use

r-L

ocat

ion

Gra

ph

Users

Trajectories

User Graph

User Correlation

Location Graph

Location Correlation

Location-tagged user-generated content

Page 35: Location-Based Social Networks Yu Zheng and Xing Xie Microsoft Research Asia Chapter 8 and 9 of the book Computing with Spatial Trajectories.

New Challenges in LBSNs

Heterogeneous networksLocations and users Geo-tagged media and trajectories

Special propertiesHierarchy / granularitySequential property

Fast evolving Easy to access a new locationUser experience/knowledge changes

35

Conferences

Authors

Papers

Locations

Users

Media

Page 36: Location-Based Social Networks Yu Zheng and Xing Xie Microsoft Research Asia Chapter 8 and 9 of the book Computing with Spatial Trajectories.

GeoLife Trajectory Dataset (1.1)

Version 1.0 Version 1.1 Incremental

Time span of the collection 04/2007 – 08/2009 04/2007 – 12/2010 +16 months

Number of users 155 167 +12

Number of trajectories 15,854 17,355 +1,501

Number of points 19,304,153 22,294,264 2,990,111

Total distance 600,917 km 1,070,406 km +469,489 km

Total duration 44,776 hour 48,349 hour +3,573 hour

Effective days 8,977 9,694 +717

Transportation mode

Distance (km)

Duration (hour)

Walk 11,457 5,126

Bike 6,335 2,304

Bus 21,931 1,430

Car & taxi 34,127 2,349

Train 74,449 459

Airplane 28,493 37

Other 10,886 335

Total 187,679 12,041

Page 38: Location-Based Social Networks Yu Zheng and Xing Xie Microsoft Research Asia Chapter 8 and 9 of the book Computing with Spatial Trajectories.

Conferences

ACM SIGSPATIAL Workshop on Location-Based Social Networks LBSN 2011: Nov. 1, 2011, in Chicago (3rd year)Over 40 attendees this year26 submissions. 10 full papers and 4 short papers

38

Page 39: Location-Based Social Networks Yu Zheng and Xing Xie Microsoft Research Asia Chapter 8 and 9 of the book Computing with Spatial Trajectories.

Summary

Locations and social networksSharing and understandingNew challenges and new opportunities

39