Social Mining & Big Data Analy1cs Big Data, Human Mobility & - - PowerPoint PPT Presentation

▶
social mining big data analy1cs
SMART_READER_LITE
LIVE PREVIEW

Social Mining & Big Data Analy1cs Big Data, Human Mobility & - - PowerPoint PPT Presentation

Mar 02, 2024 262 likes •666 views

Social Mining & Big Data Analy1cs Big Data, Human Mobility & Migra4on Roberto Trasar1 roberto.trasar1@is1.cnr.it h4p://www.sobigdata.eu/ Moving Object data (Vehicles) Call Detail Records (Phone data) Social Networks geo-located data

slide-1
SLIDE 1

Social Mining & Big Data Analy1cs

Big Data, Human Mobility & Migra4on

h4p://www.sobigdata.eu/

Roberto Trasar1 roberto.trasar1@is1.cnr.it

slide-2
SLIDE 2

Moving Object data (Vehicles)

slide-3
SLIDE 3

Call Detail Records (Phone data)

slide-4
SLIDE 4

Social Networks geo-located data

slide-5
SLIDE 5

Mobility Data Mining: Applica4ons

n Moving object and trajectory data mining has many important, real-world applications driven by the real need

n

Ecological analysis (e.g., animal scientists)

n

Weather forecast

n

Traffic control

n

Location-based services

n

Homeland security (e.g., border monitoring)

n

Law enforcement (e.g., video surveillance)

n

…

slide-6
SLIDE 6

mobility data mining landscape

Algorithms Models

Individual Behaviors Collec1ve Mobility Global Models

G y m Hospital Restaura nt

a

P>(a)

Tij ∝ pop2

i popj

(popi + sij)(popi + sij + popj)

raw trajectory data basic trajectory patterns derived models

semantics

slide-7
SLIDE 7

URBAN MOBILITY ATLAS

Analyzing the collec1ve behavior

slide-8
SLIDE 8
slide-9
SLIDE 9

Urban Mobility Atlas http://kdd.isti.cnr.it/uma2/

slide-10
SLIDE 10
slide-11
SLIDE 11

Flows of vehicles to the two airports

Vehicles of the sample have been re-scaled using ACI data of the

circula1ng vehicle fleet.

slide-12
SLIDE 12

Discovering new borders

1 2 3 4 O/D Community Discovery

slide-13
SLIDE 13

INDIVIDUAL MOBILITY NETWORKS

A user-centric view of mobility data

slide-14
SLIDE 14

How to synthesize Individual Mobility?

Mobility Data Mining methods automatically extract relevant episodes: locations and movements.

slide-15
SLIDE 15

Cluster & rank individual preferred locations

  • A key ini1al step is the study of the

user’s personal loca+ons, i.e., the places

  • r areas where the user stops to perform

any kind of ac1vity.

  • The problem consists in discovering the

set of observa1ons defining the personal loca1ons.

15

slide-16
SLIDE 16

Individual Mobility Profile

  • Besides loca1ons, the mobility of a user is

characterized by the trajectories that start and end in the user’s personal loca1ons.

  • These trajectories can be clustered with respect to

their similarity.

  • From each cluster can be extracted a

representa1ve trajectory, named rou+ne.

  • The set of rou1nes, i.e., the individual mobility

profile Pu, is an abstrac1on in 1me and space of the systema1c movements of a user.

16

slide-17
SLIDE 17

How to synthesize Individual Mobility?

Graph abstraction based

  • n locations (nodes) and

movements (edges)

Trip Features Length Dura1on Time Interval Average Speed Network Features centrality clustering coefficient average path length predictability entropy hubbiness degree betweenness volume edge weight flow per loca1on

slide-18
SLIDE 18

Individual mobility indicator

Radius of gyration k-radius of gyra4on

the characteristic distance traveled by individuals the radius computed on the k most visited locations

slide-19
SLIDE 19

K=4

explorers returners

The movements between the K loca1ons cannot represent the user All the mobility of the user can be represented by the movements between the K loca1ons Two different and separated behaviors

slide-20
SLIDE 20

Individual Call Profile and Classifica4on

123643 Cell12 24/06/2015 14:05 123643 Cell12 24/06/2015 18:13 123643 Cell15 25/06/2015 11:05 123643 Cell15 25/06/2015 20:42 123643 Cell11 25/06/2015 21:05 123643 Cell12 26/06/2015 10:01 …. t1 = [00:00-08:00) t2 = [8:00-19:00) t3 = [19:00-24:00)

A condensed representa1on of the user’s phone calls: Individual Call profile (ICP). It is used to classify his behavior.

slide-21
SLIDE 21

INDIVIDUAL TO COLLECTIVE

Modelling individuals to discover correla1ons and pa4erns among the collec1vity

slide-22
SLIDE 22

Big Data: Diversity and economic development

slide-23
SLIDE 23

Regular vs Occasional

slide-24
SLIDE 24

The ABC classifier

slide-25
SLIDE 25

Mobility predic4on

  • Predic1on of the individual mobility
  • Based on profiles:

– If the user is following one of her rou1nes, she will con1nue to do so – Otherwise, check if other users’rou1nes fit the actual trip, and use them now predic1on

slide-26
SLIDE 26

Boos4ng Carpooling with Network Analysis

  • Match

– Rou1ne containment – A driver can pick up an

  • ther along her rou1ne
  • Network

– Nodes = users – Edges = pairs of users with matching rou1nes

26

passenger driver

PDE

slide-27
SLIDE 27

Case Study Results

27

< 5% SOV

slide-28
SLIDE 28

Detec4ng Events – Example of Piazza San Pietro

slide-29
SLIDE 29
  • St. Peter’s Square (Piazza San Pietro)

Characterizing “Padre Pio’s” Event

Event Day afer Mean day - Week 5 Mean day - Week 6

From area N. 2 3 4 5

  • utbound

Day afer

1 From area N. 1 2 3 4 5

  • utbound

Event

slide-30
SLIDE 30

MIGRATION STUDIES

slide-31
SLIDE 31

Big datasets

  • Social network and web data
  • Twi4er Streaming data: various Twi4er datasets from project

partners, in various languages, with geoloca1on

  • GDELT Knowledge Graph database, a Big Data repertoire of online

news ar1cles.

  • Mobile phone data
  • Orange dataset: mobile calls between Senegal and the rest of the

world (country to country, 2012).

  • Highly educated migrants
  • Company data (Estonia and Italy): members of the governing boards
  • f companies (with place of birth).
  • Publica1on data: DBLP (computer science) and APS (physics)
slide-32
SLIDE 32

The story: Migra4on stages

  • GO: Understanding migra4on flows and stocks
  • Migra1on stocks
  • Brain-drain and scien1fic migra1on
  • Policy and illegal migra1on
  • STAY: Evalua4ng migrant integra4on
  • Sen1ment related to migra1on topics
  • Migra1on and language
  • Mul1-culturality and sen1ment
  • Migrant start-uppers
  • RETURN: Return of migrants
  • Data journalism approach
slide-33
SLIDE 33

STAY

Sen1ment on migra1on topics: Percep1on of the Mediterranean Refugee Crisis

slide-34
SLIDE 34

Sen4ment on migra4on topics: Percep4on of the Mediterranean Refugee Crisis

  • What is the evolu4on of the discussions about refugees

migra1on in Twi4er?

  • What is the sen4ment of users across Europe in

rela1on to the refugee crisis?

  • What is the evolu4on of the percep4on in countries

affected by the phenomenon?

  • Are users more polarised in countries most impacted

by the migra1on flow?

slide-35
SLIDE 35

Analy4cal Framework

  • An analy1cal framework to interpret social trends from

large tweet collec1ons by extrac1ng and crossing informa1on about the following three dimensions: – Time – Space

  • User loca1on
  • Loca1on men1ons

– Sen1ment

  • Tweet sen1ment
  • User sen1ment
  • Perform mul1dimensional analyses considering content

and loca1ons in 1me

slide-36
SLIDE 36

Deriving Sen4ment

Posi1ve Hashtags Nega1ve Hashtags Posi1ve Tweets Nega1ve Tweets Posi1ve Users Nega1ve Users

Enrich hashtag seeds from #-tag co-occurrence

Ini1al seeds

#refugeeswelcome #refugessnotwelcome

slide-37
SLIDE 37

Sen4ment on migra4on topics: Percep4on of the Mediterranean Refugee Crisis

European country men4ons

AT-HU border

  • pens

Flow shif to Croa1a

News about Syria Terrorist a4ack in Nigeria

Africa & Middle East country men4ons

slide-38
SLIDE 38

Sen1ment Analysis in UK

  • Posi1ve and nega1ve users for different ci1es in UK before and afer

September 4 (death of Alan Kurdi, borders between AT HU, Germany welcomes refugees).

– bars show the number of polarized posi1ve and nega1ve users by city

slide-39
SLIDE 39

Thank you

h4p://www.sobigdata.eu/