PHEME Project at EDF 2015

PHEME http://www.pheme.eu

PHEME

Veracity: The 4th Challenge of Big Data

Tomás Pariente [email protected]

@tpariente


Phemes & social media

• Memes are thematic motifs that spread through

social media in ways analogous to genetic traits

• We coined the term phemes to add truthfulness

and deception to the mix

2

http://en.wikipedia.org/wiki/Pheme

PHEME focuses on a fourth crucial, but hitherto largely unstudied, challenge: Veracity

http://en.wikipedia.org/wiki/Pheme


Rumour analysis: The Problem

Now mostly manual

Rumours are challenging

Some rumours could take hours, days, weeks or even months to die out

Ill-meaning humans can currently outsmart computers (and humans)

and appear genuine


Rumour analysis: The Problem

Mike Brown shot by police in Ferguson

We have different rumors emerging from the topic

We don’t know if they are true.

We see the spikes and sometimes they come back

(different temporal dynamics)

We need to understand the overall conversation to see the

different points of view and how the rumours go forward


Social Media is Rife with Phemes


Social Media is Rife with Phemes


From manual to automatic

We are investigating...

Ontologies for modelling phemes

Use a priori knowledge (LOD) and reasoning to detect contradictions

Model phemes spread across media, social networks, and time

Conversational analysis

Real-time rumour classification

Pheme visualisation to support veracity checking: media maps, impact maps, geographical maps…


PatientsLikeMe

Cross-Media

Content Linking,

Spatio-Temporal

Grounding

Multilingual

LOD-Based

IE and Opinion

Mining

Rumour

Detection

And

Veracity

Classification

USE CASES

Veracity Intelligence In Patient

Care

Digital Journalism

Linked Open Data Rumour Ontologies &

Reasoning (GraphDB)

Historical

Data

Archive

PHEME

Visual

Analytics

Dashboard

Social Context

Models

Trust,

Authority,

Implicit

Networks

Technology Outcome:

Open Source Computational Framework

...

…

PHEME VERACITY INTELLIGENCE

FRAMEWORK

PHEME http://www.pheme.eu Some Meeting, Some Place, Some Date

Physical Infrastructure and Virtualization

Storage Infrastructure

Processing

Knowledge

Base

Stream Processing Batch Processing

Messa

gin

g /

Co

mm

s

Mu

ltil

ing

ual D

ata

Data

Collection

Rumour

Classification Usage Curation

Data Value Chain

IT V

alu

e C

hain

IT Big Data Layer

Veracity and Language Value Chain

System Workflow Orchestration

Mu

ltil

ing

ual D

ata

S

ocia

l M

edia

Multili

ngual D

ata

Data

Data

SW

LT Processing

& Analytics

Raw data

Repository

Lang

Detection

OntoText GraphDB™

Mu

ltil

ing

ual D

ata

M

ult

ilin

gu

al D

ata

E

nd U

sers

Phem

e D

ashboard

,

Journ

alis

t D

ashboard

Event

Detection

NLP

Processing

Annotation &

Training

Cross-media

linking

Cross-lingual

analysis

Reso

urc

e M

an

ag

em

en

t

PHEME Big Data Architecture

for veracity analysis


Application areas

Open-source social intelligence tools for data journalism

Involves journalists from SwissInfo.ch, the Guardian,

New York Times, and other media

Improving healthcare What health-related rumours are discussed in patient-

clinician consultations

Preventative medical advice, e.g. warn patients not to

trust certain rumours, when researching their disease

online


PHEME Dashboard

And dynamics Over Time/Location

11

vs replies


Journalism Dashboard Prototype

12


Acknowledgement

The PHEME research project has received funding from the European Union's Seventh Framework Programme for research, technological development and demonstration under grant agreement No. 611233.

13

This document does not represent the opinion of the European Community, and the European Community is not responsible for

any use that might be made of its content

Thanks!