1 of 54

Knowledge Graphs for Social Good: three challenges

Victor de Boer

With input from: Anna Bon, Christophe Guéret, Stephane Boyera , Nana Baah Gyan, Chris van Aart, Max Froumentin, Aman Grewal, Mary Allen, Amadou Tangara, Etienne Barnard, Hans Akkermans, André Baart, Gossa Lo, Myrthe van der Wekken, Onno Valkering, Fahad Ali, Romy Blankendaal, Stefan Schlobach, the Pressing Matter team…

four

2 of 54

Knowledge Graphs and the Semantic Web

Knowledge Graphs for Social Good

KGs for the rural poor: three challenges

A fourth challenge: polyvocality

Infrastructure

Interface

Relevancy

3 of 54

More and more structured data available online

Government data

Social web data

Medical data

Museum data

Research data

Development data

Moverum.com

4 of 54

CC-by-nc-nd https://www.flickr.com/photos/joinash/

Moving away from silos

5 of 54

6 of 54

Web of Documents (WWW)�Linked Documents

7 of 54

Web of Data / Knowledge

Linked Data

Semantic Web

8 of 54

Tim Berners-Lee

(The inventor of the Web)

(and the Semantic Web)

9 of 54

10 of 54

How does all this work?

Structured data not documents

Graph (networked) data!

W3C Web standards stack

URIs, HTTP, RDF, RDFa, RDFS, OWL, SKOS, SPARQL, etc.

11 of 54

3 principles for linked data/semantic web

12 of 54

Use HTTP IRIs for Things

Internationalised Resource Identifier (IRI) is a string of characters used to identify a name of a resource

http://rijksmuseum.nl/data/painting001

or (rijks:painting1)

13 of 54

Resource Description Framework (RDF)

Semantic Web standard for writing down data, information, knowledge

(Subject, Relation, Object)

<Painting001, has_location, Amsterdam>

Painting001

Amsterdam

has_location

Triples!!

14 of 54

Triples form

rijks:Painting001

geo:Haarlem

dcterms:spatial

dcterms:creator

rijks:Frans_Hals

147590

geo:population

52.38084, 4.63683

geo:partOf

geo:Noord-Holland

geo:Netherlands

geo:coordinates

geo:partOf

ex:Painting002

dcterms:creator

Knowledge Graphs

15 of 54

Relational Databases vs Knowledge Graphs

Relational Database

Knowledge Graph

16 of 54

Knowledge graphs and AI

17 of 54

But, is this all just theory?

18 of 54

KNOWLEDGE GRAPHS EVERYWHERE

19 of 54

http://lod-cloud.net/

20 of 54

(Frank van Harmelen’s Good News slide)

KNOWLEDGE GRAPHS EVERYWHERE

21 of 54

Knowledge graphs

Knowledge graphs are a useful way of representing data, information and knowledge …

    • …that are heterogeneous
    • …in such a way that others (systems/people) can interpret a piece of data correctly
    • …by making the semantics/meaning of a piece of information explicit
    • …using graph (network)
    • …explicity on the Web

22 of 54

Knowledge graphs for Social Good

23 of 54

24 of 54

Why now?

Where AI used to be hidden, with new success and increased societal impact, questions about AI for Good start to emerge..

  • Self driving cars
  • Cambridge analytica
  • Smart cameras
  • Data-driven governments
  • Health robots

25 of 54

Example: AI4good at UN

Based on available data a ML model was trained to predict the cost of various conflicts

  • GDP, tax, gender ratio in schools etc….

Identify SDG-related events in social media

Recognizes phrases like “next Saturday …”

Links to SDG

26 of 54

Example: Landportal

27 of 54

Example: Agrovoc/Agris Published by FAO

28 of 54

Example: connecting Aid information in Knowledge Graphs

  • Is the aid spent in places where the need is highest? Is it well distributed across the country?
  • A comparative index of aid versus the Human Development Index.
  • What is the geographic location of a project?
  • How does violent conflict in recipient countries affect aid activities?
  • How does aid spending as registered in the IATI standard compare to World Bank indicators?

Msc. Thesis by Kasper Brandt

29 of 54

Network of aid information

IATI:Higher Education

IATI:UN Habitat

Activity: Multi donor fund to support civil society in democracy related issues

Aid received (USD)

Geonames:Gambia

Worldbank:Gambia

N 13° 30' 0'' W 15° 30' 0'

is a

IATI:Sector

IATI:Organization

Geonames:Country

Worldbank:country

is a

is a

is a

30 of 54

End-user application

Kasper Brandt

31 of 54

32 of 54

Can the Knowledge Graphs (be made to) mean something for knowledge sharing even under very constraining conditions?

No internet, no computer, no electricity

Multitude of languages, levels of literacy

33 of 54

Three challenges for Bringing Knowledge Graphs to the Rural Poor

34 of 54

Make KGs usable in low-resource, low-connectivity contexts

Make KGs accessible for users with various (cultural) backgrounds and levels of literacy;

Develop knowledge sharing cases and applications relevant for the rural poor

Infrastructure

Interface

Relevancy

35 of 54

Case: Market information in rural Mali

36 of 54

Knowledge graph includes voice labels

rm:offering0001

rm:shea_butter

rm:product_name

rm:1000

rm:quantity

rdfs:label

rdfs:label

“Amande de Karité”@fr

“Shea Nuts”@en

speakle:voicelabel_ba

rm:audio_shea_nl.wav

rm:audio_shea_ba.wav

speakle:voicelabel_nl

rdfs:label

“1000”

speakle:voicelabel_ba

rm:audio_1000_nl.wav

rm:audio_1000_ba.wav

speakle:voicelabel_nl

rm:Mazankuy_Diarra

rm:kilo

rdfs:label

“kilo”@en

speakle:voicelabel_ba

rm:audio_kilo_nl.wav

rm:audio_kilo_ba.wav

speakle:voicelabel_nl

rm:unit_measure

rm:has_contact

37 of 54

“Slot and Filler” Text-to-Speech

Z_Diarra_ba.wav

offered by.wav

English:

Bambara:

15

liters

of

offered by

Zakari Diarra

15_ba.wav

L_ba.wav

Of_ba.wav

Honey_ba.wav

honey

38 of 54

Talking to Knowledge Graphs

Web applications

<VoiceXML> to SPARQL

Voice browser

RadioMarché

Linked market data

‘Allo Knowledge Graph?

DBpedia

GeoNames

Agrovoc

39 of 54

Challenge: Low-resource Knowledge sharing

High-end hardware, high connectivity

DOWNSCALING

Mid-range hardware, high connectivity

Affordable hardware, various connectivity situations

40 of 54

Kasadaka: Low-resource knowledge sharing platform

Kasadaka (“talking box”)

Andre Baart

41 of 54

Case: DigiVet

Gossa Lo, Myrthe van der Wekken, Romy Blankendaal

Veterinary service in North Ghana

Animal health ontology developed by eliciting information from domain experts using CommonKADS method

Users can interact with system through voice, simple visual interaction

42 of 54

Challenge: Knowledge exchange in low-connectivity setting

GSM network

43 of 54

Semantic Web in an SMS

Enable Semantic Web data exchange over GSM networks.

Converters to translate SPARQL HTTP request to SMS message (140 or 160 chars) and vice versa

Onno Valkering

44 of 54

Evaluation: 4 scenarios in 2 cases

Digivet and RadioMarche applications

Four scenarios / SPARQL queries in total

Results

45 of 54

Lessons learned

Knowledge Graphs allow for knowledge sharing in ICT4D cases

But we need to develop solutions that mean something on the ground

User-centric cases

Technological innovations

Voice-access to knowledge

Semantic Web without the Web

Low-resource computing

Infrastructure

Interface

Relevancy

46 of 54

Polyvocality: �A fourth challenge

47 of 54

The problem

Knowledge graphs are either made from existing sources or by humans…

..therefore they are sure to contain

Biased

Univocal

Single-view

Information, often ased on the majority-view.

This poses the danger of perpetuating biased view on data.

(gender, geographic location, colonial sources,…)

48 of 54

Bias Perspective

Metadata enrichment and bias detection of colonial architecture�Roz Sabir

49 of 54

50 of 54

2053 missionary objects from Africa

Loot

Gift

Idol

Fetish

Ancestor

PRESSING MATTER

OWNERSHIP, VALUE AND THE QUESTION OF COLONIAL HERITAGE IN MUSEUMS

51 of 54

Towards polyvocal Knowledge Graphs

Identifying and acquiring polyvocality knowledge

  • Identify existing voices
  • Elicit information from polyvocal sources

Representation of polyvocality: datamodels and formalisms

- Represent disagreement on categorisation, provenance, etc.

Presentation of polyvocal knowledge �- present it to variety of users, including

researchers

heritage professionals

general public

‘source communities’

52 of 54

Early work: Representing Traditional Knowledge

�1 How is the Sun dance ritual in the Hopi tribe different from the Sun dance ritual by the Cree people?

�2 What traditional knowledge is practised in Curacao?

e.g. 4 Who created the video “How to make�homemade briquettes”?�e.g. 5 What else does Anna know about?

Lois Hutubessy

53 of 54

Take home

Knowledge Graphs are the formalism to represent and share Data, Information and Knowledge on the Web

Knowledge Graphs are a part of the AI for Good agenda.

But to make them universally accessible we need to address

  1. usability in low-resource, low-connectivity contexts
  2. accessibility for users with various (cultural) backgrounds and skills
  3. develop cases and applications relevant for the rural poor

and

  1. Ensure that we can deal with polyvocal knowledge

54 of 54

Thank you

victordeboer.com

v.de.boer@vu.nl