Tutorial Cognition - Irene

Cognition for the
Semantic Web
Irene Celino + Tomi Kauppinen

Cognition… what?
Cognitive Computing refers to systems that learn at scale and interact naturally with
people to extend what humans or machines can do alone
(Eleni Pratsini – IBM Research, ESWC 2016 Keynote)
Cognitive Systems studies aim at (1) gaining a deeper understanding of how humans
realize their unique intelligent potential and (2) developing artificial cognitive agents
to assist humans in performing demanding tasks in order to strengthen their
autonomy
(Cognitive Systems Group, University of Bremen)

This morning tutorial:
Cognition for the Semantic Web
Irene will talk about
“Involving Humans in
Semantic Data Management”
 methods, techniques
and tools to include
humans in a Semantic Web
pipeline
 leverage humans to
develop better Semantic
Web systems
Tomi’s talk title is “Let us build
cognitive & semantic systems to
support understanding”
via visual examples on why
and how to make sense of
data and to understand
underlying phenomena
methods, evaluation,
discoveries

Involving Humans in
Semantic Data Management
Irene Celino (irene.celino@cefriel.com)
CEFRIEL – Milano, Italy

Agenda
Methods to involve people (a.k.a. crowdsourcing and its brothers)
Motivation and incentives (a.k.a. let’s have fun with games)
Crowdsourcing and the Semantic Web (a.k.a. this is SSSW after all…)

Methods to
involve people
What goals can humans help
machines to achieve? Which
scientific communities “exploit”
people? How to involve a crowd of
persons?
- Citizen Science
- Crowdsourcing
- Human Computation

Wisdom of crowds [1]
“Why the Many Are Smarter Than the Few and
How Collective Wisdom Shapes Business, Economies, Societies and Nations”
Criteria for a wise crowd
Diversity of opinion (importance of interpretation)
Independence (not a “single mind”)
Decentralization (importance of local knowledge)
Aggregation (aim to get a collective decision)
The are also failures/risks in crowd decisions:
Homogeneity, centralization, division, imitation, emotionality

Citizen Science [2]
Problem: a scientific experiment
requires the execution of a lot of
simple tasks, but researchers are busy Solution: engage the general audience
in solving those tasks, explaining that
they are contributing to science,
research and the public good
Example: https://www.zooniverse.org/

Crowdsourcing [3]
Problem: a company needs to execute
a lot of simple tasks, but cannot afford
hiring a person to do that job
Solution: pack tasks in bunches
(human intellingence tasks or HITs)
and outsource them to a very cheap
workforce through an online platform
Example: https://www.mturk.com/

Human Computation [4]
Problem: an Artificial Intelligence
algorithm is unable to achieve an
adequate result with a satisfactory
level of confidence
Solution: ask people to intervene when
the AI system fails, “masking” the task
within another human process
Example: https://www.google.com/recaptcha/

Spot the difference…
Similarities:
- Involvement of people
- No automatic replacement
Variations:
- Motivation
- Reward (glory, money, passion)
Hybrids or parallel!
Citizen Science
Crowdsourcing
Human
Computation

Motivation and
incentives
Apart from extrinsic rewards
(money, prizes, etc.) what are the
intrinsic incentives we can adopt to
motivate people? How can we
leverage “fun” through games and
game-like applications?
- Gamification
- Games with a Purpose (GWAP)

Gamification [5,6]
Problem: motivate people to execute
boring or mandatory tasks (especially
in cooperative environments) that they
are usually not very happy to do
Solution: introduce typical game
elements (e.g. points, badges,
leaderboards) within the more
traditional processes and systems
Example: https://badgeville.com/

Games with a Purpose (GWAP) [7,8]
Problem: same of Human
Computation (ask
humans when AI fails)
Solution: hide the task within a game, so
that users are motivated by game
challenges, often remaining unaware of
the hidden purpose, task solution
comes from agreement between players
Example: http://www.gwap.com/

Crowdsourcing
and the
Semantic Web
Can we involve people in Semantic
Web systems? What semantic data
management tasks can we
effectively “outsource” to humans?

Why Crowdsourcing in the Semantic Web?
Knowledge-intensive and/or context-speciﬁc character of Semantic Web tasks:
e.g., conceptual modelling, multi-language resource labelling, content
annotation with ontologies, concept/entity similarity recognition, …
Crowdsourcing can help to engage users and involve them in executing tasks:
e.g., wikis for semantic content authoring, folksonomies to bootstrap formal
ontologies, human computation approaches, …

Semantic Crowdsourcing [9]
Many tasks in Semantic Web data management/curation can exploit Crowdsourcing
Fact level
Schema level
Collection Creation CorrectionValidation Filtering Ranking Linking
Conceptual
modelling
Ontology
population
Quality
assessment
Ontology re-
engineering
Ontology
pruning
Ontology
elicitation
Knowledge
acquisition
Ontology
repair
Knowledge
base update
Data search/
selection Link
generation
Ontology
alignment
Ontology
matching

Focus on Data Linking
Creation of links in the form of RDF triples (subject, predicate, object)
Within the same dataset (i.e. generating new connections between resources of
the same dataset)
Across different datasets (i.e. creating RDF links, as named in the Linked Data world)
Notes:
Generated links can have an associated score σ ∈ 0,1 expressing a sort of “confidence” in the
truth value or in the “relevance” of the triple
In literature, data linking often means finding equivalent resources (similarly to record linkage in
database research), i.e. triples with correspondence/match predicate (e.g. owl:sameAs)  in the
following, data linking is intended in its broader meaning (i.e. links with any predicate)

Subject: 𝑟𝑠 ∈ {Milano cultural heritage assets}
Predicate: foaf:depiction  Goal: create <asset> foaf:depiction <photo>
Object: ? ∈ {photos}
Knowledge acquisition
Citizen science
campaign
http://bit.ly/picmiapp
Level badges as
intrinsic incentives
(gamification)
Contributions with
attribution/recognition

Set of all links: <asset> foaf:depiction <photo>
Goal: assign score 𝜎 to rank links on their “recognisability”/“representativeness”
Link ranking [10]
http://bit.ly/indomilando
Pure GWAP with
hidden purpose
Points, badges,
leaderboard as
intrinsic reward
The score 𝜎 is a
function of 𝑋 𝑁
where 𝑋 is the no. of
successes (=recogni-
tions) and 𝑁 the no.
of trials of the
Bernoulli process
(guess or not guess)
realized by the game
Link ranking is a result
of the “agreement”
between players

Link validation [11]
http://bit.ly/foss4game
Set of links: <land-area> clc:hasLandCover <land-cover>
Automatic classifications: <land-cover-assigned-by-DUSAF> ≠ <land-cover-assigned-by-GL30>
Goal: assign score 𝜎 to each link to discover the “right” land cover class
Pure GWAP with
not-so-hidden purpose
(played by “experts”)
Points, badges,
leaderboard as
intrinsic reward
https://youtu.be/Q0ru1hhDM9Q
A player scores if he/she
guess one of the two
disagreeing classifications
Score 𝜎 of each link is
updated on the basis of
players’ choices
(incremented if link
selected, decremented if
link not selected)
When the score of a link
overcomes a threshold
𝜎 ≥ 𝑡 , the link is
considered “true”
Link validation is a result
of the “agreement”
between players

Caveat 1: Mice and Men (or: keep it simple)
Crowdsourcing workers behave like mice [12]
Mice prefer to use their motor skills (biologically cheap, e.g. pressing a lever to get
food) rather than their cognitive skills (biologically expensive, e.g. going through a
labyrinth to get food)
Workers prefer/are better at simple tasks (e.g. those that can be solved at first
sight) and discard/are worse at more complex tasks (e.g. those that require logics)
Crowdsourcing tasks should be carefully designed
Tasks as simple as possible for the workers to solve
Complex tasks together with other incentives (e.g. variety/novelty)

Suggestion 1: Divide et impera (or: Find-Fix-Verify)
Find-Fix-Verify crowd programming pattern [13]
A long and “expensive” task…
Summarize a text to shorten its total length
…is decomposed in more atomic tasks…
1. find sentences that need to be shortened
2. fix a sentence by shortening it
3. verify which summarized sentence maintains original meaning
…and the complex task is turned into a workflow of simple
tasks, and each step is outsourced to a crowd

Caveat 2: aggregation and disagreement
Are all contributors “created equal”?
Contributions/results on the same task are usually aggregated on different workers
(“wisdom of crowds”, “collective intelligence”)
Update formula for 𝜎 score should weight contributions differently by including
some evaluation of contributors’ reliability (e.g. gold standard)
Is there always a “right answer”? Or is there a “crowd truth”? [14]
Not always true/false, because of human subjectivity, ambiguity and uncertainty
Disagreement across contributors is not necessarily bad, but a sign of: different
opinions, interpretations, contexts, perspectives, …

Suggestion 2: compare and contrast
From “wisdom of crowds” to “wisdom of the crowdsourcing methods”: different
approaches to solve the same problem could be put in parallel to compare results
Which is the best crowdsourcing approach
for a specific use case?
Which is the most suitable crowd?
Is crowdsourcing better/faster/cheaper
than automatic means (e.g. AI)?
Examples:
Detecting quality issues in DBpedia [15]: find-verify strategy
with different crowds (experts and workers) behind the find step
Employing people for ontology alignment [16]: outcomes comparable to results of OAEI systems
input
task
output
solution
Citizen Science
Human Computation
Crowdsourcing
Automatic/machine
computation

Bibliography (1/2)
SSWS 2016 - Bertinoro, 22th July 2016
[1] James Surowiecki. The wisdom of crowds, Anchor, 2005.
[2] Alan Irwin. Citizen science: A study of people, expertise and sustainable development. Psychology
Press, 1995.
[3] Jeﬀ Howe. Crowdsourcing: How the power of the crowd is driving the future of business. Random
House, 2008.
[4] Edith Law and Luis von Ahn. Human computation. Synthesis Lectures on Artiﬁcial Intelligence and
Machine Learning, 5(3):1–121, 2011.
[5] Jane Mc Gonigal. Reality is broken: Why games make us better and how they can change the world.
Penguin, 2011.
[6] Kevin Werbach and Dan Hunter. For The Win: How Game Thinking Can Revolutionize Your Business.
Wharton Digital Press, 2012.
[7] Luis Von Ahn. Games with a purpose. Computer, 39(6):92–94, 2006.
[8] Luis Von Ahn and Laura Dabbish. Designing games with a purpose. Communications of the ACM,
51(8):58–67, 2008.

Bibliography (2/2)
[9] Cristina Sarasua, Elena Simperl, Natasha Noy, Abraham Bernstein, Jan Marco Leimeister.
Crowdsourcing and the Semantic Web: A Research Manifesto, Human Computation 2 (1), 3-17, 2015.
[10] Irene Celino, Andrea Fiano, and Riccardo Fino. Analysis of a Cultural Heritage Game with a Purpose
with an Educational Incentive, ICWE 2016 Proceedings, pp. 422-430, 2016.
[11] Maria Antonia Brovelli, Irene Celino, Monia Molinari, Vijay Charan Venkatachalam. A crowdsourcing-
based game for land cover validation, ESA Living Planet Symposium 2016 Proceedings, 2016.
[12] Panos Ipeirotis. On Mice and Men: The Role of Biology in Crowdsourcing, Keynote talk at Collective
Intelligence, 2012.
[13] M. Bernstein, G. Little, R. Miller, B. Hartmann, M. Ackerman, D. Karger, D. Crowell, K. Panovich.
Soylent: A Word Processor with a Crowd Inside, UIST Proceedings, 2010.
[14] Lora Aroyo, Chris Welty. Truth is a Lie: 7 Myths about Human Annotation, AI Magazine 2014.
[15] Maribel Acosta, Amrapali Zaveri, Elena Simperl, Dimitris Kontokostas, Fabian Flöck, Jens Lehmann.
Detecting Linked Data Quality Issues via Crowdsourcing: A DBpedia Study, Semantic Web Journal, 2016.
[16] Cristina Sarasua, Elena Simperl, Natasha Noy. Crowdmap: Crowdsourcing ontology alignment with
microtasks, ISWC 2012 Proceedings, pp. 525-541, 2012.

Other relevant work (1/2)
Cultural heritage annotation:
C. Wieser, F. Bry, A. Bérard and R. Lagrange. ARTigo: building an artwork search engine with games and
higher-order latent semantic analysis. In First AAAI Conference on Human Computation and
Crowdsourcing, 2013.
Ranking triples for relevance:
J. Hees, T. Roth-Berghofer, R. Biedert, B. Adrian and A. Dengel. BetterRelations: using a game to rate
linked data triples. In Annual Conference on Artificial Intelligence, 2011.
I. Celino, E. Della Valle and R. Gualandris. On the effectiveness of a Mobile Puzzle Game UI to
Crowdsource Linked Data Management tasks. In CrowdUI workshop, 2014.
DBpedia data cleansing:
J. Waitelonis, N. Ludwig, M. Knuth and H. Sack. WhoKnows? Evaluating Linked Data Heuristics with a
Quiz that cleans up DBpedia. Interactive Technology and Smart Education, 8(4), 2011.
Urban Games on spatial knowledge:
I. Celino, S. Contessa, M. Corubolo, D. Dell'Aglio, E. Della Valle, S. Fumeo and T. Krüger. Linking Smart
Cities Datasets with Human Computation – the case of UrbanMatch, In ISWC 2012.
I. Celino, D. Cerizza, S. Contessa, M. Corubolo, D. Dell'Aglio, E. Della Valle and S. Fumeo. Urbanopoly – a
Social and Location-based Game with a Purpose to Crowdsource your Urban Data, Proceedings of
SoHuman 2012, 2012.

Other relevant work (2/2)
Crowdsourcing ontology engineering tasks or SPARQL querying:
N. Noy, J. Mortensen, M. Musen and P. Alexander. Mechanical turk as an ontology engineer?: using
microtasks as a component of an ontology-engineering workﬂow. In WebSci 2013.
G. Wohlgenannt, M. Sabou and F. Hanika. Crowd-based ontology engineering with the uComp Protégé
plugin. Semantic Web, 7(4), 2016.
M. Acosta, E. Simperl, F. Flöck and M.E. Vidal. HARE: A Hybrid SPARQL Engine to Enhance Query Answers
via Crowdsourcing. K-CAP 2015.
Crowdsourced contributions and crowd quality:
R. Kern, H. Thies, C. Zirpins and G. Satzger,. Dynamic and Goal-Based Quality Management for Human-
Based Electronic Services. Int. J. Cooperative Inf. Syst. 21, 1, 2012.
T. Schulze, S. Krug and M. Schader. Workers’ Task Choice in Crowdsourcing and Human Computation
Markets. In ICIS Association for Information Systems, 2012.
D. Difallah, G. Demartini and P. Cudré-Mauroux. Pick-a-crowd: tell me what you like, and I'll tell you what
to do. In WWW 2013.
M. Feldman and A. Bernstein. Cognition-based Task Routing: Towards Highly-Effective Task-Assignments
in Crowdsourcing Settings. In ICIS 2014.
Mixed crowdsourcing approaches:
M. S. Bernstein. Crowd-Powered Systems. KI 27, 1, 69–73, 2013.

Research questions
Irene Celino + Tomi Kauppinen

Warning on group forming
Today is the last day you form groups to investigate research questions
We suggest you to take the chance to work with people you haven’t grouped
together yet… diversity is a resource!
Mini-project groups are not allowed!

Before getting too serious,
let’s seriously play…
You will be asked to present your research task results in 3 minutes (which is tough!)
We want to give a chance to win 2 additional minutes to one of the groups…
To whom? To the group of the winner of this morning tutorial’s quiz game!!
1. Grab your mobile phone (or tablet or laptop)
2. Be sure you are connected to the internet
3. And finally go to:
KAHOOT.IT

Research Question
Why and how to make sense of linked spatio-temporal data?
Can we make machines to be cognitive systems? What is the role of human cognitive
capabilities? How can Linked Data / Semantic Web technologies help?
Possible approaches: crowdsourcing, information visualization, storytelling,
gamification, sensor data fusion, affordances, …
Possible starting point paper: K. Janowicz, The role of space and time for knowledge
organization on the Semantic Web. Semantic Web 1.1, 2 (2010): 25-32.

What you have to do
Task: devise your own approach
Provide a convincing future scenario (i.e. design fiction) as an example
Use your creativity and freedom!
Come up with a proposal including motivation (why), approach (how) and expected
results (what); bonus point if you add ideas about evaluation
Put your group results in the shared Etherpad (no PowerPoint!):
http://public.etherpad-mozilla.org/p/cognition-day

Tutorial Cognition - Irene

More Related Content

What's hot (20)

Viewers also liked (20)

Similar to Tutorial Cognition - Irene (20)

Recently uploaded (20)

Tutorial Cognition - Irene