Food and Culture CSS @GESIS Claudia Wagner GESIS & University of Koblenz 6nd Nov 2014, Yahoo Labs, Spain
Food and CultureCSS @GESIS
Claudia Wagner
GESIS & University of Koblenz6nd Nov 2014, Yahoo Labs, Spain
18.11.2014 Claudia Wagner 2
Survey Design andMethodology
Computer Science and Information
Science
Research and Services at GESIS
Raise the standards of surveys at all phases of the survey life cycle
Gender studies, Political science (e.g., GLES), Values and Attitudesresearch (e.g. ALLBUS), ...
Knowledge Discovery, Information Retrieval, Information Extraction, …
Social Science Research
18.11.2014 Claudia Wagner 3
ComputationalSocial Science
CSS Agenda @GESIS
Support traditional Social Science research with computational methods and tools
Develop new instruments to tap into the potential of found data and crowds building a telescope for the Social Sciences
Online impacts offline! Build new algorithms and tools to shift the current configurations of societies towards better futures.
18.11.2014 Claudia Wagner 4
PAST
PRESENT
FUTURE
18.11.2014 Claudia Wagner 5
Food
Data
• Ichkoche.at~ 470k Unique Users
~1 Mil. Page Impressions per week
• Kochbar.de– 2,27 Mil. Unique User in July 2014
– 1.29 million Visits (12.1 Mio. PI) in December 2008
• Chefkoch.de – 11,05 Mil. Unique User in July 2014
– 28 Mio. Visits and 242 Mio. PI in December 2010
6Sources: http://www.agof.de/aktuelle-studie-internet/#aktuellestudiehttp://www.ichkoche.at/data/repository/Keyaccount/ichkoche-oewaplus-q4-2012.pdf
Recipe Popularities
0
10000
20000
30000
40000
50000
18.11.2014 Claudia Wagner 7
Ingredient Popularities
18.11.2014 Claudia Wagner 8
0
20000
40000
60000
80000
100000
120000
18.11.2014 Claudia Wagner 9
Temporal Stability
10
Meat
Carbohydrates
Fish
Vegetable
Alcohol
Normalized Access Volume per Weekday
)( t
t
XZ
Ichkoche.at
18.11.2014 Claudia Wagner 11
kochbar.de
18.11.2014 Claudia Wagner 12
ichkoche.at
18.11.2014 Claudia Wagner 13
kochbar.de
18.11.2014 Claudia Wagner 14
15
Meat
Carbohydrates
Fish
Vegetable
Alcohol
Change Rateper Weekday
N
j jj
iit
tFtF
tFtFR
1 1
1
)()(
))()((
Most Popular Recipes
• Berlin:
18.11.2014 Claudia Wagner 16
• Frankfurt: • Vienna:• Kiel:
City Similarities
18.11.2014 Claudia Wagner 17
Bundesarchiv Bild 173-1282, Berlin, Brandenburger Tor, Wasserwerfer 18
Regional Similarities
18.11.2014 Claudia Wagner 19
Regional Similarities
18.11.2014 20
West
East
Berlin
EastWest
18.11.2014 Claudia Wagner 21
Culture
Wikipedia27 language communities
31 cuisines
22
Cultural Relations
18.11.2014 Claudia Wagner 23
Understanding
Similarity
Affinity
Cultural Similarity
sim(𝐴, 𝐵) =|𝐴 ∩ 𝐵|
|𝐴 ∪ 𝐵|Jaccard
similarity
German cuisine
Italian cuisine
Sauerkraut
Riesling Pasta
Sousage
Pizza
Parmigiano
sim( , ) =1
82418.11.2014 Claudia Wagner
Tortano
Wheat Beer
Cultural Similarity between
Neighbors
18.11.2014 Claudia Wagner 25
Cultural Understanding
Understanding the Italian food culture
Wikipedia edition
Used concepts
“Native” definition
2 / 5 0 / 6Understanding
2618.11.2014
Cultural Understanding
2718.11.2014
What may explain Cultural
Understanding?
• Create for each country a list of countries ranked by where most of its immigrants come from
• Create for each country a list of countries ranked by how similar their values and beliefs are according to ESS
Pair ρ (p-value)
wiki – ess 0.18 (0.00019)
wiki – migration 0.36 (1.74e-22)
28
Germany
Claudia Wagner18.11.2014
Cultural Affinity
• View statistics of cuisine pages in different language editions
• How much more attention than we would expect does language community A pay to the culture of community B?
2918.11.2014
Cross-cultural
affinities
18.11.2014 30
But what
explains them?
GERMANY
de/Croatian (+0.0173)de/Serbian (+0.0114)de/Polish (+0.0051)de/Dutch (+0.0037)
TURKEY
tr/German (+0.1464)tr/French (+0.0850)tr/Italian (+0.0114)
ρ=0.25
18.11.2014 Claudia Wagner 31
What drives
cross-cultural attention?
es
it
dees
it
de
Popularity-Affinity ModelPopularity Model
What drives
cross-cultural attention?
18.11.2014 32
Popularity Model Popularity-Affinity Model
Self-Focus & Regional Bias
33Claudia Wagner18.11.2014
Summary
• Affinities between language communities are present in Wikipedia and drive the attention process
• Cultural understanding can to some extent be explained by migration
• Cultural similarities inferred from Wikipedia are pretty plausible crowdflower
• Relation between similarity, understanding and affinities?– Understanding and affinity: -0.35
– Similarity and affinity: 0.27
– Similarity and understanding: 0.19
18.11.2014 Claudia Wagner 34