1/20
Digitally Empowered Education in SSH
Kristoffer L [email protected]
knielbo.github.io
Dept. of History & SDU eScience CenterUniversity of Southern Denmark
2/20www.skynettoday.com/content/news/facebook-chatbot-language/
3/20
I’d like the books and the hats
I will take the books and hats
I really need the books and at least oneother object
Ok, you can have one book and one ball
If I can have all the books, I can leave youthe rest
Deal
You can have the ball if I can haveeverything else
No can’t do that the ball is not going togive me anything
I need the hats and you can have the rest
Deal
Great! Thank you!
https://github.com/facebookresearch/end-to-end-negotiator
4/20
i can i i everything else . . . . . . . . . . . . . .
balls have zero to me to me to me to me to me to me to me to me to
you i everything else . . . . . . . . . . . . . .
balls have a ball to me to me to me to me to me to me to me
i i can i i i everything else . . . . . . . . . . . . . .
balls have a ball to me to me to me to me to me to me to me
i . . . . . . . . . . . . . . . . . . .
balls have zero to me to me to me to me to me to me to me to me to
you i i i i i everything else . . . . . . . . . . . . . .
balls have 0 to me to me to me to me to me to me to me to me to
you i i i everything else . . . . . . . . . . . . . .
balls have zero to me to me to me to me to me to me to me to me to
5/20
compromise0: IPRON willAUX takeVERB theDET booksNOUN andCONJ hatsNOUN
compromise1: YouPRON canAUX haveVERB theDET ballNOUN ifSCONJ IPRON canAUX
haveVERB everythingNOUN elseADJ
stubborn: IPRON getVERB allDET theDET ballsNOUN ?PUNCT
singularity: ballsNOUN haveVERB zeroADJ toADP mePRON toADP mePRON toADP mePRON
toADP mePRON toADP mePRON toADP mePRON toADP mePRON toADP mePRON toPART
compromise0 compromise1 stubborn singularityH(X ) 2.53 (1.16) 2.3 (1.35) 2.59 (0.84) 1.62 (0.51)TTR 0.92 (0.09) 0.94 (0.07) 0.96 (0.09) 0.5 (0.27)
6/20
7/20
8/20
9/20
Core observations
– impossible without digitization– cultural data require culture analytics– qual-quant distinction is no longer valid– scaling requires automation– there is no way around basic programming
humanities research and education need a define our human-centered informatics
10/20
– the data deluge is transforming knowledge discovery and understanding in everydomain of human inquiry
– knowledge discovery depends critically on advanced computing capabilities
a large part of these data are soft and unstructured
– to get additional value from these data, faculties of humanities must becomecomputationally and data literate
11/20
– number of research publications alone makes computational literacy a necessity forthe humanities scholar
– publications related to Gospel of Marc (KJV) > 50K, ∼ 16,500 words in 16 chp. on 11 p.
– plus a massive increase in digitized cultural heritage databases (libraries, archieves,museums)
12/20
13/20
14/20
Computational Literacy|Programming & Analytics
– every knowledge intensive organization has to break the learning curve, but certainsectors are more challenged
– co-develop with the eScience Center and other resources @ SDU
– promote a common language and import best practice from software development
15/20
Computational Literacy|Programming & Analytics
GUI → CLI
- novice-friendly visual approach to computer interaction w. a fast learning curve ERROR
- expert-friendly text-based approach to computer interaction w. ++freedom VALID
- CONFLICT break the learning curve through training intensive, non-intuitive, andspecialized tools
- in research, we try to solve this conflict by establishing small, semi-autonomouseScience units that intervene in (humanities) research
16/20
Literary Studies|Sentiment Analysis
0 1000 2000 3000 4000 5000 6000−5
0
5
10
Time
Sentim
ent
Madame Bovary
(a) Original t = L/400 t = L/10
0 1000 2000 3000 4000 5000 6000−1
−0.5
0
0.5
1
Time
Sentim
ent
(b)
filtered (t = L/10)
filtered (t = 3L/8)
Figure: sentiment analysis and adaptive filteringreconstructs narrative vectors that reflect thereader experience. Particular fractalscaling-range, 0.6 < H ≤ 0.8, indicates literaryoptimality.
0 2 4 6 8 10 12−2
0
2
4
6
Hs=0.57
Hl=0.74
log2w
log
2F
(w)
17/20
History|Predictive Causality & Slow Decay
– historians and media researchers theorize about the causal dependencies betweenpublic discourse and advertisement
– time series analysis of keyword frequencies (from seedlists) indicated that for somecategories ‘ads shape society’, while other categories merely ‘reflect’
– advertisements show a faster decay (on-off intermittant behavior) than publicdiscourse (long-range dependencies)
Wevers, M., Nielbo, K. L., & Gao, J. (in review). Tracking the Consumption Junction: Temporal Dependencies in Dutch NewspaperArticles and Advertisements.
18/20
8 10 12
2
3
4
5
log10
GDP
log
10 n
o.
of
eve
nts
r = 0.81
(a) 1985
8 10 12
1
2
3
4
5
log10
GDP
log
10 n
o.
of
eve
nts
r = 0.68
(b) 1995
9 10 11 12 13
2
3
4
5
log10
GDP
log
10 n
o.
of
eve
nts
r = 0.69
(c) 2005
9 10 11 12 13
4
5
6
7
log10
GDP
log
10 n
o.
of
eve
nts
r = 0.8
(d) 2015
1980 1985 1990 1995 2000 2005 2010 20150.6
0.7
0.8
0.9
year
Pe
ars
on
co
rre
latio
n r (e)
15 20 25 30 35 40 4525
30
35
40USA
GBRLVA
ESPGRCPRT
AUSNZL
ITACAN
IRL
POLCHEFRA DEU
HUN
LUX SWEAUTNLD
SVKBELFIN
DNKNOR
r(Total)= 0.616
r(Gini≥26.5%)= 0.694
Domestic events(%)
Gin
i co
eff
icie
nt(
%)
1980 1985 1990 1995 2000 2005 2010 201515
20
25
30
35
40
45
Time
Dom
estic e
vents
(%)
USA IRL GBR NLD ITA
DEU DNK FIN FRA SWE Median
Figure: Event counts in the GDELT databasereflect economic and political dynamics
Gao J., Ma M., Liu B., Nielbo K.L., Roepstorff A., Tangherlini T., Roychowdhury V. (in review) Brexit and Trump Presidency: werethey black swan events or inevitable?
19/20
EMOTION|Grundtvig
– early phase: negative affective tone– late phase: positive affective tone– inverse relation → state incongruent writer
– emotional state Granger-causes creative state → dostoyevskian trope
20/20
THANK YOU
knielbo.github.io
& credits toMax R. Echardt and Katrine F. Baunvig, datakube, University of Southern Denmark, DK
Jianbo Gao and Bin Liu, Institute of Complexity Science and Big Data, Guangxi University, CHNMelvin Wevers, DH Lab, KNAW Humanities Cluster, NL
Culture Analytics @ Institute of Pure and Applied Mathematics, UCLA, US
Top Related