In [1]:
library(data.table)
In [2]:
## Using a table of article assessments and views, build tables
## (matrices) that shows the number of dissonant articles per
## assessment category based on sorting by popularity.
##
## The underlying assumption is that in an ideal system with a limited
## and fixed amount of resources (in other words, popularity and high quality
## artefacts does not increase the amount of resources in the system),
## popularity ranking and assessment class follow a 1-to-1 relationship.
## We can therefore sort by popularity and group articles that way
## because work will be prioritised by popularity.
## DATA ASSUMPTION: views_with_redirects from resolve-redirects.R
## is loaded into memory.
## 3: build a 2x2 matrix of assessment classes and popularity classes
##
## Assessment classes in ascending order of quality.
In [3]:
assessment_classes = c('E', 'D', 'C', 'B', 'A');
In [4]:
quality_prediction_and_page_views <- read.table("../../results/sql_queries/entity_views_and_aggregated_revisions/entity_views_and_aggregated_revisions_and_quality_scoring_20150201.tsv", header=FALSE, sep="\t")
In [5]:
quality_prediction_and_page_views <- data.table(quality_prediction_and_page_views)
In [6]:
colnames(quality_prediction_and_page_views) <- c('entity_id','number_of_revisions', 'page_views', 'prediction')
In [7]:
summary(quality_prediction_and_page_views)
entity_id number_of_revisions page_views prediction
Q1 : 1 Min. : 1.00 Min. :0.000e+00 A: 87
Q100 : 1 1st Qu.: 8.00 1st Qu.:3.900e+01 B: 40183
Q1000 : 1 Median : 16.00 Median :2.850e+02 C: 1708501
Q10000 : 1 Mean : 21.65 Mean :3.237e+04 D: 3149707
Q100000 : 1 3rd Qu.: 28.00 3rd Qu.:1.652e+03 E:11037868
Q1000000: 1 Max. :21863.00 Max. :1.253e+10
(Other) :15936340
In [8]:
## 0: calculate number of articles in each assessment class
n_per_class = quality_prediction_and_page_views[, list(narticles=sum(.N)), by='prediction']
In [9]:
setkey(n_per_class, prediction);
## NOTE: setkey allows us to do n_per_class['GA']$narticles to get counts
In [10]:
## 1: order articles by popularity
articles_by_pop = quality_prediction_and_page_views[order(quality_prediction_and_page_views$page_views)][,list(entity_id, prediction, page_views)];
In [11]:
## 2: assign popularity assessment class based on rank
## (buckets based on number of articles in each class)
articles_by_pop[, pop_class := ''];
articles_by_pop[, seqNum := seq_len(nrow(articles_by_pop))];
entity_id prediction page_views pop_class
Q10040378 E 0
Q10069140 E 0
Q10081695 E 0
Q10092002 E 0
Q10111267 E 0
Q10149726 E 0
Q10180230 E 0
Q10185035 E 0
Q10205202 E 0
Q10252966 E 0
Q10444494 D 0
Q10624171 D 0
Q10704108 D 0
Q10750354 E 0
Q10766855 E 0
Q10827611 E 0
Q11093044 E 0
Q11934537 E 0
Q12133466 E 0
Q12264503 E 0
Q12267516 E 0
Q12304084 E 0
Q12443525 E 0
Q12543904 E 0
Q12890205 E 0
Q12891524 E 0
Q12918202 E 0
Q13005653 E 0
Q13073896 E 0
Q13163823 E 0
⋮ ⋮ ⋮ ⋮
Q1048694 C 2048095025
Q31165 C 2048330818
Q40629 C 2049755644
Q105584 C 2049926923
Q4584301 D 2052339927
Q565 C 2052996261
Q1868372 E 2056080224
Q209330 C 2060928966
Q14005 D 2063120071
Q918 C 2063217449
Q150248 C 2068796814
Q866 C 2079749157
Q477675 C 2080785713
Q1967876 C 2084215818
Q750403 C 2084693498
Q355 C 2093900731
Q623578 C 2097991400
Q17299517 D 2105487660
Q33999 C 2108672678
Q2494649 C 2114531894
Q2597810 C 2128920607
Q193563 C 2130725560
Q423048 C 2136131564
Q37312 C 2142913121
Q54919 C 2148531382
Q36578 C 2229315598
Q30 A 2277746226
Q6581097 C 3273952711
Q5 A 5668008721
Q5296 C 12530369761
entity_id prediction page_views pop_class seqNum
Q10040378 E 0 1
Q10069140 E 0 2
Q10081695 E 0 3
Q10092002 E 0 4
Q10111267 E 0 5
Q10149726 E 0 6
Q10180230 E 0 7
Q10185035 E 0 8
Q10205202 E 0 9
Q10252966 E 0 10
Q10444494 D 0 11
Q10624171 D 0 12
Q10704108 D 0 13
Q10750354 E 0 14
Q10766855 E 0 15
Q10827611 E 0 16
Q11093044 E 0 17
Q11934537 E 0 18
Q12133466 E 0 19
Q12264503 E 0 20
Q12267516 E 0 21
Q12304084 E 0 22
Q12443525 E 0 23
Q12543904 E 0 24
Q12890205 E 0 25
Q12891524 E 0 26
Q12918202 E 0 27
Q13005653 E 0 28
Q13073896 E 0 29
Q13163823 E 0 30
⋮ ⋮ ⋮ ⋮ ⋮
Q1048694 C 2048095025 15936317
Q31165 C 2048330818 15936318
Q40629 C 2049755644 15936319
Q105584 C 2049926923 15936320
Q4584301 D 2052339927 15936321
Q565 C 2052996261 15936322
Q1868372 E 2056080224 15936323
Q209330 C 2060928966 15936324
Q14005 D 2063120071 15936325
Q918 C 2063217449 15936326
Q150248 C 2068796814 15936327
Q866 C 2079749157 15936328
Q477675 C 2080785713 15936329
Q1967876 C 2084215818 15936330
Q750403 C 2084693498 15936331
Q355 C 2093900731 15936332
Q623578 C 2097991400 15936333
Q17299517 D 2105487660 15936334
Q33999 C 2108672678 15936335
Q2494649 C 2114531894 15936336
Q2597810 C 2128920607 15936337
Q193563 C 2130725560 15936338
Q423048 C 2136131564 15936339
Q37312 C 2142913121 15936340
Q54919 C 2148531382 15936341
Q36578 C 2229315598 15936342
Q30 A 2277746226 15936343
Q6581097 C 3273952711 15936344
Q5 A 5668008721 15936345
Q5296 C 12530369761 15936346
In [12]:
assign_pop_class = function(dataset, classes, class_n) {
## Based on the per-class number of articles in class_n
## assign popularity based on classes to dataset.
prev_idx = 0;
for(rating in classes) {
start_idx = prev_idx + 1;
end_idx = start_idx + class_n[prediction == rating]$narticles;
print(paste('start_idx =', start_idx, ', end_idx = ', end_idx));
dataset[seqNum >= start_idx & seqNum <= end_idx, pop_class := rating];
prev_idx = end_idx -1;
}
dataset;
}
In [13]:
articles_by_pop = assign_pop_class(articles_by_pop,
assessment_classes, n_per_class);
[1] "start_idx = 1 , end_idx = 11037869"
[1] "start_idx = 11037869 , end_idx = 14187576"
[1] "start_idx = 14187576 , end_idx = 15896077"
[1] "start_idx = 15896077 , end_idx = 15936260"
[1] "start_idx = 15936260 , end_idx = 15936347"
In [14]:
create_dissonance_matrix = function(articledata, classes) {
d_mtrx = matrix(0, nrow=length(classes), ncol=length(classes));
rownames(d_mtrx) = classes;
colnames(d_mtrx) = classes;
for(real_rating in classes) {
for(pop_rating in classes) {
d_mtrx[real_rating, pop_rating] = length(articledata[prediction == real_rating & pop_class == pop_rating]$entity_id);
}
}
d_mtrx;
}
In [15]:
## Based on direct hits to articles:
create_dissonance_matrix(articles_by_pop, assessment_classes)
E D C B A
E 7997926 2120351 913558 6021 12
D 2331192 524761 288263 5472 19
C 699326 493758 488573 26790 54
B 9424 10835 18100 1824 0
A 0 2 7 76 2
In [16]:
dissonance_matrix = create_dissonance_matrix(articles_by_pop,
assessment_classes);
In [17]:
# Total misaligned entities
(dissonance_matrix[1,1]+dissonance_matrix[2,2]+dissonance_matrix[3,3]+dissonance_matrix[4,4]+dissonance_matrix[5,5])/sum(dissonance_matrix[,])
0.565567916258846
In [18]:
# A class quality and A class views over A class quality
dissonance_matrix[5,5]/sum(dissonance_matrix[5,])
0.0229885057471264
In [19]:
# A class quality and E and D class views over A class quality
(dissonance_matrix[5,1]+dissonance_matrix[5,2])/sum(dissonance_matrix[5,])
0.0229885057471264
In [20]:
# A class quality and < A class views
(dissonance_matrix[5,1]+dissonance_matrix[5,2]+dissonance_matrix[5,3]+dissonance_matrix[5,4])/sum(dissonance_matrix[5,])
0.977011494252874
In [21]:
# < A class quality and A class views
(dissonance_matrix[1,5]+dissonance_matrix[2,5]+dissonance_matrix[3,5]+dissonance_matrix[4,5])/sum(dissonance_matrix[,5])
0.977011494252874
In [22]:
prediction_e_pop_class_a <- merge(articles_by_pop[prediction == 'E' & pop_class == 'A'],quality_prediction_and_page_views, by='entity_id')[, c("entity_id","page_views.x", "number_of_revisions")]
In [23]:
head(prediction_e_pop_class_a)
entity_id page_views.x number_of_revisions
Q1002972 2045659200 30
Q156376 2046132338 83
Q1868372 2056080224 45
Q2638147 2045739408 25
Q372827 2045652543 36
Q4043051 2045595548 32
In [24]:
## Q: why do I get _two_ pageid columns? Solution is to do the selection
## on the joined table, not as a select _in_ the join.
## Dissonance matrix proportions by row (..., 1) and column (..., 2)
## rounded to 1 decimal places.
In [25]:
round(100*prop.table(dissonance_matrix, 1), 1);
E D C B A
E 72.5 19.2 8.3 0.1 0.0
D 74.0 16.7 9.2 0.2 0.0
C 40.9 28.9 28.6 1.6 0.0
B 23.5 27.0 45.0 4.5 0.0
A 0.0 2.3 8.0 87.4 2.3
In [26]:
round(100*prop.table(dissonance_matrix, 2), 1);
E D C B A
E 72.5 67.3 53.5 15.0 13.8
D 21.1 16.7 16.9 13.6 21.8
C 6.3 15.7 28.6 66.7 62.1
B 0.1 0.3 1.1 4.5 0.0
A 0.0 0.0 0.0 0.2 2.3
In [27]:
## Let's write the stubs out to a file
write.table(merge(articles_by_pop[(prediction == 'E' | prediction == 'D' | prediction == 'C' | prediction == 'B') & pop_class == 'A'], quality_prediction_and_page_views, by='entity_id')[, c("entity_id","pop_class", "prediction.x")],
'../../results/entity_categorization/201502_a_class_views_less_than_a_quality.tsv', row.names=FALSE, col.names=FALSE, quote=FALSE, sep='\t');
merge(articles_by_pop[(prediction == 'E' | prediction == 'D' | prediction == 'C' | prediction == 'B') & pop_class == 'A'], quality_prediction_and_page_views, by='entity_id')[, c("entity_id","pop_class", "prediction.x")]
entity_id pop_class prediction.x
Q1002972 A E
Q103204 A C
Q1048694 A C
Q105584 A C
Q1063819 A C
Q10726338 A D
Q1123836 A D
Q1133733 A D
Q116933 A C
Q11789729 A D
Q1200925 A D
Q1373513 A C
Q14005 A D
Q150248 A C
Q1526131 A C
Q156376 A E
Q16744133 A D
Q17117201 A D
Q171186 A C
Q17144398 A D
Q17195318 A D
Q17299517 A D
Q17299580 A D
Q183718 A C
Q1868372 A E
Q193563 A C
Q1967876 A C
Q209330 A C
Q213678 A C
Q219523 A D
⋮ ⋮ ⋮
Q4299858 A E
Q4380129 A E
Q4442644 A E
Q4584301 A D
Q477675 A C
Q501851 A C
Q51044 A C
Q523660 A D
Q5296 A C
Q54919 A C
Q565 A C
Q568769 A C
Q618340 A C
Q620946 A C
Q622012 A D
Q623578 A C
Q63056 A C
Q631375 A C
Q649227 A C
Q6581097 A C
Q6883832 A E
Q7315186 A D
Q732353 A C
Q750403 A C
Q809830 A C
Q829984 A C
Q866 A C
Q918 A C
Q9384291 A D
Q953058 A C
In [28]:
write.table(merge(articles_by_pop[prediction == 'A' & (pop_class == 'B' | pop_class == 'C' | pop_class == 'D' | pop_class == 'E')], quality_prediction_and_page_views, by='entity_id')[, c("entity_id","pop_class", "prediction.x")],
'../../results/entity_categorization/201502_a_class_quality_less_than_a_views.tsv', row.names=FALSE, col.names=FALSE, quote=FALSE, sep='\t');
In [29]:
write.table(merge(articles_by_pop[(prediction == 'A' & pop_class == 'A') | (prediction == 'B' & pop_class == 'B') | (prediction == 'C' & pop_class == 'C') | (prediction == 'D' & pop_class == 'D') | (prediction == 'E' & pop_class == 'E')], quality_prediction_and_page_views, by='entity_id')[, c("entity_id","pop_class", "prediction.x")],
'../../results/entity_categorization/201502_aligned.tsv', row.names=FALSE, col.names=FALSE, quote=FALSE, sep='\t');
In [30]:
write.table(merge(articles_by_pop[(prediction == 'A' & pop_class != 'A') | (prediction == 'B' & pop_class != 'B') | (prediction == 'C' & pop_class != 'C') | (prediction == 'D' & pop_class != 'D') | (prediction == 'E' & pop_class != 'E')], quality_prediction_and_page_views, by='entity_id')[, c("entity_id","pop_class", "prediction.x")],
'../../results/entity_categorization/201502_misaligned.tsv', row.names=FALSE, col.names=FALSE, quote=FALSE, sep='\t');
In [29]:
## Various ways of measuring dissonance.
## DATA ASSUMPTION: articles_by_pop from build-dissonance-table.R
## is loaded into memory.
## None/Moderate/High measure of dissonance
In [30]:
articles_by_pop[, pop_class := ordered(pop_class, assessment_classes)];
entity_id prediction page_views pop_class seqNum
Q10040378 E 0 E 1
Q10069140 E 0 E 2
Q10081695 E 0 E 3
Q10092002 E 0 E 4
Q10111267 E 0 E 5
Q10149726 E 0 E 6
Q10180230 E 0 E 7
Q10185035 E 0 E 8
Q10205202 E 0 E 9
Q10252966 E 0 E 10
Q10444494 D 0 E 11
Q10624171 D 0 E 12
Q10704108 D 0 E 13
Q10750354 E 0 E 14
Q10766855 E 0 E 15
Q10827611 E 0 E 16
Q11093044 E 0 E 17
Q11934537 E 0 E 18
Q12133466 E 0 E 19
Q12264503 E 0 E 20
Q12267516 E 0 E 21
Q12304084 E 0 E 22
Q12443525 E 0 E 23
Q12543904 E 0 E 24
Q12890205 E 0 E 25
Q12891524 E 0 E 26
Q12918202 E 0 E 27
Q13005653 E 0 E 28
Q13073896 E 0 E 29
Q13163823 E 0 E 30
⋮ ⋮ ⋮ ⋮ ⋮
Q1048694 C 2048095025 A 15936317
Q31165 C 2048330818 A 15936318
Q40629 C 2049755644 A 15936319
Q105584 C 2049926923 A 15936320
Q4584301 D 2052339927 A 15936321
Q565 C 2052996261 A 15936322
Q1868372 E 2056080224 A 15936323
Q209330 C 2060928966 A 15936324
Q14005 D 2063120071 A 15936325
Q918 C 2063217449 A 15936326
Q150248 C 2068796814 A 15936327
Q866 C 2079749157 A 15936328
Q477675 C 2080785713 A 15936329
Q1967876 C 2084215818 A 15936330
Q750403 C 2084693498 A 15936331
Q355 C 2093900731 A 15936332
Q623578 C 2097991400 A 15936333
Q17299517 D 2105487660 A 15936334
Q33999 C 2108672678 A 15936335
Q2494649 C 2114531894 A 15936336
Q2597810 C 2128920607 A 15936337
Q193563 C 2130725560 A 15936338
Q423048 C 2136131564 A 15936339
Q37312 C 2142913121 A 15936340
Q54919 C 2148531382 A 15936341
Q36578 C 2229315598 A 15936342
Q30 A 2277746226 A 15936343
Q6581097 C 3273952711 A 15936344
Q5 A 5668008721 A 15936345
Q5296 C 12530369761 A 15936346
In [31]:
dissonance_metric = c('High negative', 'Moderate negative',
'None', 'Moderate positive', 'High positive');
In [32]:
articles_by_pop[, dissonance := factor(NA, dissonance_metric)];
entity_id prediction page_views pop_class seqNum dissonance
Q10040378 E 0 E 1 NA
Q10069140 E 0 E 2 NA
Q10081695 E 0 E 3 NA
Q10092002 E 0 E 4 NA
Q10111267 E 0 E 5 NA
Q10149726 E 0 E 6 NA
Q10180230 E 0 E 7 NA
Q10185035 E 0 E 8 NA
Q10205202 E 0 E 9 NA
Q10252966 E 0 E 10 NA
Q10444494 D 0 E 11 NA
Q10624171 D 0 E 12 NA
Q10704108 D 0 E 13 NA
Q10750354 E 0 E 14 NA
Q10766855 E 0 E 15 NA
Q10827611 E 0 E 16 NA
Q11093044 E 0 E 17 NA
Q11934537 E 0 E 18 NA
Q12133466 E 0 E 19 NA
Q12264503 E 0 E 20 NA
Q12267516 E 0 E 21 NA
Q12304084 E 0 E 22 NA
Q12443525 E 0 E 23 NA
Q12543904 E 0 E 24 NA
Q12890205 E 0 E 25 NA
Q12891524 E 0 E 26 NA
Q12918202 E 0 E 27 NA
Q13005653 E 0 E 28 NA
Q13073896 E 0 E 29 NA
Q13163823 E 0 E 30 NA
⋮ ⋮ ⋮ ⋮ ⋮ ⋮
Q1048694 C 2048095025 A 15936317 NA
Q31165 C 2048330818 A 15936318 NA
Q40629 C 2049755644 A 15936319 NA
Q105584 C 2049926923 A 15936320 NA
Q4584301 D 2052339927 A 15936321 NA
Q565 C 2052996261 A 15936322 NA
Q1868372 E 2056080224 A 15936323 NA
Q209330 C 2060928966 A 15936324 NA
Q14005 D 2063120071 A 15936325 NA
Q918 C 2063217449 A 15936326 NA
Q150248 C 2068796814 A 15936327 NA
Q866 C 2079749157 A 15936328 NA
Q477675 C 2080785713 A 15936329 NA
Q1967876 C 2084215818 A 15936330 NA
Q750403 C 2084693498 A 15936331 NA
Q355 C 2093900731 A 15936332 NA
Q623578 C 2097991400 A 15936333 NA
Q17299517 D 2105487660 A 15936334 NA
Q33999 C 2108672678 A 15936335 NA
Q2494649 C 2114531894 A 15936336 NA
Q2597810 C 2128920607 A 15936337 NA
Q193563 C 2130725560 A 15936338 NA
Q423048 C 2136131564 A 15936339 NA
Q37312 C 2142913121 A 15936340 NA
Q54919 C 2148531382 A 15936341 NA
Q36578 C 2229315598 A 15936342 NA
Q30 A 2277746226 A 15936343 NA
Q6581097 C 3273952711 A 15936344 NA
Q5 A 5668008721 A 15936345 NA
Q5296 C 12530369761 A 15936346 NA
In [33]:
## NOTE: because pop_class is of class ordered, we can use
## expressions like "pop_class < 'C'" as expected
In [34]:
## A: None if A, Moderate if A, High elsewhere
articles_by_pop[prediction == 'A' & pop_class <= 'C',
dissonance := 'High negative'];
articles_by_pop[prediction == 'A' & pop_class == 'B',
dissonance := 'Moderate negative'];
articles_by_pop[prediction == 'A' & pop_class == 'A',
dissonance := 'None'];
entity_id prediction page_views pop_class seqNum dissonance
Q10040378 E 0 E 1 NA
Q10069140 E 0 E 2 NA
Q10081695 E 0 E 3 NA
Q10092002 E 0 E 4 NA
Q10111267 E 0 E 5 NA
Q10149726 E 0 E 6 NA
Q10180230 E 0 E 7 NA
Q10185035 E 0 E 8 NA
Q10205202 E 0 E 9 NA
Q10252966 E 0 E 10 NA
Q10444494 D 0 E 11 NA
Q10624171 D 0 E 12 NA
Q10704108 D 0 E 13 NA
Q10750354 E 0 E 14 NA
Q10766855 E 0 E 15 NA
Q10827611 E 0 E 16 NA
Q11093044 E 0 E 17 NA
Q11934537 E 0 E 18 NA
Q12133466 E 0 E 19 NA
Q12264503 E 0 E 20 NA
Q12267516 E 0 E 21 NA
Q12304084 E 0 E 22 NA
Q12443525 E 0 E 23 NA
Q12543904 E 0 E 24 NA
Q12890205 E 0 E 25 NA
Q12891524 E 0 E 26 NA
Q12918202 E 0 E 27 NA
Q13005653 E 0 E 28 NA
Q13073896 E 0 E 29 NA
Q13163823 E 0 E 30 NA
⋮ ⋮ ⋮ ⋮ ⋮ ⋮
Q1048694 C 2048095025 A 15936317 NA
Q31165 C 2048330818 A 15936318 NA
Q40629 C 2049755644 A 15936319 NA
Q105584 C 2049926923 A 15936320 NA
Q4584301 D 2052339927 A 15936321 NA
Q565 C 2052996261 A 15936322 NA
Q1868372 E 2056080224 A 15936323 NA
Q209330 C 2060928966 A 15936324 NA
Q14005 D 2063120071 A 15936325 NA
Q918 C 2063217449 A 15936326 NA
Q150248 C 2068796814 A 15936327 NA
Q866 C 2079749157 A 15936328 NA
Q477675 C 2080785713 A 15936329 NA
Q1967876 C 2084215818 A 15936330 NA
Q750403 C 2084693498 A 15936331 NA
Q355 C 2093900731 A 15936332 NA
Q623578 C 2097991400 A 15936333 NA
Q17299517 D 2105487660 A 15936334 NA
Q33999 C 2108672678 A 15936335 NA
Q2494649 C 2114531894 A 15936336 NA
Q2597810 C 2128920607 A 15936337 NA
Q193563 C 2130725560 A 15936338 NA
Q423048 C 2136131564 A 15936339 NA
Q37312 C 2142913121 A 15936340 NA
Q54919 C 2148531382 A 15936341 NA
Q36578 C 2229315598 A 15936342 NA
Q30 A 2277746226 A 15936343 NA
Q6581097 C 3273952711 A 15936344 NA
Q5 A 5668008721 A 15936345 NA
Q5296 C 12530369761 A 15936346 NA
entity_id prediction page_views pop_class seqNum dissonance
Q10040378 E 0 E 1 NA
Q10069140 E 0 E 2 NA
Q10081695 E 0 E 3 NA
Q10092002 E 0 E 4 NA
Q10111267 E 0 E 5 NA
Q10149726 E 0 E 6 NA
Q10180230 E 0 E 7 NA
Q10185035 E 0 E 8 NA
Q10205202 E 0 E 9 NA
Q10252966 E 0 E 10 NA
Q10444494 D 0 E 11 NA
Q10624171 D 0 E 12 NA
Q10704108 D 0 E 13 NA
Q10750354 E 0 E 14 NA
Q10766855 E 0 E 15 NA
Q10827611 E 0 E 16 NA
Q11093044 E 0 E 17 NA
Q11934537 E 0 E 18 NA
Q12133466 E 0 E 19 NA
Q12264503 E 0 E 20 NA
Q12267516 E 0 E 21 NA
Q12304084 E 0 E 22 NA
Q12443525 E 0 E 23 NA
Q12543904 E 0 E 24 NA
Q12890205 E 0 E 25 NA
Q12891524 E 0 E 26 NA
Q12918202 E 0 E 27 NA
Q13005653 E 0 E 28 NA
Q13073896 E 0 E 29 NA
Q13163823 E 0 E 30 NA
⋮ ⋮ ⋮ ⋮ ⋮ ⋮
Q1048694 C 2048095025 A 15936317 NA
Q31165 C 2048330818 A 15936318 NA
Q40629 C 2049755644 A 15936319 NA
Q105584 C 2049926923 A 15936320 NA
Q4584301 D 2052339927 A 15936321 NA
Q565 C 2052996261 A 15936322 NA
Q1868372 E 2056080224 A 15936323 NA
Q209330 C 2060928966 A 15936324 NA
Q14005 D 2063120071 A 15936325 NA
Q918 C 2063217449 A 15936326 NA
Q150248 C 2068796814 A 15936327 NA
Q866 C 2079749157 A 15936328 NA
Q477675 C 2080785713 A 15936329 NA
Q1967876 C 2084215818 A 15936330 NA
Q750403 C 2084693498 A 15936331 NA
Q355 C 2093900731 A 15936332 NA
Q623578 C 2097991400 A 15936333 NA
Q17299517 D 2105487660 A 15936334 NA
Q33999 C 2108672678 A 15936335 NA
Q2494649 C 2114531894 A 15936336 NA
Q2597810 C 2128920607 A 15936337 NA
Q193563 C 2130725560 A 15936338 NA
Q423048 C 2136131564 A 15936339 NA
Q37312 C 2142913121 A 15936340 NA
Q54919 C 2148531382 A 15936341 NA
Q36578 C 2229315598 A 15936342 NA
Q30 A 2277746226 A 15936343 NA
Q6581097 C 3273952711 A 15936344 NA
Q5 A 5668008721 A 15936345 NA
Q5296 C 12530369761 A 15936346 NA
entity_id prediction page_views pop_class seqNum dissonance
Q10040378 E 0 E 1 NA
Q10069140 E 0 E 2 NA
Q10081695 E 0 E 3 NA
Q10092002 E 0 E 4 NA
Q10111267 E 0 E 5 NA
Q10149726 E 0 E 6 NA
Q10180230 E 0 E 7 NA
Q10185035 E 0 E 8 NA
Q10205202 E 0 E 9 NA
Q10252966 E 0 E 10 NA
Q10444494 D 0 E 11 NA
Q10624171 D 0 E 12 NA
Q10704108 D 0 E 13 NA
Q10750354 E 0 E 14 NA
Q10766855 E 0 E 15 NA
Q10827611 E 0 E 16 NA
Q11093044 E 0 E 17 NA
Q11934537 E 0 E 18 NA
Q12133466 E 0 E 19 NA
Q12264503 E 0 E 20 NA
Q12267516 E 0 E 21 NA
Q12304084 E 0 E 22 NA
Q12443525 E 0 E 23 NA
Q12543904 E 0 E 24 NA
Q12890205 E 0 E 25 NA
Q12891524 E 0 E 26 NA
Q12918202 E 0 E 27 NA
Q13005653 E 0 E 28 NA
Q13073896 E 0 E 29 NA
Q13163823 E 0 E 30 NA
⋮ ⋮ ⋮ ⋮ ⋮ ⋮
Q1048694 C 2048095025 A 15936317 NA
Q31165 C 2048330818 A 15936318 NA
Q40629 C 2049755644 A 15936319 NA
Q105584 C 2049926923 A 15936320 NA
Q4584301 D 2052339927 A 15936321 NA
Q565 C 2052996261 A 15936322 NA
Q1868372 E 2056080224 A 15936323 NA
Q209330 C 2060928966 A 15936324 NA
Q14005 D 2063120071 A 15936325 NA
Q918 C 2063217449 A 15936326 NA
Q150248 C 2068796814 A 15936327 NA
Q866 C 2079749157 A 15936328 NA
Q477675 C 2080785713 A 15936329 NA
Q1967876 C 2084215818 A 15936330 NA
Q750403 C 2084693498 A 15936331 NA
Q355 C 2093900731 A 15936332 NA
Q623578 C 2097991400 A 15936333 NA
Q17299517 D 2105487660 A 15936334 NA
Q33999 C 2108672678 A 15936335 NA
Q2494649 C 2114531894 A 15936336 NA
Q2597810 C 2128920607 A 15936337 NA
Q193563 C 2130725560 A 15936338 NA
Q423048 C 2136131564 A 15936339 NA
Q37312 C 2142913121 A 15936340 NA
Q54919 C 2148531382 A 15936341 NA
Q36578 C 2229315598 A 15936342 NA
Q30 A 2277746226 A 15936343 None
Q6581097 C 3273952711 A 15936344 NA
Q5 A 5668008721 A 15936345 None
Q5296 C 12530369761 A 15936346 NA
In [35]:
## B:
articles_by_pop[prediction == 'B' & pop_class <= 'D',
dissonance := 'High negative'];
articles_by_pop[prediction == 'B' & pop_class == 'C',
dissonance := 'Moderate negative'];
articles_by_pop[prediction == 'B' & pop_class == 'B',
dissonance := 'None'];
articles_by_pop[prediction == 'B' & pop_class == 'A',
dissonance := 'Moderate positive'];
entity_id prediction page_views pop_class seqNum dissonance
Q10040378 E 0 E 1 NA
Q10069140 E 0 E 2 NA
Q10081695 E 0 E 3 NA
Q10092002 E 0 E 4 NA
Q10111267 E 0 E 5 NA
Q10149726 E 0 E 6 NA
Q10180230 E 0 E 7 NA
Q10185035 E 0 E 8 NA
Q10205202 E 0 E 9 NA
Q10252966 E 0 E 10 NA
Q10444494 D 0 E 11 NA
Q10624171 D 0 E 12 NA
Q10704108 D 0 E 13 NA
Q10750354 E 0 E 14 NA
Q10766855 E 0 E 15 NA
Q10827611 E 0 E 16 NA
Q11093044 E 0 E 17 NA
Q11934537 E 0 E 18 NA
Q12133466 E 0 E 19 NA
Q12264503 E 0 E 20 NA
Q12267516 E 0 E 21 NA
Q12304084 E 0 E 22 NA
Q12443525 E 0 E 23 NA
Q12543904 E 0 E 24 NA
Q12890205 E 0 E 25 NA
Q12891524 E 0 E 26 NA
Q12918202 E 0 E 27 NA
Q13005653 E 0 E 28 NA
Q13073896 E 0 E 29 NA
Q13163823 E 0 E 30 NA
⋮ ⋮ ⋮ ⋮ ⋮ ⋮
Q1048694 C 2048095025 A 15936317 NA
Q31165 C 2048330818 A 15936318 NA
Q40629 C 2049755644 A 15936319 NA
Q105584 C 2049926923 A 15936320 NA
Q4584301 D 2052339927 A 15936321 NA
Q565 C 2052996261 A 15936322 NA
Q1868372 E 2056080224 A 15936323 NA
Q209330 C 2060928966 A 15936324 NA
Q14005 D 2063120071 A 15936325 NA
Q918 C 2063217449 A 15936326 NA
Q150248 C 2068796814 A 15936327 NA
Q866 C 2079749157 A 15936328 NA
Q477675 C 2080785713 A 15936329 NA
Q1967876 C 2084215818 A 15936330 NA
Q750403 C 2084693498 A 15936331 NA
Q355 C 2093900731 A 15936332 NA
Q623578 C 2097991400 A 15936333 NA
Q17299517 D 2105487660 A 15936334 NA
Q33999 C 2108672678 A 15936335 NA
Q2494649 C 2114531894 A 15936336 NA
Q2597810 C 2128920607 A 15936337 NA
Q193563 C 2130725560 A 15936338 NA
Q423048 C 2136131564 A 15936339 NA
Q37312 C 2142913121 A 15936340 NA
Q54919 C 2148531382 A 15936341 NA
Q36578 C 2229315598 A 15936342 NA
Q30 A 2277746226 A 15936343 None
Q6581097 C 3273952711 A 15936344 NA
Q5 A 5668008721 A 15936345 None
Q5296 C 12530369761 A 15936346 NA
entity_id prediction page_views pop_class seqNum dissonance
Q10040378 E 0 E 1 NA
Q10069140 E 0 E 2 NA
Q10081695 E 0 E 3 NA
Q10092002 E 0 E 4 NA
Q10111267 E 0 E 5 NA
Q10149726 E 0 E 6 NA
Q10180230 E 0 E 7 NA
Q10185035 E 0 E 8 NA
Q10205202 E 0 E 9 NA
Q10252966 E 0 E 10 NA
Q10444494 D 0 E 11 NA
Q10624171 D 0 E 12 NA
Q10704108 D 0 E 13 NA
Q10750354 E 0 E 14 NA
Q10766855 E 0 E 15 NA
Q10827611 E 0 E 16 NA
Q11093044 E 0 E 17 NA
Q11934537 E 0 E 18 NA
Q12133466 E 0 E 19 NA
Q12264503 E 0 E 20 NA
Q12267516 E 0 E 21 NA
Q12304084 E 0 E 22 NA
Q12443525 E 0 E 23 NA
Q12543904 E 0 E 24 NA
Q12890205 E 0 E 25 NA
Q12891524 E 0 E 26 NA
Q12918202 E 0 E 27 NA
Q13005653 E 0 E 28 NA
Q13073896 E 0 E 29 NA
Q13163823 E 0 E 30 NA
⋮ ⋮ ⋮ ⋮ ⋮ ⋮
Q1048694 C 2048095025 A 15936317 NA
Q31165 C 2048330818 A 15936318 NA
Q40629 C 2049755644 A 15936319 NA
Q105584 C 2049926923 A 15936320 NA
Q4584301 D 2052339927 A 15936321 NA
Q565 C 2052996261 A 15936322 NA
Q1868372 E 2056080224 A 15936323 NA
Q209330 C 2060928966 A 15936324 NA
Q14005 D 2063120071 A 15936325 NA
Q918 C 2063217449 A 15936326 NA
Q150248 C 2068796814 A 15936327 NA
Q866 C 2079749157 A 15936328 NA
Q477675 C 2080785713 A 15936329 NA
Q1967876 C 2084215818 A 15936330 NA
Q750403 C 2084693498 A 15936331 NA
Q355 C 2093900731 A 15936332 NA
Q623578 C 2097991400 A 15936333 NA
Q17299517 D 2105487660 A 15936334 NA
Q33999 C 2108672678 A 15936335 NA
Q2494649 C 2114531894 A 15936336 NA
Q2597810 C 2128920607 A 15936337 NA
Q193563 C 2130725560 A 15936338 NA
Q423048 C 2136131564 A 15936339 NA
Q37312 C 2142913121 A 15936340 NA
Q54919 C 2148531382 A 15936341 NA
Q36578 C 2229315598 A 15936342 NA
Q30 A 2277746226 A 15936343 None
Q6581097 C 3273952711 A 15936344 NA
Q5 A 5668008721 A 15936345 None
Q5296 C 12530369761 A 15936346 NA
entity_id prediction page_views pop_class seqNum dissonance
Q10040378 E 0 E 1 NA
Q10069140 E 0 E 2 NA
Q10081695 E 0 E 3 NA
Q10092002 E 0 E 4 NA
Q10111267 E 0 E 5 NA
Q10149726 E 0 E 6 NA
Q10180230 E 0 E 7 NA
Q10185035 E 0 E 8 NA
Q10205202 E 0 E 9 NA
Q10252966 E 0 E 10 NA
Q10444494 D 0 E 11 NA
Q10624171 D 0 E 12 NA
Q10704108 D 0 E 13 NA
Q10750354 E 0 E 14 NA
Q10766855 E 0 E 15 NA
Q10827611 E 0 E 16 NA
Q11093044 E 0 E 17 NA
Q11934537 E 0 E 18 NA
Q12133466 E 0 E 19 NA
Q12264503 E 0 E 20 NA
Q12267516 E 0 E 21 NA
Q12304084 E 0 E 22 NA
Q12443525 E 0 E 23 NA
Q12543904 E 0 E 24 NA
Q12890205 E 0 E 25 NA
Q12891524 E 0 E 26 NA
Q12918202 E 0 E 27 NA
Q13005653 E 0 E 28 NA
Q13073896 E 0 E 29 NA
Q13163823 E 0 E 30 NA
⋮ ⋮ ⋮ ⋮ ⋮ ⋮
Q1048694 C 2048095025 A 15936317 NA
Q31165 C 2048330818 A 15936318 NA
Q40629 C 2049755644 A 15936319 NA
Q105584 C 2049926923 A 15936320 NA
Q4584301 D 2052339927 A 15936321 NA
Q565 C 2052996261 A 15936322 NA
Q1868372 E 2056080224 A 15936323 NA
Q209330 C 2060928966 A 15936324 NA
Q14005 D 2063120071 A 15936325 NA
Q918 C 2063217449 A 15936326 NA
Q150248 C 2068796814 A 15936327 NA
Q866 C 2079749157 A 15936328 NA
Q477675 C 2080785713 A 15936329 NA
Q1967876 C 2084215818 A 15936330 NA
Q750403 C 2084693498 A 15936331 NA
Q355 C 2093900731 A 15936332 NA
Q623578 C 2097991400 A 15936333 NA
Q17299517 D 2105487660 A 15936334 NA
Q33999 C 2108672678 A 15936335 NA
Q2494649 C 2114531894 A 15936336 NA
Q2597810 C 2128920607 A 15936337 NA
Q193563 C 2130725560 A 15936338 NA
Q423048 C 2136131564 A 15936339 NA
Q37312 C 2142913121 A 15936340 NA
Q54919 C 2148531382 A 15936341 NA
Q36578 C 2229315598 A 15936342 NA
Q30 A 2277746226 A 15936343 None
Q6581097 C 3273952711 A 15936344 NA
Q5 A 5668008721 A 15936345 None
Q5296 C 12530369761 A 15936346 NA
entity_id prediction page_views pop_class seqNum dissonance
Q10040378 E 0 E 1 NA
Q10069140 E 0 E 2 NA
Q10081695 E 0 E 3 NA
Q10092002 E 0 E 4 NA
Q10111267 E 0 E 5 NA
Q10149726 E 0 E 6 NA
Q10180230 E 0 E 7 NA
Q10185035 E 0 E 8 NA
Q10205202 E 0 E 9 NA
Q10252966 E 0 E 10 NA
Q10444494 D 0 E 11 NA
Q10624171 D 0 E 12 NA
Q10704108 D 0 E 13 NA
Q10750354 E 0 E 14 NA
Q10766855 E 0 E 15 NA
Q10827611 E 0 E 16 NA
Q11093044 E 0 E 17 NA
Q11934537 E 0 E 18 NA
Q12133466 E 0 E 19 NA
Q12264503 E 0 E 20 NA
Q12267516 E 0 E 21 NA
Q12304084 E 0 E 22 NA
Q12443525 E 0 E 23 NA
Q12543904 E 0 E 24 NA
Q12890205 E 0 E 25 NA
Q12891524 E 0 E 26 NA
Q12918202 E 0 E 27 NA
Q13005653 E 0 E 28 NA
Q13073896 E 0 E 29 NA
Q13163823 E 0 E 30 NA
⋮ ⋮ ⋮ ⋮ ⋮ ⋮
Q1048694 C 2048095025 A 15936317 NA
Q31165 C 2048330818 A 15936318 NA
Q40629 C 2049755644 A 15936319 NA
Q105584 C 2049926923 A 15936320 NA
Q4584301 D 2052339927 A 15936321 NA
Q565 C 2052996261 A 15936322 NA
Q1868372 E 2056080224 A 15936323 NA
Q209330 C 2060928966 A 15936324 NA
Q14005 D 2063120071 A 15936325 NA
Q918 C 2063217449 A 15936326 NA
Q150248 C 2068796814 A 15936327 NA
Q866 C 2079749157 A 15936328 NA
Q477675 C 2080785713 A 15936329 NA
Q1967876 C 2084215818 A 15936330 NA
Q750403 C 2084693498 A 15936331 NA
Q355 C 2093900731 A 15936332 NA
Q623578 C 2097991400 A 15936333 NA
Q17299517 D 2105487660 A 15936334 NA
Q33999 C 2108672678 A 15936335 NA
Q2494649 C 2114531894 A 15936336 NA
Q2597810 C 2128920607 A 15936337 NA
Q193563 C 2130725560 A 15936338 NA
Q423048 C 2136131564 A 15936339 NA
Q37312 C 2142913121 A 15936340 NA
Q54919 C 2148531382 A 15936341 NA
Q36578 C 2229315598 A 15936342 NA
Q30 A 2277746226 A 15936343 None
Q6581097 C 3273952711 A 15936344 NA
Q5 A 5668008721 A 15936345 None
Q5296 C 12530369761 A 15936346 NA
In [36]:
## C:
articles_by_pop[prediction == 'C' & pop_class == 'E',
dissonance := 'High negative'];
articles_by_pop[prediction == 'C' & pop_class == 'D',
dissonance := 'Moderate negative'];
articles_by_pop[prediction == 'C' & pop_class == 'C',
dissonance := 'None'];
articles_by_pop[prediction == 'C' & pop_class == 'B',
dissonance := 'Moderate positive'];
articles_by_pop[prediction == 'C' & pop_class == 'A',
dissonance := 'High positive'];
entity_id prediction page_views pop_class seqNum dissonance
Q10040378 E 0 E 1 NA
Q10069140 E 0 E 2 NA
Q10081695 E 0 E 3 NA
Q10092002 E 0 E 4 NA
Q10111267 E 0 E 5 NA
Q10149726 E 0 E 6 NA
Q10180230 E 0 E 7 NA
Q10185035 E 0 E 8 NA
Q10205202 E 0 E 9 NA
Q10252966 E 0 E 10 NA
Q10444494 D 0 E 11 NA
Q10624171 D 0 E 12 NA
Q10704108 D 0 E 13 NA
Q10750354 E 0 E 14 NA
Q10766855 E 0 E 15 NA
Q10827611 E 0 E 16 NA
Q11093044 E 0 E 17 NA
Q11934537 E 0 E 18 NA
Q12133466 E 0 E 19 NA
Q12264503 E 0 E 20 NA
Q12267516 E 0 E 21 NA
Q12304084 E 0 E 22 NA
Q12443525 E 0 E 23 NA
Q12543904 E 0 E 24 NA
Q12890205 E 0 E 25 NA
Q12891524 E 0 E 26 NA
Q12918202 E 0 E 27 NA
Q13005653 E 0 E 28 NA
Q13073896 E 0 E 29 NA
Q13163823 E 0 E 30 NA
⋮ ⋮ ⋮ ⋮ ⋮ ⋮
Q1048694 C 2048095025 A 15936317 NA
Q31165 C 2048330818 A 15936318 NA
Q40629 C 2049755644 A 15936319 NA
Q105584 C 2049926923 A 15936320 NA
Q4584301 D 2052339927 A 15936321 NA
Q565 C 2052996261 A 15936322 NA
Q1868372 E 2056080224 A 15936323 NA
Q209330 C 2060928966 A 15936324 NA
Q14005 D 2063120071 A 15936325 NA
Q918 C 2063217449 A 15936326 NA
Q150248 C 2068796814 A 15936327 NA
Q866 C 2079749157 A 15936328 NA
Q477675 C 2080785713 A 15936329 NA
Q1967876 C 2084215818 A 15936330 NA
Q750403 C 2084693498 A 15936331 NA
Q355 C 2093900731 A 15936332 NA
Q623578 C 2097991400 A 15936333 NA
Q17299517 D 2105487660 A 15936334 NA
Q33999 C 2108672678 A 15936335 NA
Q2494649 C 2114531894 A 15936336 NA
Q2597810 C 2128920607 A 15936337 NA
Q193563 C 2130725560 A 15936338 NA
Q423048 C 2136131564 A 15936339 NA
Q37312 C 2142913121 A 15936340 NA
Q54919 C 2148531382 A 15936341 NA
Q36578 C 2229315598 A 15936342 NA
Q30 A 2277746226 A 15936343 None
Q6581097 C 3273952711 A 15936344 NA
Q5 A 5668008721 A 15936345 None
Q5296 C 12530369761 A 15936346 NA
entity_id prediction page_views pop_class seqNum dissonance
Q10040378 E 0 E 1 NA
Q10069140 E 0 E 2 NA
Q10081695 E 0 E 3 NA
Q10092002 E 0 E 4 NA
Q10111267 E 0 E 5 NA
Q10149726 E 0 E 6 NA
Q10180230 E 0 E 7 NA
Q10185035 E 0 E 8 NA
Q10205202 E 0 E 9 NA
Q10252966 E 0 E 10 NA
Q10444494 D 0 E 11 NA
Q10624171 D 0 E 12 NA
Q10704108 D 0 E 13 NA
Q10750354 E 0 E 14 NA
Q10766855 E 0 E 15 NA
Q10827611 E 0 E 16 NA
Q11093044 E 0 E 17 NA
Q11934537 E 0 E 18 NA
Q12133466 E 0 E 19 NA
Q12264503 E 0 E 20 NA
Q12267516 E 0 E 21 NA
Q12304084 E 0 E 22 NA
Q12443525 E 0 E 23 NA
Q12543904 E 0 E 24 NA
Q12890205 E 0 E 25 NA
Q12891524 E 0 E 26 NA
Q12918202 E 0 E 27 NA
Q13005653 E 0 E 28 NA
Q13073896 E 0 E 29 NA
Q13163823 E 0 E 30 NA
⋮ ⋮ ⋮ ⋮ ⋮ ⋮
Q1048694 C 2048095025 A 15936317 NA
Q31165 C 2048330818 A 15936318 NA
Q40629 C 2049755644 A 15936319 NA
Q105584 C 2049926923 A 15936320 NA
Q4584301 D 2052339927 A 15936321 NA
Q565 C 2052996261 A 15936322 NA
Q1868372 E 2056080224 A 15936323 NA
Q209330 C 2060928966 A 15936324 NA
Q14005 D 2063120071 A 15936325 NA
Q918 C 2063217449 A 15936326 NA
Q150248 C 2068796814 A 15936327 NA
Q866 C 2079749157 A 15936328 NA
Q477675 C 2080785713 A 15936329 NA
Q1967876 C 2084215818 A 15936330 NA
Q750403 C 2084693498 A 15936331 NA
Q355 C 2093900731 A 15936332 NA
Q623578 C 2097991400 A 15936333 NA
Q17299517 D 2105487660 A 15936334 NA
Q33999 C 2108672678 A 15936335 NA
Q2494649 C 2114531894 A 15936336 NA
Q2597810 C 2128920607 A 15936337 NA
Q193563 C 2130725560 A 15936338 NA
Q423048 C 2136131564 A 15936339 NA
Q37312 C 2142913121 A 15936340 NA
Q54919 C 2148531382 A 15936341 NA
Q36578 C 2229315598 A 15936342 NA
Q30 A 2277746226 A 15936343 None
Q6581097 C 3273952711 A 15936344 NA
Q5 A 5668008721 A 15936345 None
Q5296 C 12530369761 A 15936346 NA
entity_id prediction page_views pop_class seqNum dissonance
Q10040378 E 0 E 1 NA
Q10069140 E 0 E 2 NA
Q10081695 E 0 E 3 NA
Q10092002 E 0 E 4 NA
Q10111267 E 0 E 5 NA
Q10149726 E 0 E 6 NA
Q10180230 E 0 E 7 NA
Q10185035 E 0 E 8 NA
Q10205202 E 0 E 9 NA
Q10252966 E 0 E 10 NA
Q10444494 D 0 E 11 NA
Q10624171 D 0 E 12 NA
Q10704108 D 0 E 13 NA
Q10750354 E 0 E 14 NA
Q10766855 E 0 E 15 NA
Q10827611 E 0 E 16 NA
Q11093044 E 0 E 17 NA
Q11934537 E 0 E 18 NA
Q12133466 E 0 E 19 NA
Q12264503 E 0 E 20 NA
Q12267516 E 0 E 21 NA
Q12304084 E 0 E 22 NA
Q12443525 E 0 E 23 NA
Q12543904 E 0 E 24 NA
Q12890205 E 0 E 25 NA
Q12891524 E 0 E 26 NA
Q12918202 E 0 E 27 NA
Q13005653 E 0 E 28 NA
Q13073896 E 0 E 29 NA
Q13163823 E 0 E 30 NA
⋮ ⋮ ⋮ ⋮ ⋮ ⋮
Q1048694 C 2048095025 A 15936317 NA
Q31165 C 2048330818 A 15936318 NA
Q40629 C 2049755644 A 15936319 NA
Q105584 C 2049926923 A 15936320 NA
Q4584301 D 2052339927 A 15936321 NA
Q565 C 2052996261 A 15936322 NA
Q1868372 E 2056080224 A 15936323 NA
Q209330 C 2060928966 A 15936324 NA
Q14005 D 2063120071 A 15936325 NA
Q918 C 2063217449 A 15936326 NA
Q150248 C 2068796814 A 15936327 NA
Q866 C 2079749157 A 15936328 NA
Q477675 C 2080785713 A 15936329 NA
Q1967876 C 2084215818 A 15936330 NA
Q750403 C 2084693498 A 15936331 NA
Q355 C 2093900731 A 15936332 NA
Q623578 C 2097991400 A 15936333 NA
Q17299517 D 2105487660 A 15936334 NA
Q33999 C 2108672678 A 15936335 NA
Q2494649 C 2114531894 A 15936336 NA
Q2597810 C 2128920607 A 15936337 NA
Q193563 C 2130725560 A 15936338 NA
Q423048 C 2136131564 A 15936339 NA
Q37312 C 2142913121 A 15936340 NA
Q54919 C 2148531382 A 15936341 NA
Q36578 C 2229315598 A 15936342 NA
Q30 A 2277746226 A 15936343 None
Q6581097 C 3273952711 A 15936344 NA
Q5 A 5668008721 A 15936345 None
Q5296 C 12530369761 A 15936346 NA
entity_id prediction page_views pop_class seqNum dissonance
Q10040378 E 0 E 1 NA
Q10069140 E 0 E 2 NA
Q10081695 E 0 E 3 NA
Q10092002 E 0 E 4 NA
Q10111267 E 0 E 5 NA
Q10149726 E 0 E 6 NA
Q10180230 E 0 E 7 NA
Q10185035 E 0 E 8 NA
Q10205202 E 0 E 9 NA
Q10252966 E 0 E 10 NA
Q10444494 D 0 E 11 NA
Q10624171 D 0 E 12 NA
Q10704108 D 0 E 13 NA
Q10750354 E 0 E 14 NA
Q10766855 E 0 E 15 NA
Q10827611 E 0 E 16 NA
Q11093044 E 0 E 17 NA
Q11934537 E 0 E 18 NA
Q12133466 E 0 E 19 NA
Q12264503 E 0 E 20 NA
Q12267516 E 0 E 21 NA
Q12304084 E 0 E 22 NA
Q12443525 E 0 E 23 NA
Q12543904 E 0 E 24 NA
Q12890205 E 0 E 25 NA
Q12891524 E 0 E 26 NA
Q12918202 E 0 E 27 NA
Q13005653 E 0 E 28 NA
Q13073896 E 0 E 29 NA
Q13163823 E 0 E 30 NA
⋮ ⋮ ⋮ ⋮ ⋮ ⋮
Q1048694 C 2048095025 A 15936317 NA
Q31165 C 2048330818 A 15936318 NA
Q40629 C 2049755644 A 15936319 NA
Q105584 C 2049926923 A 15936320 NA
Q4584301 D 2052339927 A 15936321 NA
Q565 C 2052996261 A 15936322 NA
Q1868372 E 2056080224 A 15936323 NA
Q209330 C 2060928966 A 15936324 NA
Q14005 D 2063120071 A 15936325 NA
Q918 C 2063217449 A 15936326 NA
Q150248 C 2068796814 A 15936327 NA
Q866 C 2079749157 A 15936328 NA
Q477675 C 2080785713 A 15936329 NA
Q1967876 C 2084215818 A 15936330 NA
Q750403 C 2084693498 A 15936331 NA
Q355 C 2093900731 A 15936332 NA
Q623578 C 2097991400 A 15936333 NA
Q17299517 D 2105487660 A 15936334 NA
Q33999 C 2108672678 A 15936335 NA
Q2494649 C 2114531894 A 15936336 NA
Q2597810 C 2128920607 A 15936337 NA
Q193563 C 2130725560 A 15936338 NA
Q423048 C 2136131564 A 15936339 NA
Q37312 C 2142913121 A 15936340 NA
Q54919 C 2148531382 A 15936341 NA
Q36578 C 2229315598 A 15936342 NA
Q30 A 2277746226 A 15936343 None
Q6581097 C 3273952711 A 15936344 NA
Q5 A 5668008721 A 15936345 None
Q5296 C 12530369761 A 15936346 NA
entity_id prediction page_views pop_class seqNum dissonance
Q10040378 E 0 E 1 NA
Q10069140 E 0 E 2 NA
Q10081695 E 0 E 3 NA
Q10092002 E 0 E 4 NA
Q10111267 E 0 E 5 NA
Q10149726 E 0 E 6 NA
Q10180230 E 0 E 7 NA
Q10185035 E 0 E 8 NA
Q10205202 E 0 E 9 NA
Q10252966 E 0 E 10 NA
Q10444494 D 0 E 11 NA
Q10624171 D 0 E 12 NA
Q10704108 D 0 E 13 NA
Q10750354 E 0 E 14 NA
Q10766855 E 0 E 15 NA
Q10827611 E 0 E 16 NA
Q11093044 E 0 E 17 NA
Q11934537 E 0 E 18 NA
Q12133466 E 0 E 19 NA
Q12264503 E 0 E 20 NA
Q12267516 E 0 E 21 NA
Q12304084 E 0 E 22 NA
Q12443525 E 0 E 23 NA
Q12543904 E 0 E 24 NA
Q12890205 E 0 E 25 NA
Q12891524 E 0 E 26 NA
Q12918202 E 0 E 27 NA
Q13005653 E 0 E 28 NA
Q13073896 E 0 E 29 NA
Q13163823 E 0 E 30 NA
⋮ ⋮ ⋮ ⋮ ⋮ ⋮
Q1048694 C 2048095025 A 15936317 High positive
Q31165 C 2048330818 A 15936318 High positive
Q40629 C 2049755644 A 15936319 High positive
Q105584 C 2049926923 A 15936320 High positive
Q4584301 D 2052339927 A 15936321 NA
Q565 C 2052996261 A 15936322 High positive
Q1868372 E 2056080224 A 15936323 NA
Q209330 C 2060928966 A 15936324 High positive
Q14005 D 2063120071 A 15936325 NA
Q918 C 2063217449 A 15936326 High positive
Q150248 C 2068796814 A 15936327 High positive
Q866 C 2079749157 A 15936328 High positive
Q477675 C 2080785713 A 15936329 High positive
Q1967876 C 2084215818 A 15936330 High positive
Q750403 C 2084693498 A 15936331 High positive
Q355 C 2093900731 A 15936332 High positive
Q623578 C 2097991400 A 15936333 High positive
Q17299517 D 2105487660 A 15936334 NA
Q33999 C 2108672678 A 15936335 High positive
Q2494649 C 2114531894 A 15936336 High positive
Q2597810 C 2128920607 A 15936337 High positive
Q193563 C 2130725560 A 15936338 High positive
Q423048 C 2136131564 A 15936339 High positive
Q37312 C 2142913121 A 15936340 High positive
Q54919 C 2148531382 A 15936341 High positive
Q36578 C 2229315598 A 15936342 High positive
Q30 A 2277746226 A 15936343 None
Q6581097 C 3273952711 A 15936344 High positive
Q5 A 5668008721 A 15936345 None
Q5296 C 12530369761 A 15936346 High positive
In [37]:
## D
articles_by_pop[prediction == 'D' & pop_class == 'E',
dissonance := 'Moderate negative'];
articles_by_pop[prediction == 'D' & pop_class == 'D',
dissonance := 'None'];
articles_by_pop[prediction == 'D' & pop_class == 'C',
dissonance := 'Moderate positive'];
articles_by_pop[prediction == 'D' & pop_class >= 'B',
dissonance := 'High positive'];
entity_id prediction page_views pop_class seqNum dissonance
Q10040378 E 0 E 1 NA
Q10069140 E 0 E 2 NA
Q10081695 E 0 E 3 NA
Q10092002 E 0 E 4 NA
Q10111267 E 0 E 5 NA
Q10149726 E 0 E 6 NA
Q10180230 E 0 E 7 NA
Q10185035 E 0 E 8 NA
Q10205202 E 0 E 9 NA
Q10252966 E 0 E 10 NA
Q10444494 D 0 E 11 Moderate negative
Q10624171 D 0 E 12 Moderate negative
Q10704108 D 0 E 13 Moderate negative
Q10750354 E 0 E 14 NA
Q10766855 E 0 E 15 NA
Q10827611 E 0 E 16 NA
Q11093044 E 0 E 17 NA
Q11934537 E 0 E 18 NA
Q12133466 E 0 E 19 NA
Q12264503 E 0 E 20 NA
Q12267516 E 0 E 21 NA
Q12304084 E 0 E 22 NA
Q12443525 E 0 E 23 NA
Q12543904 E 0 E 24 NA
Q12890205 E 0 E 25 NA
Q12891524 E 0 E 26 NA
Q12918202 E 0 E 27 NA
Q13005653 E 0 E 28 NA
Q13073896 E 0 E 29 NA
Q13163823 E 0 E 30 NA
⋮ ⋮ ⋮ ⋮ ⋮ ⋮
Q1048694 C 2048095025 A 15936317 High positive
Q31165 C 2048330818 A 15936318 High positive
Q40629 C 2049755644 A 15936319 High positive
Q105584 C 2049926923 A 15936320 High positive
Q4584301 D 2052339927 A 15936321 NA
Q565 C 2052996261 A 15936322 High positive
Q1868372 E 2056080224 A 15936323 NA
Q209330 C 2060928966 A 15936324 High positive
Q14005 D 2063120071 A 15936325 NA
Q918 C 2063217449 A 15936326 High positive
Q150248 C 2068796814 A 15936327 High positive
Q866 C 2079749157 A 15936328 High positive
Q477675 C 2080785713 A 15936329 High positive
Q1967876 C 2084215818 A 15936330 High positive
Q750403 C 2084693498 A 15936331 High positive
Q355 C 2093900731 A 15936332 High positive
Q623578 C 2097991400 A 15936333 High positive
Q17299517 D 2105487660 A 15936334 NA
Q33999 C 2108672678 A 15936335 High positive
Q2494649 C 2114531894 A 15936336 High positive
Q2597810 C 2128920607 A 15936337 High positive
Q193563 C 2130725560 A 15936338 High positive
Q423048 C 2136131564 A 15936339 High positive
Q37312 C 2142913121 A 15936340 High positive
Q54919 C 2148531382 A 15936341 High positive
Q36578 C 2229315598 A 15936342 High positive
Q30 A 2277746226 A 15936343 None
Q6581097 C 3273952711 A 15936344 High positive
Q5 A 5668008721 A 15936345 None
Q5296 C 12530369761 A 15936346 High positive
entity_id prediction page_views pop_class seqNum dissonance
Q10040378 E 0 E 1 NA
Q10069140 E 0 E 2 NA
Q10081695 E 0 E 3 NA
Q10092002 E 0 E 4 NA
Q10111267 E 0 E 5 NA
Q10149726 E 0 E 6 NA
Q10180230 E 0 E 7 NA
Q10185035 E 0 E 8 NA
Q10205202 E 0 E 9 NA
Q10252966 E 0 E 10 NA
Q10444494 D 0 E 11 Moderate negative
Q10624171 D 0 E 12 Moderate negative
Q10704108 D 0 E 13 Moderate negative
Q10750354 E 0 E 14 NA
Q10766855 E 0 E 15 NA
Q10827611 E 0 E 16 NA
Q11093044 E 0 E 17 NA
Q11934537 E 0 E 18 NA
Q12133466 E 0 E 19 NA
Q12264503 E 0 E 20 NA
Q12267516 E 0 E 21 NA
Q12304084 E 0 E 22 NA
Q12443525 E 0 E 23 NA
Q12543904 E 0 E 24 NA
Q12890205 E 0 E 25 NA
Q12891524 E 0 E 26 NA
Q12918202 E 0 E 27 NA
Q13005653 E 0 E 28 NA
Q13073896 E 0 E 29 NA
Q13163823 E 0 E 30 NA
⋮ ⋮ ⋮ ⋮ ⋮ ⋮
Q1048694 C 2048095025 A 15936317 High positive
Q31165 C 2048330818 A 15936318 High positive
Q40629 C 2049755644 A 15936319 High positive
Q105584 C 2049926923 A 15936320 High positive
Q4584301 D 2052339927 A 15936321 NA
Q565 C 2052996261 A 15936322 High positive
Q1868372 E 2056080224 A 15936323 NA
Q209330 C 2060928966 A 15936324 High positive
Q14005 D 2063120071 A 15936325 NA
Q918 C 2063217449 A 15936326 High positive
Q150248 C 2068796814 A 15936327 High positive
Q866 C 2079749157 A 15936328 High positive
Q477675 C 2080785713 A 15936329 High positive
Q1967876 C 2084215818 A 15936330 High positive
Q750403 C 2084693498 A 15936331 High positive
Q355 C 2093900731 A 15936332 High positive
Q623578 C 2097991400 A 15936333 High positive
Q17299517 D 2105487660 A 15936334 NA
Q33999 C 2108672678 A 15936335 High positive
Q2494649 C 2114531894 A 15936336 High positive
Q2597810 C 2128920607 A 15936337 High positive
Q193563 C 2130725560 A 15936338 High positive
Q423048 C 2136131564 A 15936339 High positive
Q37312 C 2142913121 A 15936340 High positive
Q54919 C 2148531382 A 15936341 High positive
Q36578 C 2229315598 A 15936342 High positive
Q30 A 2277746226 A 15936343 None
Q6581097 C 3273952711 A 15936344 High positive
Q5 A 5668008721 A 15936345 None
Q5296 C 12530369761 A 15936346 High positive
entity_id prediction page_views pop_class seqNum dissonance
Q10040378 E 0 E 1 NA
Q10069140 E 0 E 2 NA
Q10081695 E 0 E 3 NA
Q10092002 E 0 E 4 NA
Q10111267 E 0 E 5 NA
Q10149726 E 0 E 6 NA
Q10180230 E 0 E 7 NA
Q10185035 E 0 E 8 NA
Q10205202 E 0 E 9 NA
Q10252966 E 0 E 10 NA
Q10444494 D 0 E 11 Moderate negative
Q10624171 D 0 E 12 Moderate negative
Q10704108 D 0 E 13 Moderate negative
Q10750354 E 0 E 14 NA
Q10766855 E 0 E 15 NA
Q10827611 E 0 E 16 NA
Q11093044 E 0 E 17 NA
Q11934537 E 0 E 18 NA
Q12133466 E 0 E 19 NA
Q12264503 E 0 E 20 NA
Q12267516 E 0 E 21 NA
Q12304084 E 0 E 22 NA
Q12443525 E 0 E 23 NA
Q12543904 E 0 E 24 NA
Q12890205 E 0 E 25 NA
Q12891524 E 0 E 26 NA
Q12918202 E 0 E 27 NA
Q13005653 E 0 E 28 NA
Q13073896 E 0 E 29 NA
Q13163823 E 0 E 30 NA
⋮ ⋮ ⋮ ⋮ ⋮ ⋮
Q1048694 C 2048095025 A 15936317 High positive
Q31165 C 2048330818 A 15936318 High positive
Q40629 C 2049755644 A 15936319 High positive
Q105584 C 2049926923 A 15936320 High positive
Q4584301 D 2052339927 A 15936321 NA
Q565 C 2052996261 A 15936322 High positive
Q1868372 E 2056080224 A 15936323 NA
Q209330 C 2060928966 A 15936324 High positive
Q14005 D 2063120071 A 15936325 NA
Q918 C 2063217449 A 15936326 High positive
Q150248 C 2068796814 A 15936327 High positive
Q866 C 2079749157 A 15936328 High positive
Q477675 C 2080785713 A 15936329 High positive
Q1967876 C 2084215818 A 15936330 High positive
Q750403 C 2084693498 A 15936331 High positive
Q355 C 2093900731 A 15936332 High positive
Q623578 C 2097991400 A 15936333 High positive
Q17299517 D 2105487660 A 15936334 NA
Q33999 C 2108672678 A 15936335 High positive
Q2494649 C 2114531894 A 15936336 High positive
Q2597810 C 2128920607 A 15936337 High positive
Q193563 C 2130725560 A 15936338 High positive
Q423048 C 2136131564 A 15936339 High positive
Q37312 C 2142913121 A 15936340 High positive
Q54919 C 2148531382 A 15936341 High positive
Q36578 C 2229315598 A 15936342 High positive
Q30 A 2277746226 A 15936343 None
Q6581097 C 3273952711 A 15936344 High positive
Q5 A 5668008721 A 15936345 None
Q5296 C 12530369761 A 15936346 High positive
entity_id prediction page_views pop_class seqNum dissonance
Q10040378 E 0 E 1 NA
Q10069140 E 0 E 2 NA
Q10081695 E 0 E 3 NA
Q10092002 E 0 E 4 NA
Q10111267 E 0 E 5 NA
Q10149726 E 0 E 6 NA
Q10180230 E 0 E 7 NA
Q10185035 E 0 E 8 NA
Q10205202 E 0 E 9 NA
Q10252966 E 0 E 10 NA
Q10444494 D 0 E 11 Moderate negative
Q10624171 D 0 E 12 Moderate negative
Q10704108 D 0 E 13 Moderate negative
Q10750354 E 0 E 14 NA
Q10766855 E 0 E 15 NA
Q10827611 E 0 E 16 NA
Q11093044 E 0 E 17 NA
Q11934537 E 0 E 18 NA
Q12133466 E 0 E 19 NA
Q12264503 E 0 E 20 NA
Q12267516 E 0 E 21 NA
Q12304084 E 0 E 22 NA
Q12443525 E 0 E 23 NA
Q12543904 E 0 E 24 NA
Q12890205 E 0 E 25 NA
Q12891524 E 0 E 26 NA
Q12918202 E 0 E 27 NA
Q13005653 E 0 E 28 NA
Q13073896 E 0 E 29 NA
Q13163823 E 0 E 30 NA
⋮ ⋮ ⋮ ⋮ ⋮ ⋮
Q1048694 C 2048095025 A 15936317 High positive
Q31165 C 2048330818 A 15936318 High positive
Q40629 C 2049755644 A 15936319 High positive
Q105584 C 2049926923 A 15936320 High positive
Q4584301 D 2052339927 A 15936321 High positive
Q565 C 2052996261 A 15936322 High positive
Q1868372 E 2056080224 A 15936323 NA
Q209330 C 2060928966 A 15936324 High positive
Q14005 D 2063120071 A 15936325 High positive
Q918 C 2063217449 A 15936326 High positive
Q150248 C 2068796814 A 15936327 High positive
Q866 C 2079749157 A 15936328 High positive
Q477675 C 2080785713 A 15936329 High positive
Q1967876 C 2084215818 A 15936330 High positive
Q750403 C 2084693498 A 15936331 High positive
Q355 C 2093900731 A 15936332 High positive
Q623578 C 2097991400 A 15936333 High positive
Q17299517 D 2105487660 A 15936334 High positive
Q33999 C 2108672678 A 15936335 High positive
Q2494649 C 2114531894 A 15936336 High positive
Q2597810 C 2128920607 A 15936337 High positive
Q193563 C 2130725560 A 15936338 High positive
Q423048 C 2136131564 A 15936339 High positive
Q37312 C 2142913121 A 15936340 High positive
Q54919 C 2148531382 A 15936341 High positive
Q36578 C 2229315598 A 15936342 High positive
Q30 A 2277746226 A 15936343 None
Q6581097 C 3273952711 A 15936344 High positive
Q5 A 5668008721 A 15936345 None
Q5296 C 12530369761 A 15936346 High positive
In [38]:
## E
articles_by_pop[prediction == 'E' & pop_class == 'E',
dissonance := 'None'];
articles_by_pop[prediction == 'E' & pop_class == 'D',
dissonance := 'Moderate positive'];
articles_by_pop[prediction == 'E' & pop_class >= 'C',
dissonance := 'High positive'];
entity_id prediction page_views pop_class seqNum dissonance
Q10040378 E 0 E 1 None
Q10069140 E 0 E 2 None
Q10081695 E 0 E 3 None
Q10092002 E 0 E 4 None
Q10111267 E 0 E 5 None
Q10149726 E 0 E 6 None
Q10180230 E 0 E 7 None
Q10185035 E 0 E 8 None
Q10205202 E 0 E 9 None
Q10252966 E 0 E 10 None
Q10444494 D 0 E 11 Moderate negative
Q10624171 D 0 E 12 Moderate negative
Q10704108 D 0 E 13 Moderate negative
Q10750354 E 0 E 14 None
Q10766855 E 0 E 15 None
Q10827611 E 0 E 16 None
Q11093044 E 0 E 17 None
Q11934537 E 0 E 18 None
Q12133466 E 0 E 19 None
Q12264503 E 0 E 20 None
Q12267516 E 0 E 21 None
Q12304084 E 0 E 22 None
Q12443525 E 0 E 23 None
Q12543904 E 0 E 24 None
Q12890205 E 0 E 25 None
Q12891524 E 0 E 26 None
Q12918202 E 0 E 27 None
Q13005653 E 0 E 28 None
Q13073896 E 0 E 29 None
Q13163823 E 0 E 30 None
⋮ ⋮ ⋮ ⋮ ⋮ ⋮
Q1048694 C 2048095025 A 15936317 High positive
Q31165 C 2048330818 A 15936318 High positive
Q40629 C 2049755644 A 15936319 High positive
Q105584 C 2049926923 A 15936320 High positive
Q4584301 D 2052339927 A 15936321 High positive
Q565 C 2052996261 A 15936322 High positive
Q1868372 E 2056080224 A 15936323 NA
Q209330 C 2060928966 A 15936324 High positive
Q14005 D 2063120071 A 15936325 High positive
Q918 C 2063217449 A 15936326 High positive
Q150248 C 2068796814 A 15936327 High positive
Q866 C 2079749157 A 15936328 High positive
Q477675 C 2080785713 A 15936329 High positive
Q1967876 C 2084215818 A 15936330 High positive
Q750403 C 2084693498 A 15936331 High positive
Q355 C 2093900731 A 15936332 High positive
Q623578 C 2097991400 A 15936333 High positive
Q17299517 D 2105487660 A 15936334 High positive
Q33999 C 2108672678 A 15936335 High positive
Q2494649 C 2114531894 A 15936336 High positive
Q2597810 C 2128920607 A 15936337 High positive
Q193563 C 2130725560 A 15936338 High positive
Q423048 C 2136131564 A 15936339 High positive
Q37312 C 2142913121 A 15936340 High positive
Q54919 C 2148531382 A 15936341 High positive
Q36578 C 2229315598 A 15936342 High positive
Q30 A 2277746226 A 15936343 None
Q6581097 C 3273952711 A 15936344 High positive
Q5 A 5668008721 A 15936345 None
Q5296 C 12530369761 A 15936346 High positive
entity_id prediction page_views pop_class seqNum dissonance
Q10040378 E 0 E 1 None
Q10069140 E 0 E 2 None
Q10081695 E 0 E 3 None
Q10092002 E 0 E 4 None
Q10111267 E 0 E 5 None
Q10149726 E 0 E 6 None
Q10180230 E 0 E 7 None
Q10185035 E 0 E 8 None
Q10205202 E 0 E 9 None
Q10252966 E 0 E 10 None
Q10444494 D 0 E 11 Moderate negative
Q10624171 D 0 E 12 Moderate negative
Q10704108 D 0 E 13 Moderate negative
Q10750354 E 0 E 14 None
Q10766855 E 0 E 15 None
Q10827611 E 0 E 16 None
Q11093044 E 0 E 17 None
Q11934537 E 0 E 18 None
Q12133466 E 0 E 19 None
Q12264503 E 0 E 20 None
Q12267516 E 0 E 21 None
Q12304084 E 0 E 22 None
Q12443525 E 0 E 23 None
Q12543904 E 0 E 24 None
Q12890205 E 0 E 25 None
Q12891524 E 0 E 26 None
Q12918202 E 0 E 27 None
Q13005653 E 0 E 28 None
Q13073896 E 0 E 29 None
Q13163823 E 0 E 30 None
⋮ ⋮ ⋮ ⋮ ⋮ ⋮
Q1048694 C 2048095025 A 15936317 High positive
Q31165 C 2048330818 A 15936318 High positive
Q40629 C 2049755644 A 15936319 High positive
Q105584 C 2049926923 A 15936320 High positive
Q4584301 D 2052339927 A 15936321 High positive
Q565 C 2052996261 A 15936322 High positive
Q1868372 E 2056080224 A 15936323 NA
Q209330 C 2060928966 A 15936324 High positive
Q14005 D 2063120071 A 15936325 High positive
Q918 C 2063217449 A 15936326 High positive
Q150248 C 2068796814 A 15936327 High positive
Q866 C 2079749157 A 15936328 High positive
Q477675 C 2080785713 A 15936329 High positive
Q1967876 C 2084215818 A 15936330 High positive
Q750403 C 2084693498 A 15936331 High positive
Q355 C 2093900731 A 15936332 High positive
Q623578 C 2097991400 A 15936333 High positive
Q17299517 D 2105487660 A 15936334 High positive
Q33999 C 2108672678 A 15936335 High positive
Q2494649 C 2114531894 A 15936336 High positive
Q2597810 C 2128920607 A 15936337 High positive
Q193563 C 2130725560 A 15936338 High positive
Q423048 C 2136131564 A 15936339 High positive
Q37312 C 2142913121 A 15936340 High positive
Q54919 C 2148531382 A 15936341 High positive
Q36578 C 2229315598 A 15936342 High positive
Q30 A 2277746226 A 15936343 None
Q6581097 C 3273952711 A 15936344 High positive
Q5 A 5668008721 A 15936345 None
Q5296 C 12530369761 A 15936346 High positive
entity_id prediction page_views pop_class seqNum dissonance
Q10040378 E 0 E 1 None
Q10069140 E 0 E 2 None
Q10081695 E 0 E 3 None
Q10092002 E 0 E 4 None
Q10111267 E 0 E 5 None
Q10149726 E 0 E 6 None
Q10180230 E 0 E 7 None
Q10185035 E 0 E 8 None
Q10205202 E 0 E 9 None
Q10252966 E 0 E 10 None
Q10444494 D 0 E 11 Moderate negative
Q10624171 D 0 E 12 Moderate negative
Q10704108 D 0 E 13 Moderate negative
Q10750354 E 0 E 14 None
Q10766855 E 0 E 15 None
Q10827611 E 0 E 16 None
Q11093044 E 0 E 17 None
Q11934537 E 0 E 18 None
Q12133466 E 0 E 19 None
Q12264503 E 0 E 20 None
Q12267516 E 0 E 21 None
Q12304084 E 0 E 22 None
Q12443525 E 0 E 23 None
Q12543904 E 0 E 24 None
Q12890205 E 0 E 25 None
Q12891524 E 0 E 26 None
Q12918202 E 0 E 27 None
Q13005653 E 0 E 28 None
Q13073896 E 0 E 29 None
Q13163823 E 0 E 30 None
⋮ ⋮ ⋮ ⋮ ⋮ ⋮
Q1048694 C 2048095025 A 15936317 High positive
Q31165 C 2048330818 A 15936318 High positive
Q40629 C 2049755644 A 15936319 High positive
Q105584 C 2049926923 A 15936320 High positive
Q4584301 D 2052339927 A 15936321 High positive
Q565 C 2052996261 A 15936322 High positive
Q1868372 E 2056080224 A 15936323 High positive
Q209330 C 2060928966 A 15936324 High positive
Q14005 D 2063120071 A 15936325 High positive
Q918 C 2063217449 A 15936326 High positive
Q150248 C 2068796814 A 15936327 High positive
Q866 C 2079749157 A 15936328 High positive
Q477675 C 2080785713 A 15936329 High positive
Q1967876 C 2084215818 A 15936330 High positive
Q750403 C 2084693498 A 15936331 High positive
Q355 C 2093900731 A 15936332 High positive
Q623578 C 2097991400 A 15936333 High positive
Q17299517 D 2105487660 A 15936334 High positive
Q33999 C 2108672678 A 15936335 High positive
Q2494649 C 2114531894 A 15936336 High positive
Q2597810 C 2128920607 A 15936337 High positive
Q193563 C 2130725560 A 15936338 High positive
Q423048 C 2136131564 A 15936339 High positive
Q37312 C 2142913121 A 15936340 High positive
Q54919 C 2148531382 A 15936341 High positive
Q36578 C 2229315598 A 15936342 High positive
Q30 A 2277746226 A 15936343 None
Q6581097 C 3273952711 A 15936344 High positive
Q5 A 5668008721 A 15936345 None
Q5296 C 12530369761 A 15936346 High positive
In [39]:
## Build a matrix where columns are the metric and rows are classes
create_alt_diss_matrix = function(articledata, metric, classes) {
d_mtrx = matrix(0, nrow=length(classes), ncol=length(metric));
rownames(d_mtrx) = classes;
colnames(d_mtrx) = metric;
## NOTE: R matrix values are [row,col] dimensions
for(real_rating in classes) {
for(diss_rating in metric) {
d_mtrx[real_rating, diss_rating] = length(articledata[prediction == real_rating & dissonance == diss_rating]$entity_id);
}
}
d_mtrx;
}
alternative_dissonance_matrix.1 = create_alt_diss_matrix(articles_by_pop,
dissonance_metric, assessment_classes);
In [40]:
## Normalise by row
round(100*prop.table(alternative_dissonance_matrix.1, 1), 1);
High negative Moderate negative None Moderate positive High positive
E 0.0 0.0 72.5 19.2 8.3
D 0.0 74.0 16.7 9.2 0.2
C 40.9 28.9 28.6 1.6 0.0
B 50.4 45.0 4.5 0.0 0.0
A 10.3 87.4 2.3 0.0 0.0
In [41]:
## Number of dissonant views per assessment class and amount of dissonance
articles_by_pop[, list(dissonant_views=sum(page_views)), by=list(prediction, dissonance)];
prediction dissonance dissonant_views
E None 1742892963
D Moderate negative 383587534
C High negative 210542385
B High negative 42563805
E Moderate positive 6073386089
C Moderate negative 1597131601
D None 1531268726
A High negative 2763748
C None 44483736592
E High positive 99100387449
D Moderate positive 18020632360
B Moderate negative 1945297826
C Moderate positive 123835495968
D High positive 74475704181
B None 6103111220
A Moderate negative 5047163563
C High positive 123291694252
A None 7945754947
In [42]:
## Calculations of total number of dissonant views per dissonance
articles_by_pop[, list(dissonant_views=sum(page_views)), by=list(dissonance)];
dissonance dissonant_views
None 61806764448
Moderate negative 8973180524
High negative 255869938
Moderate positive 147929514417
High positive 296867785882
In [43]:
articles_by_pop[,sum(as.numeric(page_views))];
515833115209
In [44]:
## Proportions
100*65938379920/545180810059;
100*125047198/545180810059;
100*6713682043/545180810059;
100*120523625541/545180810059;
100*351880075357/545180810059;
12.0947727255594
0.0229368304409811
1.23145971375505
22.107092420945
64.5437383092995
In [45]:
# 87% of views are high positive
In [46]:
100*(articles_by_pop[, list(dissonant_views=sum(page_views)), by=list(dissonance)][1][,c('dissonant_views')]/articles_by_pop[,sum(as.numeric(page_views))])
dissonant_views
11.98193
In [47]:
100*(articles_by_pop[, list(dissonant_views=sum(page_views)), by=list(dissonance)][2][,c('dissonant_views')]/articles_by_pop[,sum(as.numeric(page_views))])
dissonant_views
1.739551
In [48]:
100*(articles_by_pop[, list(dissonant_views=sum(page_views)), by=list(dissonance)][3][,c('dissonant_views')]/articles_by_pop[,sum(as.numeric(page_views))])
dissonant_views
0.04960324
In [49]:
100*(articles_by_pop[, list(dissonant_views=sum(page_views)), by=list(dissonance)][4][,c('dissonant_views')]/articles_by_pop[,sum(as.numeric(page_views))])
dissonant_views
28.67779
In [50]:
100*(articles_by_pop[, list(dissonant_views=sum(page_views)), by=list(dissonance)][5][,c('dissonant_views')]/articles_by_pop[,sum(as.numeric(page_views))])
dissonant_views
57.55113
Content source: hall1467/wikidata_usage_tracking
Similar notebooks: