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_20130201.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 C: 1920
Q100 : 1 1st Qu.: 14.00 1st Qu.:2.710e+02 D: 201964
Q1000 : 1 Median : 28.00 Median :1.437e+03 E:3394634
Q10000 : 1 Mean : 36.24 Mean :1.102e+05
Q100000 : 1 3rd Qu.: 47.00 3rd Qu.:8.824e+03
Q1000000: 1 Max. :3364.00 Max. :1.253e+10
(Other) :3598512
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
Q3822211 E 0
Q3456322 E 0
Q3807084 E 0
Q3911232 E 0
Q2727432 E 0
Q3559277 E 0
Q2107007 E 0
Q2763928 E 0
Q2633768 E 0
Q3732410 E 0
Q1491146 E 0
Q3543307 E 0
Q3694340 E 0
Q3732853 E 0
Q2000513 E 0
Q2840622 E 0
Q3562813 E 0
Q3791515 E 0
Q2676015 E 0
Q1592439 E 0
Q2827819 E 0
Q157851 E 0
Q3012022 E 0
Q3695862 E 0
Q2775238 E 0
Q3867355 E 0
Q2768542 E 0
Q2722863 E 0
Q2483188 E 0
Q2769385 E 0
⋮ ⋮ ⋮ ⋮
Q356 D 2047631596
Q829984 E 2047695596
Q384060 E 2047954248
Q1048694 E 2048095025
Q31165 E 2048330818
Q40629 E 2049755644
Q105584 E 2049926923
Q565 D 2052996261
Q1868372 E 2056080224
Q209330 E 2060928966
Q14005 D 2063120071
Q918 D 2063217449
Q150248 E 2068796814
Q866 D 2079749157
Q477675 E 2080785713
Q1967876 E 2084215818
Q750403 E 2084693498
Q355 D 2093900731
Q623578 E 2097991400
Q33999 E 2108672678
Q2494649 E 2114531894
Q2597810 E 2128920607
Q193563 E 2130725560
Q423048 E 2136131564
Q37312 E 2142913121
Q54919 D 2148531382
Q36578 D 2229315598
Q30 C 2277746226
Q5 C 5668008721
Q5296 D 12530369761
entity_id prediction page_views pop_class seqNum
Q3822211 E 0 1
Q3456322 E 0 2
Q3807084 E 0 3
Q3911232 E 0 4
Q2727432 E 0 5
Q3559277 E 0 6
Q2107007 E 0 7
Q2763928 E 0 8
Q2633768 E 0 9
Q3732410 E 0 10
Q1491146 E 0 11
Q3543307 E 0 12
Q3694340 E 0 13
Q3732853 E 0 14
Q2000513 E 0 15
Q2840622 E 0 16
Q3562813 E 0 17
Q3791515 E 0 18
Q2676015 E 0 19
Q1592439 E 0 20
Q2827819 E 0 21
Q157851 E 0 22
Q3012022 E 0 23
Q3695862 E 0 24
Q2775238 E 0 25
Q3867355 E 0 26
Q2768542 E 0 27
Q2722863 E 0 28
Q2483188 E 0 29
Q2769385 E 0 30
⋮ ⋮ ⋮ ⋮ ⋮
Q356 D 2047631596 3598489
Q829984 E 2047695596 3598490
Q384060 E 2047954248 3598491
Q1048694 E 2048095025 3598492
Q31165 E 2048330818 3598493
Q40629 E 2049755644 3598494
Q105584 E 2049926923 3598495
Q565 D 2052996261 3598496
Q1868372 E 2056080224 3598497
Q209330 E 2060928966 3598498
Q14005 D 2063120071 3598499
Q918 D 2063217449 3598500
Q150248 E 2068796814 3598501
Q866 D 2079749157 3598502
Q477675 E 2080785713 3598503
Q1967876 E 2084215818 3598504
Q750403 E 2084693498 3598505
Q355 D 2093900731 3598506
Q623578 E 2097991400 3598507
Q33999 E 2108672678 3598508
Q2494649 E 2114531894 3598509
Q2597810 E 2128920607 3598510
Q193563 E 2130725560 3598511
Q423048 E 2136131564 3598512
Q37312 E 2142913121 3598513
Q54919 D 2148531382 3598514
Q36578 D 2229315598 3598515
Q30 C 2277746226 3598516
Q5 C 5668008721 3598517
Q5296 D 12530369761 3598518
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]$narticles;
print(paste('start_idx =', start_idx, ', end_idx = ', end_idx));
dataset[seqNum >= start_idx & seqNum <= end_idx, pop_class := rating];
prev_idx = end_idx -1;
}
dataset;
}
In [13]:
articles_by_pop = assign_pop_class(articles_by_pop,
assessment_classes, n_per_class);
[1] "start_idx = 1 , end_idx = 3394635"
[1] "start_idx = 3394635 , end_idx = 3596599"
[1] "start_idx = 3596599 , end_idx = 3598519"
[1] "start_idx = 3598519 , end_idx = "
[1] "start_idx = , end_idx = "
In [14]:
create_dissonance_matrix = function(articledata, classes) {
d_mtrx = matrix(0, nrow=length(classes), ncol=length(classes));
rownames(d_mtrx) = classes;
colnames(d_mtrx) = classes;
for(real_rating in classes) {
for(pop_rating in classes) {
d_mtrx[real_rating, pop_rating] = length(articledata[prediction == real_rating & pop_class == pop_rating]$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 3212382 181165 1087 0 0
D 181022 20138 804 0 0
C 1230 661 29 0 0
B 0 0 0 0 0
A 0 0 0 0 0
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[,])
0.898300077976545
In [18]:
# A class quality and A class views over A class quality
dissonance_matrix[5,5]/sum(dissonance_matrix[5,])
NaN
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,])
NaN
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,])
NaN
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])
NaN
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
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 94.6 5.3 0.0 0 0
D 89.6 10.0 0.4 0 0
C 64.1 34.4 1.5 0 0
B NaN NaN NaN NaN NaN
A NaN NaN NaN NaN NaN
In [26]:
round(100*prop.table(dissonance_matrix, 2), 1);
E D C B A
E 94.6 89.7 56.6 NaN NaN
D 5.3 10.0 41.9 NaN NaN
C 0.0 0.3 1.5 NaN NaN
B 0.0 0.0 0.0 NaN NaN
A 0.0 0.0 0.0 NaN NaN
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/201302_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
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/201302_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/201302_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/201302_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
Q3822211 E 0 E 1
Q3456322 E 0 E 2
Q3807084 E 0 E 3
Q3911232 E 0 E 4
Q2727432 E 0 E 5
Q3559277 E 0 E 6
Q2107007 E 0 E 7
Q2763928 E 0 E 8
Q2633768 E 0 E 9
Q3732410 E 0 E 10
Q1491146 E 0 E 11
Q3543307 E 0 E 12
Q3694340 E 0 E 13
Q3732853 E 0 E 14
Q2000513 E 0 E 15
Q2840622 E 0 E 16
Q3562813 E 0 E 17
Q3791515 E 0 E 18
Q2676015 E 0 E 19
Q1592439 E 0 E 20
Q2827819 E 0 E 21
Q157851 E 0 E 22
Q3012022 E 0 E 23
Q3695862 E 0 E 24
Q2775238 E 0 E 25
Q3867355 E 0 E 26
Q2768542 E 0 E 27
Q2722863 E 0 E 28
Q2483188 E 0 E 29
Q2769385 E 0 E 30
⋮ ⋮ ⋮ ⋮ ⋮
Q356 D 2047631596 C 3598489
Q829984 E 2047695596 C 3598490
Q384060 E 2047954248 C 3598491
Q1048694 E 2048095025 C 3598492
Q31165 E 2048330818 C 3598493
Q40629 E 2049755644 C 3598494
Q105584 E 2049926923 C 3598495
Q565 D 2052996261 C 3598496
Q1868372 E 2056080224 C 3598497
Q209330 E 2060928966 C 3598498
Q14005 D 2063120071 C 3598499
Q918 D 2063217449 C 3598500
Q150248 E 2068796814 C 3598501
Q866 D 2079749157 C 3598502
Q477675 E 2080785713 C 3598503
Q1967876 E 2084215818 C 3598504
Q750403 E 2084693498 C 3598505
Q355 D 2093900731 C 3598506
Q623578 E 2097991400 C 3598507
Q33999 E 2108672678 C 3598508
Q2494649 E 2114531894 C 3598509
Q2597810 E 2128920607 C 3598510
Q193563 E 2130725560 C 3598511
Q423048 E 2136131564 C 3598512
Q37312 E 2142913121 C 3598513
Q54919 D 2148531382 C 3598514
Q36578 D 2229315598 C 3598515
Q30 C 2277746226 C 3598516
Q5 C 5668008721 C 3598517
Q5296 D 12530369761 C 3598518
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
Q3822211 E 0 E 1 NA
Q3456322 E 0 E 2 NA
Q3807084 E 0 E 3 NA
Q3911232 E 0 E 4 NA
Q2727432 E 0 E 5 NA
Q3559277 E 0 E 6 NA
Q2107007 E 0 E 7 NA
Q2763928 E 0 E 8 NA
Q2633768 E 0 E 9 NA
Q3732410 E 0 E 10 NA
Q1491146 E 0 E 11 NA
Q3543307 E 0 E 12 NA
Q3694340 E 0 E 13 NA
Q3732853 E 0 E 14 NA
Q2000513 E 0 E 15 NA
Q2840622 E 0 E 16 NA
Q3562813 E 0 E 17 NA
Q3791515 E 0 E 18 NA
Q2676015 E 0 E 19 NA
Q1592439 E 0 E 20 NA
Q2827819 E 0 E 21 NA
Q157851 E 0 E 22 NA
Q3012022 E 0 E 23 NA
Q3695862 E 0 E 24 NA
Q2775238 E 0 E 25 NA
Q3867355 E 0 E 26 NA
Q2768542 E 0 E 27 NA
Q2722863 E 0 E 28 NA
Q2483188 E 0 E 29 NA
Q2769385 E 0 E 30 NA
⋮ ⋮ ⋮ ⋮ ⋮ ⋮
Q356 D 2047631596 C 3598489 NA
Q829984 E 2047695596 C 3598490 NA
Q384060 E 2047954248 C 3598491 NA
Q1048694 E 2048095025 C 3598492 NA
Q31165 E 2048330818 C 3598493 NA
Q40629 E 2049755644 C 3598494 NA
Q105584 E 2049926923 C 3598495 NA
Q565 D 2052996261 C 3598496 NA
Q1868372 E 2056080224 C 3598497 NA
Q209330 E 2060928966 C 3598498 NA
Q14005 D 2063120071 C 3598499 NA
Q918 D 2063217449 C 3598500 NA
Q150248 E 2068796814 C 3598501 NA
Q866 D 2079749157 C 3598502 NA
Q477675 E 2080785713 C 3598503 NA
Q1967876 E 2084215818 C 3598504 NA
Q750403 E 2084693498 C 3598505 NA
Q355 D 2093900731 C 3598506 NA
Q623578 E 2097991400 C 3598507 NA
Q33999 E 2108672678 C 3598508 NA
Q2494649 E 2114531894 C 3598509 NA
Q2597810 E 2128920607 C 3598510 NA
Q193563 E 2130725560 C 3598511 NA
Q423048 E 2136131564 C 3598512 NA
Q37312 E 2142913121 C 3598513 NA
Q54919 D 2148531382 C 3598514 NA
Q36578 D 2229315598 C 3598515 NA
Q30 C 2277746226 C 3598516 NA
Q5 C 5668008721 C 3598517 NA
Q5296 D 12530369761 C 3598518 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
Q3822211 E 0 E 1 NA
Q3456322 E 0 E 2 NA
Q3807084 E 0 E 3 NA
Q3911232 E 0 E 4 NA
Q2727432 E 0 E 5 NA
Q3559277 E 0 E 6 NA
Q2107007 E 0 E 7 NA
Q2763928 E 0 E 8 NA
Q2633768 E 0 E 9 NA
Q3732410 E 0 E 10 NA
Q1491146 E 0 E 11 NA
Q3543307 E 0 E 12 NA
Q3694340 E 0 E 13 NA
Q3732853 E 0 E 14 NA
Q2000513 E 0 E 15 NA
Q2840622 E 0 E 16 NA
Q3562813 E 0 E 17 NA
Q3791515 E 0 E 18 NA
Q2676015 E 0 E 19 NA
Q1592439 E 0 E 20 NA
Q2827819 E 0 E 21 NA
Q157851 E 0 E 22 NA
Q3012022 E 0 E 23 NA
Q3695862 E 0 E 24 NA
Q2775238 E 0 E 25 NA
Q3867355 E 0 E 26 NA
Q2768542 E 0 E 27 NA
Q2722863 E 0 E 28 NA
Q2483188 E 0 E 29 NA
Q2769385 E 0 E 30 NA
⋮ ⋮ ⋮ ⋮ ⋮ ⋮
Q356 D 2047631596 C 3598489 NA
Q829984 E 2047695596 C 3598490 NA
Q384060 E 2047954248 C 3598491 NA
Q1048694 E 2048095025 C 3598492 NA
Q31165 E 2048330818 C 3598493 NA
Q40629 E 2049755644 C 3598494 NA
Q105584 E 2049926923 C 3598495 NA
Q565 D 2052996261 C 3598496 NA
Q1868372 E 2056080224 C 3598497 NA
Q209330 E 2060928966 C 3598498 NA
Q14005 D 2063120071 C 3598499 NA
Q918 D 2063217449 C 3598500 NA
Q150248 E 2068796814 C 3598501 NA
Q866 D 2079749157 C 3598502 NA
Q477675 E 2080785713 C 3598503 NA
Q1967876 E 2084215818 C 3598504 NA
Q750403 E 2084693498 C 3598505 NA
Q355 D 2093900731 C 3598506 NA
Q623578 E 2097991400 C 3598507 NA
Q33999 E 2108672678 C 3598508 NA
Q2494649 E 2114531894 C 3598509 NA
Q2597810 E 2128920607 C 3598510 NA
Q193563 E 2130725560 C 3598511 NA
Q423048 E 2136131564 C 3598512 NA
Q37312 E 2142913121 C 3598513 NA
Q54919 D 2148531382 C 3598514 NA
Q36578 D 2229315598 C 3598515 NA
Q30 C 2277746226 C 3598516 NA
Q5 C 5668008721 C 3598517 NA
Q5296 D 12530369761 C 3598518 NA
entity_id prediction page_views pop_class seqNum dissonance
Q3822211 E 0 E 1 NA
Q3456322 E 0 E 2 NA
Q3807084 E 0 E 3 NA
Q3911232 E 0 E 4 NA
Q2727432 E 0 E 5 NA
Q3559277 E 0 E 6 NA
Q2107007 E 0 E 7 NA
Q2763928 E 0 E 8 NA
Q2633768 E 0 E 9 NA
Q3732410 E 0 E 10 NA
Q1491146 E 0 E 11 NA
Q3543307 E 0 E 12 NA
Q3694340 E 0 E 13 NA
Q3732853 E 0 E 14 NA
Q2000513 E 0 E 15 NA
Q2840622 E 0 E 16 NA
Q3562813 E 0 E 17 NA
Q3791515 E 0 E 18 NA
Q2676015 E 0 E 19 NA
Q1592439 E 0 E 20 NA
Q2827819 E 0 E 21 NA
Q157851 E 0 E 22 NA
Q3012022 E 0 E 23 NA
Q3695862 E 0 E 24 NA
Q2775238 E 0 E 25 NA
Q3867355 E 0 E 26 NA
Q2768542 E 0 E 27 NA
Q2722863 E 0 E 28 NA
Q2483188 E 0 E 29 NA
Q2769385 E 0 E 30 NA
⋮ ⋮ ⋮ ⋮ ⋮ ⋮
Q356 D 2047631596 C 3598489 NA
Q829984 E 2047695596 C 3598490 NA
Q384060 E 2047954248 C 3598491 NA
Q1048694 E 2048095025 C 3598492 NA
Q31165 E 2048330818 C 3598493 NA
Q40629 E 2049755644 C 3598494 NA
Q105584 E 2049926923 C 3598495 NA
Q565 D 2052996261 C 3598496 NA
Q1868372 E 2056080224 C 3598497 NA
Q209330 E 2060928966 C 3598498 NA
Q14005 D 2063120071 C 3598499 NA
Q918 D 2063217449 C 3598500 NA
Q150248 E 2068796814 C 3598501 NA
Q866 D 2079749157 C 3598502 NA
Q477675 E 2080785713 C 3598503 NA
Q1967876 E 2084215818 C 3598504 NA
Q750403 E 2084693498 C 3598505 NA
Q355 D 2093900731 C 3598506 NA
Q623578 E 2097991400 C 3598507 NA
Q33999 E 2108672678 C 3598508 NA
Q2494649 E 2114531894 C 3598509 NA
Q2597810 E 2128920607 C 3598510 NA
Q193563 E 2130725560 C 3598511 NA
Q423048 E 2136131564 C 3598512 NA
Q37312 E 2142913121 C 3598513 NA
Q54919 D 2148531382 C 3598514 NA
Q36578 D 2229315598 C 3598515 NA
Q30 C 2277746226 C 3598516 NA
Q5 C 5668008721 C 3598517 NA
Q5296 D 12530369761 C 3598518 NA
entity_id prediction page_views pop_class seqNum dissonance
Q3822211 E 0 E 1 NA
Q3456322 E 0 E 2 NA
Q3807084 E 0 E 3 NA
Q3911232 E 0 E 4 NA
Q2727432 E 0 E 5 NA
Q3559277 E 0 E 6 NA
Q2107007 E 0 E 7 NA
Q2763928 E 0 E 8 NA
Q2633768 E 0 E 9 NA
Q3732410 E 0 E 10 NA
Q1491146 E 0 E 11 NA
Q3543307 E 0 E 12 NA
Q3694340 E 0 E 13 NA
Q3732853 E 0 E 14 NA
Q2000513 E 0 E 15 NA
Q2840622 E 0 E 16 NA
Q3562813 E 0 E 17 NA
Q3791515 E 0 E 18 NA
Q2676015 E 0 E 19 NA
Q1592439 E 0 E 20 NA
Q2827819 E 0 E 21 NA
Q157851 E 0 E 22 NA
Q3012022 E 0 E 23 NA
Q3695862 E 0 E 24 NA
Q2775238 E 0 E 25 NA
Q3867355 E 0 E 26 NA
Q2768542 E 0 E 27 NA
Q2722863 E 0 E 28 NA
Q2483188 E 0 E 29 NA
Q2769385 E 0 E 30 NA
⋮ ⋮ ⋮ ⋮ ⋮ ⋮
Q356 D 2047631596 C 3598489 NA
Q829984 E 2047695596 C 3598490 NA
Q384060 E 2047954248 C 3598491 NA
Q1048694 E 2048095025 C 3598492 NA
Q31165 E 2048330818 C 3598493 NA
Q40629 E 2049755644 C 3598494 NA
Q105584 E 2049926923 C 3598495 NA
Q565 D 2052996261 C 3598496 NA
Q1868372 E 2056080224 C 3598497 NA
Q209330 E 2060928966 C 3598498 NA
Q14005 D 2063120071 C 3598499 NA
Q918 D 2063217449 C 3598500 NA
Q150248 E 2068796814 C 3598501 NA
Q866 D 2079749157 C 3598502 NA
Q477675 E 2080785713 C 3598503 NA
Q1967876 E 2084215818 C 3598504 NA
Q750403 E 2084693498 C 3598505 NA
Q355 D 2093900731 C 3598506 NA
Q623578 E 2097991400 C 3598507 NA
Q33999 E 2108672678 C 3598508 NA
Q2494649 E 2114531894 C 3598509 NA
Q2597810 E 2128920607 C 3598510 NA
Q193563 E 2130725560 C 3598511 NA
Q423048 E 2136131564 C 3598512 NA
Q37312 E 2142913121 C 3598513 NA
Q54919 D 2148531382 C 3598514 NA
Q36578 D 2229315598 C 3598515 NA
Q30 C 2277746226 C 3598516 NA
Q5 C 5668008721 C 3598517 NA
Q5296 D 12530369761 C 3598518 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
Q3822211 E 0 E 1 NA
Q3456322 E 0 E 2 NA
Q3807084 E 0 E 3 NA
Q3911232 E 0 E 4 NA
Q2727432 E 0 E 5 NA
Q3559277 E 0 E 6 NA
Q2107007 E 0 E 7 NA
Q2763928 E 0 E 8 NA
Q2633768 E 0 E 9 NA
Q3732410 E 0 E 10 NA
Q1491146 E 0 E 11 NA
Q3543307 E 0 E 12 NA
Q3694340 E 0 E 13 NA
Q3732853 E 0 E 14 NA
Q2000513 E 0 E 15 NA
Q2840622 E 0 E 16 NA
Q3562813 E 0 E 17 NA
Q3791515 E 0 E 18 NA
Q2676015 E 0 E 19 NA
Q1592439 E 0 E 20 NA
Q2827819 E 0 E 21 NA
Q157851 E 0 E 22 NA
Q3012022 E 0 E 23 NA
Q3695862 E 0 E 24 NA
Q2775238 E 0 E 25 NA
Q3867355 E 0 E 26 NA
Q2768542 E 0 E 27 NA
Q2722863 E 0 E 28 NA
Q2483188 E 0 E 29 NA
Q2769385 E 0 E 30 NA
⋮ ⋮ ⋮ ⋮ ⋮ ⋮
Q356 D 2047631596 C 3598489 NA
Q829984 E 2047695596 C 3598490 NA
Q384060 E 2047954248 C 3598491 NA
Q1048694 E 2048095025 C 3598492 NA
Q31165 E 2048330818 C 3598493 NA
Q40629 E 2049755644 C 3598494 NA
Q105584 E 2049926923 C 3598495 NA
Q565 D 2052996261 C 3598496 NA
Q1868372 E 2056080224 C 3598497 NA
Q209330 E 2060928966 C 3598498 NA
Q14005 D 2063120071 C 3598499 NA
Q918 D 2063217449 C 3598500 NA
Q150248 E 2068796814 C 3598501 NA
Q866 D 2079749157 C 3598502 NA
Q477675 E 2080785713 C 3598503 NA
Q1967876 E 2084215818 C 3598504 NA
Q750403 E 2084693498 C 3598505 NA
Q355 D 2093900731 C 3598506 NA
Q623578 E 2097991400 C 3598507 NA
Q33999 E 2108672678 C 3598508 NA
Q2494649 E 2114531894 C 3598509 NA
Q2597810 E 2128920607 C 3598510 NA
Q193563 E 2130725560 C 3598511 NA
Q423048 E 2136131564 C 3598512 NA
Q37312 E 2142913121 C 3598513 NA
Q54919 D 2148531382 C 3598514 NA
Q36578 D 2229315598 C 3598515 NA
Q30 C 2277746226 C 3598516 NA
Q5 C 5668008721 C 3598517 NA
Q5296 D 12530369761 C 3598518 NA
entity_id prediction page_views pop_class seqNum dissonance
Q3822211 E 0 E 1 NA
Q3456322 E 0 E 2 NA
Q3807084 E 0 E 3 NA
Q3911232 E 0 E 4 NA
Q2727432 E 0 E 5 NA
Q3559277 E 0 E 6 NA
Q2107007 E 0 E 7 NA
Q2763928 E 0 E 8 NA
Q2633768 E 0 E 9 NA
Q3732410 E 0 E 10 NA
Q1491146 E 0 E 11 NA
Q3543307 E 0 E 12 NA
Q3694340 E 0 E 13 NA
Q3732853 E 0 E 14 NA
Q2000513 E 0 E 15 NA
Q2840622 E 0 E 16 NA
Q3562813 E 0 E 17 NA
Q3791515 E 0 E 18 NA
Q2676015 E 0 E 19 NA
Q1592439 E 0 E 20 NA
Q2827819 E 0 E 21 NA
Q157851 E 0 E 22 NA
Q3012022 E 0 E 23 NA
Q3695862 E 0 E 24 NA
Q2775238 E 0 E 25 NA
Q3867355 E 0 E 26 NA
Q2768542 E 0 E 27 NA
Q2722863 E 0 E 28 NA
Q2483188 E 0 E 29 NA
Q2769385 E 0 E 30 NA
⋮ ⋮ ⋮ ⋮ ⋮ ⋮
Q356 D 2047631596 C 3598489 NA
Q829984 E 2047695596 C 3598490 NA
Q384060 E 2047954248 C 3598491 NA
Q1048694 E 2048095025 C 3598492 NA
Q31165 E 2048330818 C 3598493 NA
Q40629 E 2049755644 C 3598494 NA
Q105584 E 2049926923 C 3598495 NA
Q565 D 2052996261 C 3598496 NA
Q1868372 E 2056080224 C 3598497 NA
Q209330 E 2060928966 C 3598498 NA
Q14005 D 2063120071 C 3598499 NA
Q918 D 2063217449 C 3598500 NA
Q150248 E 2068796814 C 3598501 NA
Q866 D 2079749157 C 3598502 NA
Q477675 E 2080785713 C 3598503 NA
Q1967876 E 2084215818 C 3598504 NA
Q750403 E 2084693498 C 3598505 NA
Q355 D 2093900731 C 3598506 NA
Q623578 E 2097991400 C 3598507 NA
Q33999 E 2108672678 C 3598508 NA
Q2494649 E 2114531894 C 3598509 NA
Q2597810 E 2128920607 C 3598510 NA
Q193563 E 2130725560 C 3598511 NA
Q423048 E 2136131564 C 3598512 NA
Q37312 E 2142913121 C 3598513 NA
Q54919 D 2148531382 C 3598514 NA
Q36578 D 2229315598 C 3598515 NA
Q30 C 2277746226 C 3598516 NA
Q5 C 5668008721 C 3598517 NA
Q5296 D 12530369761 C 3598518 NA
entity_id prediction page_views pop_class seqNum dissonance
Q3822211 E 0 E 1 NA
Q3456322 E 0 E 2 NA
Q3807084 E 0 E 3 NA
Q3911232 E 0 E 4 NA
Q2727432 E 0 E 5 NA
Q3559277 E 0 E 6 NA
Q2107007 E 0 E 7 NA
Q2763928 E 0 E 8 NA
Q2633768 E 0 E 9 NA
Q3732410 E 0 E 10 NA
Q1491146 E 0 E 11 NA
Q3543307 E 0 E 12 NA
Q3694340 E 0 E 13 NA
Q3732853 E 0 E 14 NA
Q2000513 E 0 E 15 NA
Q2840622 E 0 E 16 NA
Q3562813 E 0 E 17 NA
Q3791515 E 0 E 18 NA
Q2676015 E 0 E 19 NA
Q1592439 E 0 E 20 NA
Q2827819 E 0 E 21 NA
Q157851 E 0 E 22 NA
Q3012022 E 0 E 23 NA
Q3695862 E 0 E 24 NA
Q2775238 E 0 E 25 NA
Q3867355 E 0 E 26 NA
Q2768542 E 0 E 27 NA
Q2722863 E 0 E 28 NA
Q2483188 E 0 E 29 NA
Q2769385 E 0 E 30 NA
⋮ ⋮ ⋮ ⋮ ⋮ ⋮
Q356 D 2047631596 C 3598489 NA
Q829984 E 2047695596 C 3598490 NA
Q384060 E 2047954248 C 3598491 NA
Q1048694 E 2048095025 C 3598492 NA
Q31165 E 2048330818 C 3598493 NA
Q40629 E 2049755644 C 3598494 NA
Q105584 E 2049926923 C 3598495 NA
Q565 D 2052996261 C 3598496 NA
Q1868372 E 2056080224 C 3598497 NA
Q209330 E 2060928966 C 3598498 NA
Q14005 D 2063120071 C 3598499 NA
Q918 D 2063217449 C 3598500 NA
Q150248 E 2068796814 C 3598501 NA
Q866 D 2079749157 C 3598502 NA
Q477675 E 2080785713 C 3598503 NA
Q1967876 E 2084215818 C 3598504 NA
Q750403 E 2084693498 C 3598505 NA
Q355 D 2093900731 C 3598506 NA
Q623578 E 2097991400 C 3598507 NA
Q33999 E 2108672678 C 3598508 NA
Q2494649 E 2114531894 C 3598509 NA
Q2597810 E 2128920607 C 3598510 NA
Q193563 E 2130725560 C 3598511 NA
Q423048 E 2136131564 C 3598512 NA
Q37312 E 2142913121 C 3598513 NA
Q54919 D 2148531382 C 3598514 NA
Q36578 D 2229315598 C 3598515 NA
Q30 C 2277746226 C 3598516 NA
Q5 C 5668008721 C 3598517 NA
Q5296 D 12530369761 C 3598518 NA
entity_id prediction page_views pop_class seqNum dissonance
Q3822211 E 0 E 1 NA
Q3456322 E 0 E 2 NA
Q3807084 E 0 E 3 NA
Q3911232 E 0 E 4 NA
Q2727432 E 0 E 5 NA
Q3559277 E 0 E 6 NA
Q2107007 E 0 E 7 NA
Q2763928 E 0 E 8 NA
Q2633768 E 0 E 9 NA
Q3732410 E 0 E 10 NA
Q1491146 E 0 E 11 NA
Q3543307 E 0 E 12 NA
Q3694340 E 0 E 13 NA
Q3732853 E 0 E 14 NA
Q2000513 E 0 E 15 NA
Q2840622 E 0 E 16 NA
Q3562813 E 0 E 17 NA
Q3791515 E 0 E 18 NA
Q2676015 E 0 E 19 NA
Q1592439 E 0 E 20 NA
Q2827819 E 0 E 21 NA
Q157851 E 0 E 22 NA
Q3012022 E 0 E 23 NA
Q3695862 E 0 E 24 NA
Q2775238 E 0 E 25 NA
Q3867355 E 0 E 26 NA
Q2768542 E 0 E 27 NA
Q2722863 E 0 E 28 NA
Q2483188 E 0 E 29 NA
Q2769385 E 0 E 30 NA
⋮ ⋮ ⋮ ⋮ ⋮ ⋮
Q356 D 2047631596 C 3598489 NA
Q829984 E 2047695596 C 3598490 NA
Q384060 E 2047954248 C 3598491 NA
Q1048694 E 2048095025 C 3598492 NA
Q31165 E 2048330818 C 3598493 NA
Q40629 E 2049755644 C 3598494 NA
Q105584 E 2049926923 C 3598495 NA
Q565 D 2052996261 C 3598496 NA
Q1868372 E 2056080224 C 3598497 NA
Q209330 E 2060928966 C 3598498 NA
Q14005 D 2063120071 C 3598499 NA
Q918 D 2063217449 C 3598500 NA
Q150248 E 2068796814 C 3598501 NA
Q866 D 2079749157 C 3598502 NA
Q477675 E 2080785713 C 3598503 NA
Q1967876 E 2084215818 C 3598504 NA
Q750403 E 2084693498 C 3598505 NA
Q355 D 2093900731 C 3598506 NA
Q623578 E 2097991400 C 3598507 NA
Q33999 E 2108672678 C 3598508 NA
Q2494649 E 2114531894 C 3598509 NA
Q2597810 E 2128920607 C 3598510 NA
Q193563 E 2130725560 C 3598511 NA
Q423048 E 2136131564 C 3598512 NA
Q37312 E 2142913121 C 3598513 NA
Q54919 D 2148531382 C 3598514 NA
Q36578 D 2229315598 C 3598515 NA
Q30 C 2277746226 C 3598516 NA
Q5 C 5668008721 C 3598517 NA
Q5296 D 12530369761 C 3598518 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
Q3822211 E 0 E 1 NA
Q3456322 E 0 E 2 NA
Q3807084 E 0 E 3 NA
Q3911232 E 0 E 4 NA
Q2727432 E 0 E 5 NA
Q3559277 E 0 E 6 NA
Q2107007 E 0 E 7 NA
Q2763928 E 0 E 8 NA
Q2633768 E 0 E 9 NA
Q3732410 E 0 E 10 NA
Q1491146 E 0 E 11 NA
Q3543307 E 0 E 12 NA
Q3694340 E 0 E 13 NA
Q3732853 E 0 E 14 NA
Q2000513 E 0 E 15 NA
Q2840622 E 0 E 16 NA
Q3562813 E 0 E 17 NA
Q3791515 E 0 E 18 NA
Q2676015 E 0 E 19 NA
Q1592439 E 0 E 20 NA
Q2827819 E 0 E 21 NA
Q157851 E 0 E 22 NA
Q3012022 E 0 E 23 NA
Q3695862 E 0 E 24 NA
Q2775238 E 0 E 25 NA
Q3867355 E 0 E 26 NA
Q2768542 E 0 E 27 NA
Q2722863 E 0 E 28 NA
Q2483188 E 0 E 29 NA
Q2769385 E 0 E 30 NA
⋮ ⋮ ⋮ ⋮ ⋮ ⋮
Q356 D 2047631596 C 3598489 NA
Q829984 E 2047695596 C 3598490 NA
Q384060 E 2047954248 C 3598491 NA
Q1048694 E 2048095025 C 3598492 NA
Q31165 E 2048330818 C 3598493 NA
Q40629 E 2049755644 C 3598494 NA
Q105584 E 2049926923 C 3598495 NA
Q565 D 2052996261 C 3598496 NA
Q1868372 E 2056080224 C 3598497 NA
Q209330 E 2060928966 C 3598498 NA
Q14005 D 2063120071 C 3598499 NA
Q918 D 2063217449 C 3598500 NA
Q150248 E 2068796814 C 3598501 NA
Q866 D 2079749157 C 3598502 NA
Q477675 E 2080785713 C 3598503 NA
Q1967876 E 2084215818 C 3598504 NA
Q750403 E 2084693498 C 3598505 NA
Q355 D 2093900731 C 3598506 NA
Q623578 E 2097991400 C 3598507 NA
Q33999 E 2108672678 C 3598508 NA
Q2494649 E 2114531894 C 3598509 NA
Q2597810 E 2128920607 C 3598510 NA
Q193563 E 2130725560 C 3598511 NA
Q423048 E 2136131564 C 3598512 NA
Q37312 E 2142913121 C 3598513 NA
Q54919 D 2148531382 C 3598514 NA
Q36578 D 2229315598 C 3598515 NA
Q30 C 2277746226 C 3598516 NA
Q5 C 5668008721 C 3598517 NA
Q5296 D 12530369761 C 3598518 NA
entity_id prediction page_views pop_class seqNum dissonance
Q3822211 E 0 E 1 NA
Q3456322 E 0 E 2 NA
Q3807084 E 0 E 3 NA
Q3911232 E 0 E 4 NA
Q2727432 E 0 E 5 NA
Q3559277 E 0 E 6 NA
Q2107007 E 0 E 7 NA
Q2763928 E 0 E 8 NA
Q2633768 E 0 E 9 NA
Q3732410 E 0 E 10 NA
Q1491146 E 0 E 11 NA
Q3543307 E 0 E 12 NA
Q3694340 E 0 E 13 NA
Q3732853 E 0 E 14 NA
Q2000513 E 0 E 15 NA
Q2840622 E 0 E 16 NA
Q3562813 E 0 E 17 NA
Q3791515 E 0 E 18 NA
Q2676015 E 0 E 19 NA
Q1592439 E 0 E 20 NA
Q2827819 E 0 E 21 NA
Q157851 E 0 E 22 NA
Q3012022 E 0 E 23 NA
Q3695862 E 0 E 24 NA
Q2775238 E 0 E 25 NA
Q3867355 E 0 E 26 NA
Q2768542 E 0 E 27 NA
Q2722863 E 0 E 28 NA
Q2483188 E 0 E 29 NA
Q2769385 E 0 E 30 NA
⋮ ⋮ ⋮ ⋮ ⋮ ⋮
Q356 D 2047631596 C 3598489 NA
Q829984 E 2047695596 C 3598490 NA
Q384060 E 2047954248 C 3598491 NA
Q1048694 E 2048095025 C 3598492 NA
Q31165 E 2048330818 C 3598493 NA
Q40629 E 2049755644 C 3598494 NA
Q105584 E 2049926923 C 3598495 NA
Q565 D 2052996261 C 3598496 NA
Q1868372 E 2056080224 C 3598497 NA
Q209330 E 2060928966 C 3598498 NA
Q14005 D 2063120071 C 3598499 NA
Q918 D 2063217449 C 3598500 NA
Q150248 E 2068796814 C 3598501 NA
Q866 D 2079749157 C 3598502 NA
Q477675 E 2080785713 C 3598503 NA
Q1967876 E 2084215818 C 3598504 NA
Q750403 E 2084693498 C 3598505 NA
Q355 D 2093900731 C 3598506 NA
Q623578 E 2097991400 C 3598507 NA
Q33999 E 2108672678 C 3598508 NA
Q2494649 E 2114531894 C 3598509 NA
Q2597810 E 2128920607 C 3598510 NA
Q193563 E 2130725560 C 3598511 NA
Q423048 E 2136131564 C 3598512 NA
Q37312 E 2142913121 C 3598513 NA
Q54919 D 2148531382 C 3598514 NA
Q36578 D 2229315598 C 3598515 NA
Q30 C 2277746226 C 3598516 NA
Q5 C 5668008721 C 3598517 NA
Q5296 D 12530369761 C 3598518 NA
entity_id prediction page_views pop_class seqNum dissonance
Q3822211 E 0 E 1 NA
Q3456322 E 0 E 2 NA
Q3807084 E 0 E 3 NA
Q3911232 E 0 E 4 NA
Q2727432 E 0 E 5 NA
Q3559277 E 0 E 6 NA
Q2107007 E 0 E 7 NA
Q2763928 E 0 E 8 NA
Q2633768 E 0 E 9 NA
Q3732410 E 0 E 10 NA
Q1491146 E 0 E 11 NA
Q3543307 E 0 E 12 NA
Q3694340 E 0 E 13 NA
Q3732853 E 0 E 14 NA
Q2000513 E 0 E 15 NA
Q2840622 E 0 E 16 NA
Q3562813 E 0 E 17 NA
Q3791515 E 0 E 18 NA
Q2676015 E 0 E 19 NA
Q1592439 E 0 E 20 NA
Q2827819 E 0 E 21 NA
Q157851 E 0 E 22 NA
Q3012022 E 0 E 23 NA
Q3695862 E 0 E 24 NA
Q2775238 E 0 E 25 NA
Q3867355 E 0 E 26 NA
Q2768542 E 0 E 27 NA
Q2722863 E 0 E 28 NA
Q2483188 E 0 E 29 NA
Q2769385 E 0 E 30 NA
⋮ ⋮ ⋮ ⋮ ⋮ ⋮
Q356 D 2047631596 C 3598489 NA
Q829984 E 2047695596 C 3598490 NA
Q384060 E 2047954248 C 3598491 NA
Q1048694 E 2048095025 C 3598492 NA
Q31165 E 2048330818 C 3598493 NA
Q40629 E 2049755644 C 3598494 NA
Q105584 E 2049926923 C 3598495 NA
Q565 D 2052996261 C 3598496 NA
Q1868372 E 2056080224 C 3598497 NA
Q209330 E 2060928966 C 3598498 NA
Q14005 D 2063120071 C 3598499 NA
Q918 D 2063217449 C 3598500 NA
Q150248 E 2068796814 C 3598501 NA
Q866 D 2079749157 C 3598502 NA
Q477675 E 2080785713 C 3598503 NA
Q1967876 E 2084215818 C 3598504 NA
Q750403 E 2084693498 C 3598505 NA
Q355 D 2093900731 C 3598506 NA
Q623578 E 2097991400 C 3598507 NA
Q33999 E 2108672678 C 3598508 NA
Q2494649 E 2114531894 C 3598509 NA
Q2597810 E 2128920607 C 3598510 NA
Q193563 E 2130725560 C 3598511 NA
Q423048 E 2136131564 C 3598512 NA
Q37312 E 2142913121 C 3598513 NA
Q54919 D 2148531382 C 3598514 NA
Q36578 D 2229315598 C 3598515 NA
Q30 C 2277746226 C 3598516 None
Q5 C 5668008721 C 3598517 None
Q5296 D 12530369761 C 3598518 NA
entity_id prediction page_views pop_class seqNum dissonance
Q3822211 E 0 E 1 NA
Q3456322 E 0 E 2 NA
Q3807084 E 0 E 3 NA
Q3911232 E 0 E 4 NA
Q2727432 E 0 E 5 NA
Q3559277 E 0 E 6 NA
Q2107007 E 0 E 7 NA
Q2763928 E 0 E 8 NA
Q2633768 E 0 E 9 NA
Q3732410 E 0 E 10 NA
Q1491146 E 0 E 11 NA
Q3543307 E 0 E 12 NA
Q3694340 E 0 E 13 NA
Q3732853 E 0 E 14 NA
Q2000513 E 0 E 15 NA
Q2840622 E 0 E 16 NA
Q3562813 E 0 E 17 NA
Q3791515 E 0 E 18 NA
Q2676015 E 0 E 19 NA
Q1592439 E 0 E 20 NA
Q2827819 E 0 E 21 NA
Q157851 E 0 E 22 NA
Q3012022 E 0 E 23 NA
Q3695862 E 0 E 24 NA
Q2775238 E 0 E 25 NA
Q3867355 E 0 E 26 NA
Q2768542 E 0 E 27 NA
Q2722863 E 0 E 28 NA
Q2483188 E 0 E 29 NA
Q2769385 E 0 E 30 NA
⋮ ⋮ ⋮ ⋮ ⋮ ⋮
Q356 D 2047631596 C 3598489 NA
Q829984 E 2047695596 C 3598490 NA
Q384060 E 2047954248 C 3598491 NA
Q1048694 E 2048095025 C 3598492 NA
Q31165 E 2048330818 C 3598493 NA
Q40629 E 2049755644 C 3598494 NA
Q105584 E 2049926923 C 3598495 NA
Q565 D 2052996261 C 3598496 NA
Q1868372 E 2056080224 C 3598497 NA
Q209330 E 2060928966 C 3598498 NA
Q14005 D 2063120071 C 3598499 NA
Q918 D 2063217449 C 3598500 NA
Q150248 E 2068796814 C 3598501 NA
Q866 D 2079749157 C 3598502 NA
Q477675 E 2080785713 C 3598503 NA
Q1967876 E 2084215818 C 3598504 NA
Q750403 E 2084693498 C 3598505 NA
Q355 D 2093900731 C 3598506 NA
Q623578 E 2097991400 C 3598507 NA
Q33999 E 2108672678 C 3598508 NA
Q2494649 E 2114531894 C 3598509 NA
Q2597810 E 2128920607 C 3598510 NA
Q193563 E 2130725560 C 3598511 NA
Q423048 E 2136131564 C 3598512 NA
Q37312 E 2142913121 C 3598513 NA
Q54919 D 2148531382 C 3598514 NA
Q36578 D 2229315598 C 3598515 NA
Q30 C 2277746226 C 3598516 None
Q5 C 5668008721 C 3598517 None
Q5296 D 12530369761 C 3598518 NA
entity_id prediction page_views pop_class seqNum dissonance
Q3822211 E 0 E 1 NA
Q3456322 E 0 E 2 NA
Q3807084 E 0 E 3 NA
Q3911232 E 0 E 4 NA
Q2727432 E 0 E 5 NA
Q3559277 E 0 E 6 NA
Q2107007 E 0 E 7 NA
Q2763928 E 0 E 8 NA
Q2633768 E 0 E 9 NA
Q3732410 E 0 E 10 NA
Q1491146 E 0 E 11 NA
Q3543307 E 0 E 12 NA
Q3694340 E 0 E 13 NA
Q3732853 E 0 E 14 NA
Q2000513 E 0 E 15 NA
Q2840622 E 0 E 16 NA
Q3562813 E 0 E 17 NA
Q3791515 E 0 E 18 NA
Q2676015 E 0 E 19 NA
Q1592439 E 0 E 20 NA
Q2827819 E 0 E 21 NA
Q157851 E 0 E 22 NA
Q3012022 E 0 E 23 NA
Q3695862 E 0 E 24 NA
Q2775238 E 0 E 25 NA
Q3867355 E 0 E 26 NA
Q2768542 E 0 E 27 NA
Q2722863 E 0 E 28 NA
Q2483188 E 0 E 29 NA
Q2769385 E 0 E 30 NA
⋮ ⋮ ⋮ ⋮ ⋮ ⋮
Q356 D 2047631596 C 3598489 NA
Q829984 E 2047695596 C 3598490 NA
Q384060 E 2047954248 C 3598491 NA
Q1048694 E 2048095025 C 3598492 NA
Q31165 E 2048330818 C 3598493 NA
Q40629 E 2049755644 C 3598494 NA
Q105584 E 2049926923 C 3598495 NA
Q565 D 2052996261 C 3598496 NA
Q1868372 E 2056080224 C 3598497 NA
Q209330 E 2060928966 C 3598498 NA
Q14005 D 2063120071 C 3598499 NA
Q918 D 2063217449 C 3598500 NA
Q150248 E 2068796814 C 3598501 NA
Q866 D 2079749157 C 3598502 NA
Q477675 E 2080785713 C 3598503 NA
Q1967876 E 2084215818 C 3598504 NA
Q750403 E 2084693498 C 3598505 NA
Q355 D 2093900731 C 3598506 NA
Q623578 E 2097991400 C 3598507 NA
Q33999 E 2108672678 C 3598508 NA
Q2494649 E 2114531894 C 3598509 NA
Q2597810 E 2128920607 C 3598510 NA
Q193563 E 2130725560 C 3598511 NA
Q423048 E 2136131564 C 3598512 NA
Q37312 E 2142913121 C 3598513 NA
Q54919 D 2148531382 C 3598514 NA
Q36578 D 2229315598 C 3598515 NA
Q30 C 2277746226 C 3598516 None
Q5 C 5668008721 C 3598517 None
Q5296 D 12530369761 C 3598518 NA
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
Q3822211 E 0 E 1 NA
Q3456322 E 0 E 2 NA
Q3807084 E 0 E 3 NA
Q3911232 E 0 E 4 NA
Q2727432 E 0 E 5 NA
Q3559277 E 0 E 6 NA
Q2107007 E 0 E 7 NA
Q2763928 E 0 E 8 NA
Q2633768 E 0 E 9 NA
Q3732410 E 0 E 10 NA
Q1491146 E 0 E 11 NA
Q3543307 E 0 E 12 NA
Q3694340 E 0 E 13 NA
Q3732853 E 0 E 14 NA
Q2000513 E 0 E 15 NA
Q2840622 E 0 E 16 NA
Q3562813 E 0 E 17 NA
Q3791515 E 0 E 18 NA
Q2676015 E 0 E 19 NA
Q1592439 E 0 E 20 NA
Q2827819 E 0 E 21 NA
Q157851 E 0 E 22 NA
Q3012022 E 0 E 23 NA
Q3695862 E 0 E 24 NA
Q2775238 E 0 E 25 NA
Q3867355 E 0 E 26 NA
Q2768542 E 0 E 27 NA
Q2722863 E 0 E 28 NA
Q2483188 E 0 E 29 NA
Q2769385 E 0 E 30 NA
⋮ ⋮ ⋮ ⋮ ⋮ ⋮
Q356 D 2047631596 C 3598489 NA
Q829984 E 2047695596 C 3598490 NA
Q384060 E 2047954248 C 3598491 NA
Q1048694 E 2048095025 C 3598492 NA
Q31165 E 2048330818 C 3598493 NA
Q40629 E 2049755644 C 3598494 NA
Q105584 E 2049926923 C 3598495 NA
Q565 D 2052996261 C 3598496 NA
Q1868372 E 2056080224 C 3598497 NA
Q209330 E 2060928966 C 3598498 NA
Q14005 D 2063120071 C 3598499 NA
Q918 D 2063217449 C 3598500 NA
Q150248 E 2068796814 C 3598501 NA
Q866 D 2079749157 C 3598502 NA
Q477675 E 2080785713 C 3598503 NA
Q1967876 E 2084215818 C 3598504 NA
Q750403 E 2084693498 C 3598505 NA
Q355 D 2093900731 C 3598506 NA
Q623578 E 2097991400 C 3598507 NA
Q33999 E 2108672678 C 3598508 NA
Q2494649 E 2114531894 C 3598509 NA
Q2597810 E 2128920607 C 3598510 NA
Q193563 E 2130725560 C 3598511 NA
Q423048 E 2136131564 C 3598512 NA
Q37312 E 2142913121 C 3598513 NA
Q54919 D 2148531382 C 3598514 NA
Q36578 D 2229315598 C 3598515 NA
Q30 C 2277746226 C 3598516 None
Q5 C 5668008721 C 3598517 None
Q5296 D 12530369761 C 3598518 NA
entity_id prediction page_views pop_class seqNum dissonance
Q3822211 E 0 E 1 NA
Q3456322 E 0 E 2 NA
Q3807084 E 0 E 3 NA
Q3911232 E 0 E 4 NA
Q2727432 E 0 E 5 NA
Q3559277 E 0 E 6 NA
Q2107007 E 0 E 7 NA
Q2763928 E 0 E 8 NA
Q2633768 E 0 E 9 NA
Q3732410 E 0 E 10 NA
Q1491146 E 0 E 11 NA
Q3543307 E 0 E 12 NA
Q3694340 E 0 E 13 NA
Q3732853 E 0 E 14 NA
Q2000513 E 0 E 15 NA
Q2840622 E 0 E 16 NA
Q3562813 E 0 E 17 NA
Q3791515 E 0 E 18 NA
Q2676015 E 0 E 19 NA
Q1592439 E 0 E 20 NA
Q2827819 E 0 E 21 NA
Q157851 E 0 E 22 NA
Q3012022 E 0 E 23 NA
Q3695862 E 0 E 24 NA
Q2775238 E 0 E 25 NA
Q3867355 E 0 E 26 NA
Q2768542 E 0 E 27 NA
Q2722863 E 0 E 28 NA
Q2483188 E 0 E 29 NA
Q2769385 E 0 E 30 NA
⋮ ⋮ ⋮ ⋮ ⋮ ⋮
Q356 D 2047631596 C 3598489 NA
Q829984 E 2047695596 C 3598490 NA
Q384060 E 2047954248 C 3598491 NA
Q1048694 E 2048095025 C 3598492 NA
Q31165 E 2048330818 C 3598493 NA
Q40629 E 2049755644 C 3598494 NA
Q105584 E 2049926923 C 3598495 NA
Q565 D 2052996261 C 3598496 NA
Q1868372 E 2056080224 C 3598497 NA
Q209330 E 2060928966 C 3598498 NA
Q14005 D 2063120071 C 3598499 NA
Q918 D 2063217449 C 3598500 NA
Q150248 E 2068796814 C 3598501 NA
Q866 D 2079749157 C 3598502 NA
Q477675 E 2080785713 C 3598503 NA
Q1967876 E 2084215818 C 3598504 NA
Q750403 E 2084693498 C 3598505 NA
Q355 D 2093900731 C 3598506 NA
Q623578 E 2097991400 C 3598507 NA
Q33999 E 2108672678 C 3598508 NA
Q2494649 E 2114531894 C 3598509 NA
Q2597810 E 2128920607 C 3598510 NA
Q193563 E 2130725560 C 3598511 NA
Q423048 E 2136131564 C 3598512 NA
Q37312 E 2142913121 C 3598513 NA
Q54919 D 2148531382 C 3598514 NA
Q36578 D 2229315598 C 3598515 NA
Q30 C 2277746226 C 3598516 None
Q5 C 5668008721 C 3598517 None
Q5296 D 12530369761 C 3598518 NA
entity_id prediction page_views pop_class seqNum dissonance
Q3822211 E 0 E 1 NA
Q3456322 E 0 E 2 NA
Q3807084 E 0 E 3 NA
Q3911232 E 0 E 4 NA
Q2727432 E 0 E 5 NA
Q3559277 E 0 E 6 NA
Q2107007 E 0 E 7 NA
Q2763928 E 0 E 8 NA
Q2633768 E 0 E 9 NA
Q3732410 E 0 E 10 NA
Q1491146 E 0 E 11 NA
Q3543307 E 0 E 12 NA
Q3694340 E 0 E 13 NA
Q3732853 E 0 E 14 NA
Q2000513 E 0 E 15 NA
Q2840622 E 0 E 16 NA
Q3562813 E 0 E 17 NA
Q3791515 E 0 E 18 NA
Q2676015 E 0 E 19 NA
Q1592439 E 0 E 20 NA
Q2827819 E 0 E 21 NA
Q157851 E 0 E 22 NA
Q3012022 E 0 E 23 NA
Q3695862 E 0 E 24 NA
Q2775238 E 0 E 25 NA
Q3867355 E 0 E 26 NA
Q2768542 E 0 E 27 NA
Q2722863 E 0 E 28 NA
Q2483188 E 0 E 29 NA
Q2769385 E 0 E 30 NA
⋮ ⋮ ⋮ ⋮ ⋮ ⋮
Q356 D 2047631596 C 3598489 Moderate positive
Q829984 E 2047695596 C 3598490 NA
Q384060 E 2047954248 C 3598491 NA
Q1048694 E 2048095025 C 3598492 NA
Q31165 E 2048330818 C 3598493 NA
Q40629 E 2049755644 C 3598494 NA
Q105584 E 2049926923 C 3598495 NA
Q565 D 2052996261 C 3598496 Moderate positive
Q1868372 E 2056080224 C 3598497 NA
Q209330 E 2060928966 C 3598498 NA
Q14005 D 2063120071 C 3598499 Moderate positive
Q918 D 2063217449 C 3598500 Moderate positive
Q150248 E 2068796814 C 3598501 NA
Q866 D 2079749157 C 3598502 Moderate positive
Q477675 E 2080785713 C 3598503 NA
Q1967876 E 2084215818 C 3598504 NA
Q750403 E 2084693498 C 3598505 NA
Q355 D 2093900731 C 3598506 Moderate positive
Q623578 E 2097991400 C 3598507 NA
Q33999 E 2108672678 C 3598508 NA
Q2494649 E 2114531894 C 3598509 NA
Q2597810 E 2128920607 C 3598510 NA
Q193563 E 2130725560 C 3598511 NA
Q423048 E 2136131564 C 3598512 NA
Q37312 E 2142913121 C 3598513 NA
Q54919 D 2148531382 C 3598514 Moderate positive
Q36578 D 2229315598 C 3598515 Moderate positive
Q30 C 2277746226 C 3598516 None
Q5 C 5668008721 C 3598517 None
Q5296 D 12530369761 C 3598518 Moderate positive
entity_id prediction page_views pop_class seqNum dissonance
Q3822211 E 0 E 1 NA
Q3456322 E 0 E 2 NA
Q3807084 E 0 E 3 NA
Q3911232 E 0 E 4 NA
Q2727432 E 0 E 5 NA
Q3559277 E 0 E 6 NA
Q2107007 E 0 E 7 NA
Q2763928 E 0 E 8 NA
Q2633768 E 0 E 9 NA
Q3732410 E 0 E 10 NA
Q1491146 E 0 E 11 NA
Q3543307 E 0 E 12 NA
Q3694340 E 0 E 13 NA
Q3732853 E 0 E 14 NA
Q2000513 E 0 E 15 NA
Q2840622 E 0 E 16 NA
Q3562813 E 0 E 17 NA
Q3791515 E 0 E 18 NA
Q2676015 E 0 E 19 NA
Q1592439 E 0 E 20 NA
Q2827819 E 0 E 21 NA
Q157851 E 0 E 22 NA
Q3012022 E 0 E 23 NA
Q3695862 E 0 E 24 NA
Q2775238 E 0 E 25 NA
Q3867355 E 0 E 26 NA
Q2768542 E 0 E 27 NA
Q2722863 E 0 E 28 NA
Q2483188 E 0 E 29 NA
Q2769385 E 0 E 30 NA
⋮ ⋮ ⋮ ⋮ ⋮ ⋮
Q356 D 2047631596 C 3598489 Moderate positive
Q829984 E 2047695596 C 3598490 NA
Q384060 E 2047954248 C 3598491 NA
Q1048694 E 2048095025 C 3598492 NA
Q31165 E 2048330818 C 3598493 NA
Q40629 E 2049755644 C 3598494 NA
Q105584 E 2049926923 C 3598495 NA
Q565 D 2052996261 C 3598496 Moderate positive
Q1868372 E 2056080224 C 3598497 NA
Q209330 E 2060928966 C 3598498 NA
Q14005 D 2063120071 C 3598499 Moderate positive
Q918 D 2063217449 C 3598500 Moderate positive
Q150248 E 2068796814 C 3598501 NA
Q866 D 2079749157 C 3598502 Moderate positive
Q477675 E 2080785713 C 3598503 NA
Q1967876 E 2084215818 C 3598504 NA
Q750403 E 2084693498 C 3598505 NA
Q355 D 2093900731 C 3598506 Moderate positive
Q623578 E 2097991400 C 3598507 NA
Q33999 E 2108672678 C 3598508 NA
Q2494649 E 2114531894 C 3598509 NA
Q2597810 E 2128920607 C 3598510 NA
Q193563 E 2130725560 C 3598511 NA
Q423048 E 2136131564 C 3598512 NA
Q37312 E 2142913121 C 3598513 NA
Q54919 D 2148531382 C 3598514 Moderate positive
Q36578 D 2229315598 C 3598515 Moderate positive
Q30 C 2277746226 C 3598516 None
Q5 C 5668008721 C 3598517 None
Q5296 D 12530369761 C 3598518 Moderate 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
Q3822211 E 0 E 1 None
Q3456322 E 0 E 2 None
Q3807084 E 0 E 3 None
Q3911232 E 0 E 4 None
Q2727432 E 0 E 5 None
Q3559277 E 0 E 6 None
Q2107007 E 0 E 7 None
Q2763928 E 0 E 8 None
Q2633768 E 0 E 9 None
Q3732410 E 0 E 10 None
Q1491146 E 0 E 11 None
Q3543307 E 0 E 12 None
Q3694340 E 0 E 13 None
Q3732853 E 0 E 14 None
Q2000513 E 0 E 15 None
Q2840622 E 0 E 16 None
Q3562813 E 0 E 17 None
Q3791515 E 0 E 18 None
Q2676015 E 0 E 19 None
Q1592439 E 0 E 20 None
Q2827819 E 0 E 21 None
Q157851 E 0 E 22 None
Q3012022 E 0 E 23 None
Q3695862 E 0 E 24 None
Q2775238 E 0 E 25 None
Q3867355 E 0 E 26 None
Q2768542 E 0 E 27 None
Q2722863 E 0 E 28 None
Q2483188 E 0 E 29 None
Q2769385 E 0 E 30 None
⋮ ⋮ ⋮ ⋮ ⋮ ⋮
Q356 D 2047631596 C 3598489 Moderate positive
Q829984 E 2047695596 C 3598490 NA
Q384060 E 2047954248 C 3598491 NA
Q1048694 E 2048095025 C 3598492 NA
Q31165 E 2048330818 C 3598493 NA
Q40629 E 2049755644 C 3598494 NA
Q105584 E 2049926923 C 3598495 NA
Q565 D 2052996261 C 3598496 Moderate positive
Q1868372 E 2056080224 C 3598497 NA
Q209330 E 2060928966 C 3598498 NA
Q14005 D 2063120071 C 3598499 Moderate positive
Q918 D 2063217449 C 3598500 Moderate positive
Q150248 E 2068796814 C 3598501 NA
Q866 D 2079749157 C 3598502 Moderate positive
Q477675 E 2080785713 C 3598503 NA
Q1967876 E 2084215818 C 3598504 NA
Q750403 E 2084693498 C 3598505 NA
Q355 D 2093900731 C 3598506 Moderate positive
Q623578 E 2097991400 C 3598507 NA
Q33999 E 2108672678 C 3598508 NA
Q2494649 E 2114531894 C 3598509 NA
Q2597810 E 2128920607 C 3598510 NA
Q193563 E 2130725560 C 3598511 NA
Q423048 E 2136131564 C 3598512 NA
Q37312 E 2142913121 C 3598513 NA
Q54919 D 2148531382 C 3598514 Moderate positive
Q36578 D 2229315598 C 3598515 Moderate positive
Q30 C 2277746226 C 3598516 None
Q5 C 5668008721 C 3598517 None
Q5296 D 12530369761 C 3598518 Moderate positive
entity_id prediction page_views pop_class seqNum dissonance
Q3822211 E 0 E 1 None
Q3456322 E 0 E 2 None
Q3807084 E 0 E 3 None
Q3911232 E 0 E 4 None
Q2727432 E 0 E 5 None
Q3559277 E 0 E 6 None
Q2107007 E 0 E 7 None
Q2763928 E 0 E 8 None
Q2633768 E 0 E 9 None
Q3732410 E 0 E 10 None
Q1491146 E 0 E 11 None
Q3543307 E 0 E 12 None
Q3694340 E 0 E 13 None
Q3732853 E 0 E 14 None
Q2000513 E 0 E 15 None
Q2840622 E 0 E 16 None
Q3562813 E 0 E 17 None
Q3791515 E 0 E 18 None
Q2676015 E 0 E 19 None
Q1592439 E 0 E 20 None
Q2827819 E 0 E 21 None
Q157851 E 0 E 22 None
Q3012022 E 0 E 23 None
Q3695862 E 0 E 24 None
Q2775238 E 0 E 25 None
Q3867355 E 0 E 26 None
Q2768542 E 0 E 27 None
Q2722863 E 0 E 28 None
Q2483188 E 0 E 29 None
Q2769385 E 0 E 30 None
⋮ ⋮ ⋮ ⋮ ⋮ ⋮
Q356 D 2047631596 C 3598489 Moderate positive
Q829984 E 2047695596 C 3598490 NA
Q384060 E 2047954248 C 3598491 NA
Q1048694 E 2048095025 C 3598492 NA
Q31165 E 2048330818 C 3598493 NA
Q40629 E 2049755644 C 3598494 NA
Q105584 E 2049926923 C 3598495 NA
Q565 D 2052996261 C 3598496 Moderate positive
Q1868372 E 2056080224 C 3598497 NA
Q209330 E 2060928966 C 3598498 NA
Q14005 D 2063120071 C 3598499 Moderate positive
Q918 D 2063217449 C 3598500 Moderate positive
Q150248 E 2068796814 C 3598501 NA
Q866 D 2079749157 C 3598502 Moderate positive
Q477675 E 2080785713 C 3598503 NA
Q1967876 E 2084215818 C 3598504 NA
Q750403 E 2084693498 C 3598505 NA
Q355 D 2093900731 C 3598506 Moderate positive
Q623578 E 2097991400 C 3598507 NA
Q33999 E 2108672678 C 3598508 NA
Q2494649 E 2114531894 C 3598509 NA
Q2597810 E 2128920607 C 3598510 NA
Q193563 E 2130725560 C 3598511 NA
Q423048 E 2136131564 C 3598512 NA
Q37312 E 2142913121 C 3598513 NA
Q54919 D 2148531382 C 3598514 Moderate positive
Q36578 D 2229315598 C 3598515 Moderate positive
Q30 C 2277746226 C 3598516 None
Q5 C 5668008721 C 3598517 None
Q5296 D 12530369761 C 3598518 Moderate positive
entity_id prediction page_views pop_class seqNum dissonance
Q3822211 E 0 E 1 None
Q3456322 E 0 E 2 None
Q3807084 E 0 E 3 None
Q3911232 E 0 E 4 None
Q2727432 E 0 E 5 None
Q3559277 E 0 E 6 None
Q2107007 E 0 E 7 None
Q2763928 E 0 E 8 None
Q2633768 E 0 E 9 None
Q3732410 E 0 E 10 None
Q1491146 E 0 E 11 None
Q3543307 E 0 E 12 None
Q3694340 E 0 E 13 None
Q3732853 E 0 E 14 None
Q2000513 E 0 E 15 None
Q2840622 E 0 E 16 None
Q3562813 E 0 E 17 None
Q3791515 E 0 E 18 None
Q2676015 E 0 E 19 None
Q1592439 E 0 E 20 None
Q2827819 E 0 E 21 None
Q157851 E 0 E 22 None
Q3012022 E 0 E 23 None
Q3695862 E 0 E 24 None
Q2775238 E 0 E 25 None
Q3867355 E 0 E 26 None
Q2768542 E 0 E 27 None
Q2722863 E 0 E 28 None
Q2483188 E 0 E 29 None
Q2769385 E 0 E 30 None
⋮ ⋮ ⋮ ⋮ ⋮ ⋮
Q356 D 2047631596 C 3598489 Moderate positive
Q829984 E 2047695596 C 3598490 High positive
Q384060 E 2047954248 C 3598491 High positive
Q1048694 E 2048095025 C 3598492 High positive
Q31165 E 2048330818 C 3598493 High positive
Q40629 E 2049755644 C 3598494 High positive
Q105584 E 2049926923 C 3598495 High positive
Q565 D 2052996261 C 3598496 Moderate positive
Q1868372 E 2056080224 C 3598497 High positive
Q209330 E 2060928966 C 3598498 High positive
Q14005 D 2063120071 C 3598499 Moderate positive
Q918 D 2063217449 C 3598500 Moderate positive
Q150248 E 2068796814 C 3598501 High positive
Q866 D 2079749157 C 3598502 Moderate positive
Q477675 E 2080785713 C 3598503 High positive
Q1967876 E 2084215818 C 3598504 High positive
Q750403 E 2084693498 C 3598505 High positive
Q355 D 2093900731 C 3598506 Moderate positive
Q623578 E 2097991400 C 3598507 High positive
Q33999 E 2108672678 C 3598508 High positive
Q2494649 E 2114531894 C 3598509 High positive
Q2597810 E 2128920607 C 3598510 High positive
Q193563 E 2130725560 C 3598511 High positive
Q423048 E 2136131564 C 3598512 High positive
Q37312 E 2142913121 C 3598513 High positive
Q54919 D 2148531382 C 3598514 Moderate positive
Q36578 D 2229315598 C 3598515 Moderate positive
Q30 C 2277746226 C 3598516 None
Q5 C 5668008721 C 3598517 None
Q5296 D 12530369761 C 3598518 Moderate 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 94.6 5.3 0
D 0.0 89.6 10.0 0.4 0
C 64.1 34.4 1.5 0.0 0
B NaN NaN NaN NaN NaN
A NaN NaN NaN NaN NaN
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 25880030560
D Moderate negative 2270605637
C High negative 52854287
E Moderate positive 100486530597
D None 19547617174
C Moderate negative 493868583
D Moderate positive 57866782774
E High positive 180056728019
C None 10045312617
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 55472960351
Moderate negative 2764474220
High negative 52854287
Moderate positive 158353313371
High positive 180056728019
In [43]:
articles_by_pop[,sum(as.numeric(page_views))];
396700330248
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
13.98359
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
0.6968671
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
0.01332348
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
39.91762
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
45.3886
Content source: hall1467/wikidata_usage_tracking
Similar notebooks: