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_20160201.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: 438
Q100 : 1 1st Qu.: 7.00 1st Qu.:2.600e+01 B: 283127
Q1000 : 1 Median : 15.00 Median :2.160e+02 C: 4296657
Q10000 : 1 Mean : 20.13 Mean :2.901e+04 D: 2801223
Q100000 : 1 3rd Qu.: 26.00 3rd Qu.:1.349e+03 E:10980836
Q1000000: 1 Max. :21863.00 Max. :1.253e+10
(Other) :18362275
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 C 0
Q10081695 C 0
Q10092002 E 0
Q10111267 E 0
Q10149726 E 0
Q10180230 E 0
Q10185035 E 0
Q10205202 E 0
Q10252966 E 0
Q10444494 C 0
Q10624171 C 0
Q10704108 C 0
Q10750354 C 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 D 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 B 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 D 3273952711
Q5 C 5668008721
Q5296 C 12530369761
entity_id prediction page_views pop_class seqNum
Q10040378 E 0 1
Q10069140 C 0 2
Q10081695 C 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 C 0 11
Q10624171 C 0 12
Q10704108 C 0 13
Q10750354 C 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 D 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 18362252
Q31165 B 2048330818 18362253
Q40629 C 2049755644 18362254
Q105584 C 2049926923 18362255
Q4584301 D 2052339927 18362256
Q565 C 2052996261 18362257
Q1868372 E 2056080224 18362258
Q209330 C 2060928966 18362259
Q14005 D 2063120071 18362260
Q918 C 2063217449 18362261
Q150248 C 2068796814 18362262
Q866 C 2079749157 18362263
Q477675 C 2080785713 18362264
Q1967876 C 2084215818 18362265
Q750403 C 2084693498 18362266
Q355 C 2093900731 18362267
Q623578 C 2097991400 18362268
Q17299517 D 2105487660 18362269
Q33999 C 2108672678 18362270
Q2494649 C 2114531894 18362271
Q2597810 C 2128920607 18362272
Q193563 C 2130725560 18362273
Q423048 C 2136131564 18362274
Q37312 C 2142913121 18362275
Q54919 C 2148531382 18362276
Q36578 C 2229315598 18362277
Q30 A 2277746226 18362278
Q6581097 D 3273952711 18362279
Q5 C 5668008721 18362280
Q5296 C 12530369761 18362281
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]$narticles;
print(paste('start_idx =', start_idx, ', end_idx = ', end_idx));
dataset[seqNum >= start_idx & seqNum <= end_idx, pop_class := rating];
prev_idx = end_idx -1;
}
dataset;
}
In [13]:
articles_by_pop = assign_pop_class(articles_by_pop,
assessment_classes, n_per_class);
[1] "start_idx = 1 , end_idx = 10980837"
[1] "start_idx = 10980837 , end_idx = 13782060"
[1] "start_idx = 13782060 , end_idx = 18078717"
[1] "start_idx = 18078717 , end_idx = 18361844"
[1] "start_idx = 18361844 , end_idx = 18362282"
In [14]:
create_dissonance_matrix = function(articledata, classes) {
d_mtrx = matrix(0, nrow=length(classes), ncol=length(classes));
rownames(d_mtrx) = classes;
colnames(d_mtrx) = classes;
for(real_rating in classes) {
for(pop_rating in classes) {
d_mtrx[real_rating, pop_rating] = length(articledata[prediction == real_rating & pop_class == pop_rating]$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 7092449 1646254 2184964 57147 22
D 1360209 576813 813070 51050 81
C 2398352 553597 1198457 145986 265
B 129826 24559 100159 28570 13
A 0 0 7 374 57
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[,])
0.484490243886367
In [18]:
# A class quality and A class views over A class quality
dissonance_matrix[5,5]/sum(dissonance_matrix[5,])
0.13013698630137
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
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,])
0.86986301369863
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])
0.86986301369863
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
Q1097348 76241976 30
Q15401930 215204156 21
Q15980804 84469470 34
Q16617922 62072156 82
Q18241050 2045553487 6
Q1868372 2056080224 45
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 64.6 15.0 19.9 0.5 0
D 48.6 20.6 29.0 1.8 0
C 55.8 12.9 27.9 3.4 0
B 45.9 8.7 35.4 10.1 0
A 0.0 0.0 1.6 85.4 13
In [26]:
round(100*prop.table(dissonance_matrix, 2), 1);
E D C B A
E 64.6 58.8 50.9 20.2 5.0
D 12.4 20.6 18.9 18.0 18.5
C 21.8 19.8 27.9 51.6 60.5
B 1.2 0.9 2.3 10.1 3.0
A 0.0 0.0 0.0 0.1 13.0
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/201602_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
Q10000 A C
Q1002972 A D
Q1028181 A C
Q103204 A C
Q1043527 A C
Q1048694 A C
Q10511368 A D
Q1054574 A C
Q105584 A C
Q1061861 A C
Q1063819 A C
Q1065 A C
Q1071953 A C
Q10726338 A D
Q1075651 A C
Q10798782 A D
Q10800557 A D
Q1097348 A E
Q11028 A C
Q11063 A C
Q11173 A C
Q1123836 A C
Q1131356 A C
Q1133733 A C
Q11366 A C
Q11399 A C
Q11424 A C
Q11570 A C
Q11573 A C
Q1162163 A D
⋮ ⋮ ⋮
Q798490 A E
Q8042151 A C
Q809830 A C
Q81096 A C
Q8261 A C
Q827525 A C
Q82799 A C
Q828224 A C
Q82955 A C
Q829984 A C
Q830077 A C
Q83042 A C
Q83310 A B
Q83552 A B
Q8447 A C
Q85 A C
Q853614 A C
Q855091 A C
Q859369 A C
Q864380 A D
Q866 A C
Q918 A C
Q937857 A C
Q9384291 A D
Q938726 A D
Q947873 A C
Q948329 A C
Q953058 A C
Q959790 A C
Q974144 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/201602_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/201602_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/201602_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 C 0 E 2
Q10081695 C 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 C 0 E 11
Q10624171 C 0 E 12
Q10704108 C 0 E 13
Q10750354 C 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 D 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 18362252
Q31165 B 2048330818 A 18362253
Q40629 C 2049755644 A 18362254
Q105584 C 2049926923 A 18362255
Q4584301 D 2052339927 A 18362256
Q565 C 2052996261 A 18362257
Q1868372 E 2056080224 A 18362258
Q209330 C 2060928966 A 18362259
Q14005 D 2063120071 A 18362260
Q918 C 2063217449 A 18362261
Q150248 C 2068796814 A 18362262
Q866 C 2079749157 A 18362263
Q477675 C 2080785713 A 18362264
Q1967876 C 2084215818 A 18362265
Q750403 C 2084693498 A 18362266
Q355 C 2093900731 A 18362267
Q623578 C 2097991400 A 18362268
Q17299517 D 2105487660 A 18362269
Q33999 C 2108672678 A 18362270
Q2494649 C 2114531894 A 18362271
Q2597810 C 2128920607 A 18362272
Q193563 C 2130725560 A 18362273
Q423048 C 2136131564 A 18362274
Q37312 C 2142913121 A 18362275
Q54919 C 2148531382 A 18362276
Q36578 C 2229315598 A 18362277
Q30 A 2277746226 A 18362278
Q6581097 D 3273952711 A 18362279
Q5 C 5668008721 A 18362280
Q5296 C 12530369761 A 18362281
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 C 0 E 2 NA
Q10081695 C 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 C 0 E 11 NA
Q10624171 C 0 E 12 NA
Q10704108 C 0 E 13 NA
Q10750354 C 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 D 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 18362252 NA
Q31165 B 2048330818 A 18362253 NA
Q40629 C 2049755644 A 18362254 NA
Q105584 C 2049926923 A 18362255 NA
Q4584301 D 2052339927 A 18362256 NA
Q565 C 2052996261 A 18362257 NA
Q1868372 E 2056080224 A 18362258 NA
Q209330 C 2060928966 A 18362259 NA
Q14005 D 2063120071 A 18362260 NA
Q918 C 2063217449 A 18362261 NA
Q150248 C 2068796814 A 18362262 NA
Q866 C 2079749157 A 18362263 NA
Q477675 C 2080785713 A 18362264 NA
Q1967876 C 2084215818 A 18362265 NA
Q750403 C 2084693498 A 18362266 NA
Q355 C 2093900731 A 18362267 NA
Q623578 C 2097991400 A 18362268 NA
Q17299517 D 2105487660 A 18362269 NA
Q33999 C 2108672678 A 18362270 NA
Q2494649 C 2114531894 A 18362271 NA
Q2597810 C 2128920607 A 18362272 NA
Q193563 C 2130725560 A 18362273 NA
Q423048 C 2136131564 A 18362274 NA
Q37312 C 2142913121 A 18362275 NA
Q54919 C 2148531382 A 18362276 NA
Q36578 C 2229315598 A 18362277 NA
Q30 A 2277746226 A 18362278 NA
Q6581097 D 3273952711 A 18362279 NA
Q5 C 5668008721 A 18362280 NA
Q5296 C 12530369761 A 18362281 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 C 0 E 2 NA
Q10081695 C 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 C 0 E 11 NA
Q10624171 C 0 E 12 NA
Q10704108 C 0 E 13 NA
Q10750354 C 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 D 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 18362252 NA
Q31165 B 2048330818 A 18362253 NA
Q40629 C 2049755644 A 18362254 NA
Q105584 C 2049926923 A 18362255 NA
Q4584301 D 2052339927 A 18362256 NA
Q565 C 2052996261 A 18362257 NA
Q1868372 E 2056080224 A 18362258 NA
Q209330 C 2060928966 A 18362259 NA
Q14005 D 2063120071 A 18362260 NA
Q918 C 2063217449 A 18362261 NA
Q150248 C 2068796814 A 18362262 NA
Q866 C 2079749157 A 18362263 NA
Q477675 C 2080785713 A 18362264 NA
Q1967876 C 2084215818 A 18362265 NA
Q750403 C 2084693498 A 18362266 NA
Q355 C 2093900731 A 18362267 NA
Q623578 C 2097991400 A 18362268 NA
Q17299517 D 2105487660 A 18362269 NA
Q33999 C 2108672678 A 18362270 NA
Q2494649 C 2114531894 A 18362271 NA
Q2597810 C 2128920607 A 18362272 NA
Q193563 C 2130725560 A 18362273 NA
Q423048 C 2136131564 A 18362274 NA
Q37312 C 2142913121 A 18362275 NA
Q54919 C 2148531382 A 18362276 NA
Q36578 C 2229315598 A 18362277 NA
Q30 A 2277746226 A 18362278 NA
Q6581097 D 3273952711 A 18362279 NA
Q5 C 5668008721 A 18362280 NA
Q5296 C 12530369761 A 18362281 NA
entity_id prediction page_views pop_class seqNum dissonance
Q10040378 E 0 E 1 NA
Q10069140 C 0 E 2 NA
Q10081695 C 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 C 0 E 11 NA
Q10624171 C 0 E 12 NA
Q10704108 C 0 E 13 NA
Q10750354 C 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 D 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 18362252 NA
Q31165 B 2048330818 A 18362253 NA
Q40629 C 2049755644 A 18362254 NA
Q105584 C 2049926923 A 18362255 NA
Q4584301 D 2052339927 A 18362256 NA
Q565 C 2052996261 A 18362257 NA
Q1868372 E 2056080224 A 18362258 NA
Q209330 C 2060928966 A 18362259 NA
Q14005 D 2063120071 A 18362260 NA
Q918 C 2063217449 A 18362261 NA
Q150248 C 2068796814 A 18362262 NA
Q866 C 2079749157 A 18362263 NA
Q477675 C 2080785713 A 18362264 NA
Q1967876 C 2084215818 A 18362265 NA
Q750403 C 2084693498 A 18362266 NA
Q355 C 2093900731 A 18362267 NA
Q623578 C 2097991400 A 18362268 NA
Q17299517 D 2105487660 A 18362269 NA
Q33999 C 2108672678 A 18362270 NA
Q2494649 C 2114531894 A 18362271 NA
Q2597810 C 2128920607 A 18362272 NA
Q193563 C 2130725560 A 18362273 NA
Q423048 C 2136131564 A 18362274 NA
Q37312 C 2142913121 A 18362275 NA
Q54919 C 2148531382 A 18362276 NA
Q36578 C 2229315598 A 18362277 NA
Q30 A 2277746226 A 18362278 NA
Q6581097 D 3273952711 A 18362279 NA
Q5 C 5668008721 A 18362280 NA
Q5296 C 12530369761 A 18362281 NA
entity_id prediction page_views pop_class seqNum dissonance
Q10040378 E 0 E 1 NA
Q10069140 C 0 E 2 NA
Q10081695 C 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 C 0 E 11 NA
Q10624171 C 0 E 12 NA
Q10704108 C 0 E 13 NA
Q10750354 C 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 D 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 18362252 NA
Q31165 B 2048330818 A 18362253 NA
Q40629 C 2049755644 A 18362254 NA
Q105584 C 2049926923 A 18362255 NA
Q4584301 D 2052339927 A 18362256 NA
Q565 C 2052996261 A 18362257 NA
Q1868372 E 2056080224 A 18362258 NA
Q209330 C 2060928966 A 18362259 NA
Q14005 D 2063120071 A 18362260 NA
Q918 C 2063217449 A 18362261 NA
Q150248 C 2068796814 A 18362262 NA
Q866 C 2079749157 A 18362263 NA
Q477675 C 2080785713 A 18362264 NA
Q1967876 C 2084215818 A 18362265 NA
Q750403 C 2084693498 A 18362266 NA
Q355 C 2093900731 A 18362267 NA
Q623578 C 2097991400 A 18362268 NA
Q17299517 D 2105487660 A 18362269 NA
Q33999 C 2108672678 A 18362270 NA
Q2494649 C 2114531894 A 18362271 NA
Q2597810 C 2128920607 A 18362272 NA
Q193563 C 2130725560 A 18362273 NA
Q423048 C 2136131564 A 18362274 NA
Q37312 C 2142913121 A 18362275 NA
Q54919 C 2148531382 A 18362276 NA
Q36578 C 2229315598 A 18362277 NA
Q30 A 2277746226 A 18362278 None
Q6581097 D 3273952711 A 18362279 NA
Q5 C 5668008721 A 18362280 NA
Q5296 C 12530369761 A 18362281 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 C 0 E 2 NA
Q10081695 C 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 C 0 E 11 NA
Q10624171 C 0 E 12 NA
Q10704108 C 0 E 13 NA
Q10750354 C 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 D 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 18362252 NA
Q31165 B 2048330818 A 18362253 NA
Q40629 C 2049755644 A 18362254 NA
Q105584 C 2049926923 A 18362255 NA
Q4584301 D 2052339927 A 18362256 NA
Q565 C 2052996261 A 18362257 NA
Q1868372 E 2056080224 A 18362258 NA
Q209330 C 2060928966 A 18362259 NA
Q14005 D 2063120071 A 18362260 NA
Q918 C 2063217449 A 18362261 NA
Q150248 C 2068796814 A 18362262 NA
Q866 C 2079749157 A 18362263 NA
Q477675 C 2080785713 A 18362264 NA
Q1967876 C 2084215818 A 18362265 NA
Q750403 C 2084693498 A 18362266 NA
Q355 C 2093900731 A 18362267 NA
Q623578 C 2097991400 A 18362268 NA
Q17299517 D 2105487660 A 18362269 NA
Q33999 C 2108672678 A 18362270 NA
Q2494649 C 2114531894 A 18362271 NA
Q2597810 C 2128920607 A 18362272 NA
Q193563 C 2130725560 A 18362273 NA
Q423048 C 2136131564 A 18362274 NA
Q37312 C 2142913121 A 18362275 NA
Q54919 C 2148531382 A 18362276 NA
Q36578 C 2229315598 A 18362277 NA
Q30 A 2277746226 A 18362278 None
Q6581097 D 3273952711 A 18362279 NA
Q5 C 5668008721 A 18362280 NA
Q5296 C 12530369761 A 18362281 NA
entity_id prediction page_views pop_class seqNum dissonance
Q10040378 E 0 E 1 NA
Q10069140 C 0 E 2 NA
Q10081695 C 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 C 0 E 11 NA
Q10624171 C 0 E 12 NA
Q10704108 C 0 E 13 NA
Q10750354 C 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 D 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 18362252 NA
Q31165 B 2048330818 A 18362253 NA
Q40629 C 2049755644 A 18362254 NA
Q105584 C 2049926923 A 18362255 NA
Q4584301 D 2052339927 A 18362256 NA
Q565 C 2052996261 A 18362257 NA
Q1868372 E 2056080224 A 18362258 NA
Q209330 C 2060928966 A 18362259 NA
Q14005 D 2063120071 A 18362260 NA
Q918 C 2063217449 A 18362261 NA
Q150248 C 2068796814 A 18362262 NA
Q866 C 2079749157 A 18362263 NA
Q477675 C 2080785713 A 18362264 NA
Q1967876 C 2084215818 A 18362265 NA
Q750403 C 2084693498 A 18362266 NA
Q355 C 2093900731 A 18362267 NA
Q623578 C 2097991400 A 18362268 NA
Q17299517 D 2105487660 A 18362269 NA
Q33999 C 2108672678 A 18362270 NA
Q2494649 C 2114531894 A 18362271 NA
Q2597810 C 2128920607 A 18362272 NA
Q193563 C 2130725560 A 18362273 NA
Q423048 C 2136131564 A 18362274 NA
Q37312 C 2142913121 A 18362275 NA
Q54919 C 2148531382 A 18362276 NA
Q36578 C 2229315598 A 18362277 NA
Q30 A 2277746226 A 18362278 None
Q6581097 D 3273952711 A 18362279 NA
Q5 C 5668008721 A 18362280 NA
Q5296 C 12530369761 A 18362281 NA
entity_id prediction page_views pop_class seqNum dissonance
Q10040378 E 0 E 1 NA
Q10069140 C 0 E 2 NA
Q10081695 C 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 C 0 E 11 NA
Q10624171 C 0 E 12 NA
Q10704108 C 0 E 13 NA
Q10750354 C 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 D 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 18362252 NA
Q31165 B 2048330818 A 18362253 NA
Q40629 C 2049755644 A 18362254 NA
Q105584 C 2049926923 A 18362255 NA
Q4584301 D 2052339927 A 18362256 NA
Q565 C 2052996261 A 18362257 NA
Q1868372 E 2056080224 A 18362258 NA
Q209330 C 2060928966 A 18362259 NA
Q14005 D 2063120071 A 18362260 NA
Q918 C 2063217449 A 18362261 NA
Q150248 C 2068796814 A 18362262 NA
Q866 C 2079749157 A 18362263 NA
Q477675 C 2080785713 A 18362264 NA
Q1967876 C 2084215818 A 18362265 NA
Q750403 C 2084693498 A 18362266 NA
Q355 C 2093900731 A 18362267 NA
Q623578 C 2097991400 A 18362268 NA
Q17299517 D 2105487660 A 18362269 NA
Q33999 C 2108672678 A 18362270 NA
Q2494649 C 2114531894 A 18362271 NA
Q2597810 C 2128920607 A 18362272 NA
Q193563 C 2130725560 A 18362273 NA
Q423048 C 2136131564 A 18362274 NA
Q37312 C 2142913121 A 18362275 NA
Q54919 C 2148531382 A 18362276 NA
Q36578 C 2229315598 A 18362277 NA
Q30 A 2277746226 A 18362278 None
Q6581097 D 3273952711 A 18362279 NA
Q5 C 5668008721 A 18362280 NA
Q5296 C 12530369761 A 18362281 NA
entity_id prediction page_views pop_class seqNum dissonance
Q10040378 E 0 E 1 NA
Q10069140 C 0 E 2 NA
Q10081695 C 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 C 0 E 11 NA
Q10624171 C 0 E 12 NA
Q10704108 C 0 E 13 NA
Q10750354 C 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 D 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 18362252 NA
Q31165 B 2048330818 A 18362253 Moderate positive
Q40629 C 2049755644 A 18362254 NA
Q105584 C 2049926923 A 18362255 NA
Q4584301 D 2052339927 A 18362256 NA
Q565 C 2052996261 A 18362257 NA
Q1868372 E 2056080224 A 18362258 NA
Q209330 C 2060928966 A 18362259 NA
Q14005 D 2063120071 A 18362260 NA
Q918 C 2063217449 A 18362261 NA
Q150248 C 2068796814 A 18362262 NA
Q866 C 2079749157 A 18362263 NA
Q477675 C 2080785713 A 18362264 NA
Q1967876 C 2084215818 A 18362265 NA
Q750403 C 2084693498 A 18362266 NA
Q355 C 2093900731 A 18362267 NA
Q623578 C 2097991400 A 18362268 NA
Q17299517 D 2105487660 A 18362269 NA
Q33999 C 2108672678 A 18362270 NA
Q2494649 C 2114531894 A 18362271 NA
Q2597810 C 2128920607 A 18362272 NA
Q193563 C 2130725560 A 18362273 NA
Q423048 C 2136131564 A 18362274 NA
Q37312 C 2142913121 A 18362275 NA
Q54919 C 2148531382 A 18362276 NA
Q36578 C 2229315598 A 18362277 NA
Q30 A 2277746226 A 18362278 None
Q6581097 D 3273952711 A 18362279 NA
Q5 C 5668008721 A 18362280 NA
Q5296 C 12530369761 A 18362281 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 C 0 E 2 High negative
Q10081695 C 0 E 3 High negative
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 C 0 E 11 High negative
Q10624171 C 0 E 12 High negative
Q10704108 C 0 E 13 High negative
Q10750354 C 0 E 14 High negative
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 D 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 18362252 NA
Q31165 B 2048330818 A 18362253 Moderate positive
Q40629 C 2049755644 A 18362254 NA
Q105584 C 2049926923 A 18362255 NA
Q4584301 D 2052339927 A 18362256 NA
Q565 C 2052996261 A 18362257 NA
Q1868372 E 2056080224 A 18362258 NA
Q209330 C 2060928966 A 18362259 NA
Q14005 D 2063120071 A 18362260 NA
Q918 C 2063217449 A 18362261 NA
Q150248 C 2068796814 A 18362262 NA
Q866 C 2079749157 A 18362263 NA
Q477675 C 2080785713 A 18362264 NA
Q1967876 C 2084215818 A 18362265 NA
Q750403 C 2084693498 A 18362266 NA
Q355 C 2093900731 A 18362267 NA
Q623578 C 2097991400 A 18362268 NA
Q17299517 D 2105487660 A 18362269 NA
Q33999 C 2108672678 A 18362270 NA
Q2494649 C 2114531894 A 18362271 NA
Q2597810 C 2128920607 A 18362272 NA
Q193563 C 2130725560 A 18362273 NA
Q423048 C 2136131564 A 18362274 NA
Q37312 C 2142913121 A 18362275 NA
Q54919 C 2148531382 A 18362276 NA
Q36578 C 2229315598 A 18362277 NA
Q30 A 2277746226 A 18362278 None
Q6581097 D 3273952711 A 18362279 NA
Q5 C 5668008721 A 18362280 NA
Q5296 C 12530369761 A 18362281 NA
entity_id prediction page_views pop_class seqNum dissonance
Q10040378 E 0 E 1 NA
Q10069140 C 0 E 2 High negative
Q10081695 C 0 E 3 High negative
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 C 0 E 11 High negative
Q10624171 C 0 E 12 High negative
Q10704108 C 0 E 13 High negative
Q10750354 C 0 E 14 High negative
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 D 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 18362252 NA
Q31165 B 2048330818 A 18362253 Moderate positive
Q40629 C 2049755644 A 18362254 NA
Q105584 C 2049926923 A 18362255 NA
Q4584301 D 2052339927 A 18362256 NA
Q565 C 2052996261 A 18362257 NA
Q1868372 E 2056080224 A 18362258 NA
Q209330 C 2060928966 A 18362259 NA
Q14005 D 2063120071 A 18362260 NA
Q918 C 2063217449 A 18362261 NA
Q150248 C 2068796814 A 18362262 NA
Q866 C 2079749157 A 18362263 NA
Q477675 C 2080785713 A 18362264 NA
Q1967876 C 2084215818 A 18362265 NA
Q750403 C 2084693498 A 18362266 NA
Q355 C 2093900731 A 18362267 NA
Q623578 C 2097991400 A 18362268 NA
Q17299517 D 2105487660 A 18362269 NA
Q33999 C 2108672678 A 18362270 NA
Q2494649 C 2114531894 A 18362271 NA
Q2597810 C 2128920607 A 18362272 NA
Q193563 C 2130725560 A 18362273 NA
Q423048 C 2136131564 A 18362274 NA
Q37312 C 2142913121 A 18362275 NA
Q54919 C 2148531382 A 18362276 NA
Q36578 C 2229315598 A 18362277 NA
Q30 A 2277746226 A 18362278 None
Q6581097 D 3273952711 A 18362279 NA
Q5 C 5668008721 A 18362280 NA
Q5296 C 12530369761 A 18362281 NA
entity_id prediction page_views pop_class seqNum dissonance
Q10040378 E 0 E 1 NA
Q10069140 C 0 E 2 High negative
Q10081695 C 0 E 3 High negative
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 C 0 E 11 High negative
Q10624171 C 0 E 12 High negative
Q10704108 C 0 E 13 High negative
Q10750354 C 0 E 14 High negative
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 D 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 18362252 NA
Q31165 B 2048330818 A 18362253 Moderate positive
Q40629 C 2049755644 A 18362254 NA
Q105584 C 2049926923 A 18362255 NA
Q4584301 D 2052339927 A 18362256 NA
Q565 C 2052996261 A 18362257 NA
Q1868372 E 2056080224 A 18362258 NA
Q209330 C 2060928966 A 18362259 NA
Q14005 D 2063120071 A 18362260 NA
Q918 C 2063217449 A 18362261 NA
Q150248 C 2068796814 A 18362262 NA
Q866 C 2079749157 A 18362263 NA
Q477675 C 2080785713 A 18362264 NA
Q1967876 C 2084215818 A 18362265 NA
Q750403 C 2084693498 A 18362266 NA
Q355 C 2093900731 A 18362267 NA
Q623578 C 2097991400 A 18362268 NA
Q17299517 D 2105487660 A 18362269 NA
Q33999 C 2108672678 A 18362270 NA
Q2494649 C 2114531894 A 18362271 NA
Q2597810 C 2128920607 A 18362272 NA
Q193563 C 2130725560 A 18362273 NA
Q423048 C 2136131564 A 18362274 NA
Q37312 C 2142913121 A 18362275 NA
Q54919 C 2148531382 A 18362276 NA
Q36578 C 2229315598 A 18362277 NA
Q30 A 2277746226 A 18362278 None
Q6581097 D 3273952711 A 18362279 NA
Q5 C 5668008721 A 18362280 NA
Q5296 C 12530369761 A 18362281 NA
entity_id prediction page_views pop_class seqNum dissonance
Q10040378 E 0 E 1 NA
Q10069140 C 0 E 2 High negative
Q10081695 C 0 E 3 High negative
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 C 0 E 11 High negative
Q10624171 C 0 E 12 High negative
Q10704108 C 0 E 13 High negative
Q10750354 C 0 E 14 High negative
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 D 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 18362252 NA
Q31165 B 2048330818 A 18362253 Moderate positive
Q40629 C 2049755644 A 18362254 NA
Q105584 C 2049926923 A 18362255 NA
Q4584301 D 2052339927 A 18362256 NA
Q565 C 2052996261 A 18362257 NA
Q1868372 E 2056080224 A 18362258 NA
Q209330 C 2060928966 A 18362259 NA
Q14005 D 2063120071 A 18362260 NA
Q918 C 2063217449 A 18362261 NA
Q150248 C 2068796814 A 18362262 NA
Q866 C 2079749157 A 18362263 NA
Q477675 C 2080785713 A 18362264 NA
Q1967876 C 2084215818 A 18362265 NA
Q750403 C 2084693498 A 18362266 NA
Q355 C 2093900731 A 18362267 NA
Q623578 C 2097991400 A 18362268 NA
Q17299517 D 2105487660 A 18362269 NA
Q33999 C 2108672678 A 18362270 NA
Q2494649 C 2114531894 A 18362271 NA
Q2597810 C 2128920607 A 18362272 NA
Q193563 C 2130725560 A 18362273 NA
Q423048 C 2136131564 A 18362274 NA
Q37312 C 2142913121 A 18362275 NA
Q54919 C 2148531382 A 18362276 NA
Q36578 C 2229315598 A 18362277 NA
Q30 A 2277746226 A 18362278 None
Q6581097 D 3273952711 A 18362279 NA
Q5 C 5668008721 A 18362280 NA
Q5296 C 12530369761 A 18362281 NA
entity_id prediction page_views pop_class seqNum dissonance
Q10040378 E 0 E 1 NA
Q10069140 C 0 E 2 High negative
Q10081695 C 0 E 3 High negative
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 C 0 E 11 High negative
Q10624171 C 0 E 12 High negative
Q10704108 C 0 E 13 High negative
Q10750354 C 0 E 14 High negative
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 D 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 18362252 High positive
Q31165 B 2048330818 A 18362253 Moderate positive
Q40629 C 2049755644 A 18362254 High positive
Q105584 C 2049926923 A 18362255 High positive
Q4584301 D 2052339927 A 18362256 NA
Q565 C 2052996261 A 18362257 High positive
Q1868372 E 2056080224 A 18362258 NA
Q209330 C 2060928966 A 18362259 High positive
Q14005 D 2063120071 A 18362260 NA
Q918 C 2063217449 A 18362261 High positive
Q150248 C 2068796814 A 18362262 High positive
Q866 C 2079749157 A 18362263 High positive
Q477675 C 2080785713 A 18362264 High positive
Q1967876 C 2084215818 A 18362265 High positive
Q750403 C 2084693498 A 18362266 High positive
Q355 C 2093900731 A 18362267 High positive
Q623578 C 2097991400 A 18362268 High positive
Q17299517 D 2105487660 A 18362269 NA
Q33999 C 2108672678 A 18362270 High positive
Q2494649 C 2114531894 A 18362271 High positive
Q2597810 C 2128920607 A 18362272 High positive
Q193563 C 2130725560 A 18362273 High positive
Q423048 C 2136131564 A 18362274 High positive
Q37312 C 2142913121 A 18362275 High positive
Q54919 C 2148531382 A 18362276 High positive
Q36578 C 2229315598 A 18362277 High positive
Q30 A 2277746226 A 18362278 None
Q6581097 D 3273952711 A 18362279 NA
Q5 C 5668008721 A 18362280 High positive
Q5296 C 12530369761 A 18362281 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 C 0 E 2 High negative
Q10081695 C 0 E 3 High negative
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 C 0 E 11 High negative
Q10624171 C 0 E 12 High negative
Q10704108 C 0 E 13 High negative
Q10750354 C 0 E 14 High negative
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 D 0 E 23 Moderate negative
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 18362252 High positive
Q31165 B 2048330818 A 18362253 Moderate positive
Q40629 C 2049755644 A 18362254 High positive
Q105584 C 2049926923 A 18362255 High positive
Q4584301 D 2052339927 A 18362256 NA
Q565 C 2052996261 A 18362257 High positive
Q1868372 E 2056080224 A 18362258 NA
Q209330 C 2060928966 A 18362259 High positive
Q14005 D 2063120071 A 18362260 NA
Q918 C 2063217449 A 18362261 High positive
Q150248 C 2068796814 A 18362262 High positive
Q866 C 2079749157 A 18362263 High positive
Q477675 C 2080785713 A 18362264 High positive
Q1967876 C 2084215818 A 18362265 High positive
Q750403 C 2084693498 A 18362266 High positive
Q355 C 2093900731 A 18362267 High positive
Q623578 C 2097991400 A 18362268 High positive
Q17299517 D 2105487660 A 18362269 NA
Q33999 C 2108672678 A 18362270 High positive
Q2494649 C 2114531894 A 18362271 High positive
Q2597810 C 2128920607 A 18362272 High positive
Q193563 C 2130725560 A 18362273 High positive
Q423048 C 2136131564 A 18362274 High positive
Q37312 C 2142913121 A 18362275 High positive
Q54919 C 2148531382 A 18362276 High positive
Q36578 C 2229315598 A 18362277 High positive
Q30 A 2277746226 A 18362278 None
Q6581097 D 3273952711 A 18362279 NA
Q5 C 5668008721 A 18362280 High positive
Q5296 C 12530369761 A 18362281 High positive
entity_id prediction page_views pop_class seqNum dissonance
Q10040378 E 0 E 1 NA
Q10069140 C 0 E 2 High negative
Q10081695 C 0 E 3 High negative
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 C 0 E 11 High negative
Q10624171 C 0 E 12 High negative
Q10704108 C 0 E 13 High negative
Q10750354 C 0 E 14 High negative
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 D 0 E 23 Moderate negative
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 18362252 High positive
Q31165 B 2048330818 A 18362253 Moderate positive
Q40629 C 2049755644 A 18362254 High positive
Q105584 C 2049926923 A 18362255 High positive
Q4584301 D 2052339927 A 18362256 NA
Q565 C 2052996261 A 18362257 High positive
Q1868372 E 2056080224 A 18362258 NA
Q209330 C 2060928966 A 18362259 High positive
Q14005 D 2063120071 A 18362260 NA
Q918 C 2063217449 A 18362261 High positive
Q150248 C 2068796814 A 18362262 High positive
Q866 C 2079749157 A 18362263 High positive
Q477675 C 2080785713 A 18362264 High positive
Q1967876 C 2084215818 A 18362265 High positive
Q750403 C 2084693498 A 18362266 High positive
Q355 C 2093900731 A 18362267 High positive
Q623578 C 2097991400 A 18362268 High positive
Q17299517 D 2105487660 A 18362269 NA
Q33999 C 2108672678 A 18362270 High positive
Q2494649 C 2114531894 A 18362271 High positive
Q2597810 C 2128920607 A 18362272 High positive
Q193563 C 2130725560 A 18362273 High positive
Q423048 C 2136131564 A 18362274 High positive
Q37312 C 2142913121 A 18362275 High positive
Q54919 C 2148531382 A 18362276 High positive
Q36578 C 2229315598 A 18362277 High positive
Q30 A 2277746226 A 18362278 None
Q6581097 D 3273952711 A 18362279 NA
Q5 C 5668008721 A 18362280 High positive
Q5296 C 12530369761 A 18362281 High positive
entity_id prediction page_views pop_class seqNum dissonance
Q10040378 E 0 E 1 NA
Q10069140 C 0 E 2 High negative
Q10081695 C 0 E 3 High negative
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 C 0 E 11 High negative
Q10624171 C 0 E 12 High negative
Q10704108 C 0 E 13 High negative
Q10750354 C 0 E 14 High negative
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 D 0 E 23 Moderate negative
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 18362252 High positive
Q31165 B 2048330818 A 18362253 Moderate positive
Q40629 C 2049755644 A 18362254 High positive
Q105584 C 2049926923 A 18362255 High positive
Q4584301 D 2052339927 A 18362256 NA
Q565 C 2052996261 A 18362257 High positive
Q1868372 E 2056080224 A 18362258 NA
Q209330 C 2060928966 A 18362259 High positive
Q14005 D 2063120071 A 18362260 NA
Q918 C 2063217449 A 18362261 High positive
Q150248 C 2068796814 A 18362262 High positive
Q866 C 2079749157 A 18362263 High positive
Q477675 C 2080785713 A 18362264 High positive
Q1967876 C 2084215818 A 18362265 High positive
Q750403 C 2084693498 A 18362266 High positive
Q355 C 2093900731 A 18362267 High positive
Q623578 C 2097991400 A 18362268 High positive
Q17299517 D 2105487660 A 18362269 NA
Q33999 C 2108672678 A 18362270 High positive
Q2494649 C 2114531894 A 18362271 High positive
Q2597810 C 2128920607 A 18362272 High positive
Q193563 C 2130725560 A 18362273 High positive
Q423048 C 2136131564 A 18362274 High positive
Q37312 C 2142913121 A 18362275 High positive
Q54919 C 2148531382 A 18362276 High positive
Q36578 C 2229315598 A 18362277 High positive
Q30 A 2277746226 A 18362278 None
Q6581097 D 3273952711 A 18362279 NA
Q5 C 5668008721 A 18362280 High positive
Q5296 C 12530369761 A 18362281 High positive
entity_id prediction page_views pop_class seqNum dissonance
Q10040378 E 0 E 1 NA
Q10069140 C 0 E 2 High negative
Q10081695 C 0 E 3 High negative
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 C 0 E 11 High negative
Q10624171 C 0 E 12 High negative
Q10704108 C 0 E 13 High negative
Q10750354 C 0 E 14 High negative
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 D 0 E 23 Moderate negative
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 18362252 High positive
Q31165 B 2048330818 A 18362253 Moderate positive
Q40629 C 2049755644 A 18362254 High positive
Q105584 C 2049926923 A 18362255 High positive
Q4584301 D 2052339927 A 18362256 High positive
Q565 C 2052996261 A 18362257 High positive
Q1868372 E 2056080224 A 18362258 NA
Q209330 C 2060928966 A 18362259 High positive
Q14005 D 2063120071 A 18362260 High positive
Q918 C 2063217449 A 18362261 High positive
Q150248 C 2068796814 A 18362262 High positive
Q866 C 2079749157 A 18362263 High positive
Q477675 C 2080785713 A 18362264 High positive
Q1967876 C 2084215818 A 18362265 High positive
Q750403 C 2084693498 A 18362266 High positive
Q355 C 2093900731 A 18362267 High positive
Q623578 C 2097991400 A 18362268 High positive
Q17299517 D 2105487660 A 18362269 High positive
Q33999 C 2108672678 A 18362270 High positive
Q2494649 C 2114531894 A 18362271 High positive
Q2597810 C 2128920607 A 18362272 High positive
Q193563 C 2130725560 A 18362273 High positive
Q423048 C 2136131564 A 18362274 High positive
Q37312 C 2142913121 A 18362275 High positive
Q54919 C 2148531382 A 18362276 High positive
Q36578 C 2229315598 A 18362277 High positive
Q30 A 2277746226 A 18362278 None
Q6581097 D 3273952711 A 18362279 High positive
Q5 C 5668008721 A 18362280 High positive
Q5296 C 12530369761 A 18362281 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 C 0 E 2 High negative
Q10081695 C 0 E 3 High negative
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 C 0 E 11 High negative
Q10624171 C 0 E 12 High negative
Q10704108 C 0 E 13 High negative
Q10750354 C 0 E 14 High negative
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 D 0 E 23 Moderate negative
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 18362252 High positive
Q31165 B 2048330818 A 18362253 Moderate positive
Q40629 C 2049755644 A 18362254 High positive
Q105584 C 2049926923 A 18362255 High positive
Q4584301 D 2052339927 A 18362256 High positive
Q565 C 2052996261 A 18362257 High positive
Q1868372 E 2056080224 A 18362258 NA
Q209330 C 2060928966 A 18362259 High positive
Q14005 D 2063120071 A 18362260 High positive
Q918 C 2063217449 A 18362261 High positive
Q150248 C 2068796814 A 18362262 High positive
Q866 C 2079749157 A 18362263 High positive
Q477675 C 2080785713 A 18362264 High positive
Q1967876 C 2084215818 A 18362265 High positive
Q750403 C 2084693498 A 18362266 High positive
Q355 C 2093900731 A 18362267 High positive
Q623578 C 2097991400 A 18362268 High positive
Q17299517 D 2105487660 A 18362269 High positive
Q33999 C 2108672678 A 18362270 High positive
Q2494649 C 2114531894 A 18362271 High positive
Q2597810 C 2128920607 A 18362272 High positive
Q193563 C 2130725560 A 18362273 High positive
Q423048 C 2136131564 A 18362274 High positive
Q37312 C 2142913121 A 18362275 High positive
Q54919 C 2148531382 A 18362276 High positive
Q36578 C 2229315598 A 18362277 High positive
Q30 A 2277746226 A 18362278 None
Q6581097 D 3273952711 A 18362279 High positive
Q5 C 5668008721 A 18362280 High positive
Q5296 C 12530369761 A 18362281 High positive
entity_id prediction page_views pop_class seqNum dissonance
Q10040378 E 0 E 1 None
Q10069140 C 0 E 2 High negative
Q10081695 C 0 E 3 High negative
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 C 0 E 11 High negative
Q10624171 C 0 E 12 High negative
Q10704108 C 0 E 13 High negative
Q10750354 C 0 E 14 High negative
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 D 0 E 23 Moderate negative
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 18362252 High positive
Q31165 B 2048330818 A 18362253 Moderate positive
Q40629 C 2049755644 A 18362254 High positive
Q105584 C 2049926923 A 18362255 High positive
Q4584301 D 2052339927 A 18362256 High positive
Q565 C 2052996261 A 18362257 High positive
Q1868372 E 2056080224 A 18362258 NA
Q209330 C 2060928966 A 18362259 High positive
Q14005 D 2063120071 A 18362260 High positive
Q918 C 2063217449 A 18362261 High positive
Q150248 C 2068796814 A 18362262 High positive
Q866 C 2079749157 A 18362263 High positive
Q477675 C 2080785713 A 18362264 High positive
Q1967876 C 2084215818 A 18362265 High positive
Q750403 C 2084693498 A 18362266 High positive
Q355 C 2093900731 A 18362267 High positive
Q623578 C 2097991400 A 18362268 High positive
Q17299517 D 2105487660 A 18362269 High positive
Q33999 C 2108672678 A 18362270 High positive
Q2494649 C 2114531894 A 18362271 High positive
Q2597810 C 2128920607 A 18362272 High positive
Q193563 C 2130725560 A 18362273 High positive
Q423048 C 2136131564 A 18362274 High positive
Q37312 C 2142913121 A 18362275 High positive
Q54919 C 2148531382 A 18362276 High positive
Q36578 C 2229315598 A 18362277 High positive
Q30 A 2277746226 A 18362278 None
Q6581097 D 3273952711 A 18362279 High positive
Q5 C 5668008721 A 18362280 High positive
Q5296 C 12530369761 A 18362281 High positive
entity_id prediction page_views pop_class seqNum dissonance
Q10040378 E 0 E 1 None
Q10069140 C 0 E 2 High negative
Q10081695 C 0 E 3 High negative
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 C 0 E 11 High negative
Q10624171 C 0 E 12 High negative
Q10704108 C 0 E 13 High negative
Q10750354 C 0 E 14 High negative
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 D 0 E 23 Moderate negative
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 18362252 High positive
Q31165 B 2048330818 A 18362253 Moderate positive
Q40629 C 2049755644 A 18362254 High positive
Q105584 C 2049926923 A 18362255 High positive
Q4584301 D 2052339927 A 18362256 High positive
Q565 C 2052996261 A 18362257 High positive
Q1868372 E 2056080224 A 18362258 High positive
Q209330 C 2060928966 A 18362259 High positive
Q14005 D 2063120071 A 18362260 High positive
Q918 C 2063217449 A 18362261 High positive
Q150248 C 2068796814 A 18362262 High positive
Q866 C 2079749157 A 18362263 High positive
Q477675 C 2080785713 A 18362264 High positive
Q1967876 C 2084215818 A 18362265 High positive
Q750403 C 2084693498 A 18362266 High positive
Q355 C 2093900731 A 18362267 High positive
Q623578 C 2097991400 A 18362268 High positive
Q17299517 D 2105487660 A 18362269 High positive
Q33999 C 2108672678 A 18362270 High positive
Q2494649 C 2114531894 A 18362271 High positive
Q2597810 C 2128920607 A 18362272 High positive
Q193563 C 2130725560 A 18362273 High positive
Q423048 C 2136131564 A 18362274 High positive
Q37312 C 2142913121 A 18362275 High positive
Q54919 C 2148531382 A 18362276 High positive
Q36578 C 2229315598 A 18362277 High positive
Q30 A 2277746226 A 18362278 None
Q6581097 D 3273952711 A 18362279 High positive
Q5 C 5668008721 A 18362280 High positive
Q5296 C 12530369761 A 18362281 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 64.6 15.0 20.4
D 0.0 48.6 20.6 29.0 1.8
C 55.8 12.9 27.9 3.4 0.0
B 54.5 35.4 10.1 0.0 0.0
A 1.6 85.4 13.0 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 640544739
C High negative 178701731
D Moderate negative 188177915
B High negative 29851728
D None 454611593
E Moderate positive 1301151665
C Moderate negative 444820169
E High positive 62471156668
C None 18000080376
D Moderate positive 9560972075
B Moderate negative 1874783298
A High negative 311336
C Moderate positive 100263726778
B None 29090446351
D High positive 98025943115
A Moderate negative 3112334330
C High positive 188306864863
A None 9771617551
B Moderate positive 9048790670
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 57957300610
High negative 208864795
Moderate negative 5620115712
Moderate positive 120174641188
High positive 348803964646
In [43]:
articles_by_pop[,sum(as.numeric(page_views))];
532764886951
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
10.87859
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
0.03920393
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
1.054896
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
22.55679
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
65.47052
Content source: hall1467/wikidata_usage_tracking
Similar notebooks: