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_20141201.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: 73
Q100 : 1 1st Qu.: 9.00 1st Qu.:4.000e+01 B: 32098
Q1000 : 1 Median : 16.00 Median :2.930e+02 C: 1559149
Q10000 : 1 Mean : 21.82 Mean :3.285e+04 D: 2778214
Q100000 : 1 3rd Qu.: 28.00 3rd Qu.:1.692e+03 E:11301154
Q1000000: 1 Max. :21863.00 Max. :1.253e+10
(Other) :15670682
In [8]:
## 0: calculate number of articles in each assessment class
n_per_class = quality_prediction_and_page_views[, list(narticles=sum(.N)), by='prediction']
In [9]:
setkey(n_per_class, prediction);
## NOTE: setkey allows us to do n_per_class['GA']$narticles to get counts
In [10]:
## 1: order articles by popularity
articles_by_pop = quality_prediction_and_page_views[order(quality_prediction_and_page_views$page_views)][,list(entity_id, prediction, page_views)];
In [11]:
## 2: assign popularity assessment class based on rank
## (buckets based on number of articles in each class)
articles_by_pop[, pop_class := ''];
articles_by_pop[, seqNum := seq_len(nrow(articles_by_pop))];
entity_id prediction page_views pop_class Q10040378 E 0 Q10069140 E 0 Q10081695 E 0 Q10092002 E 0 Q10111267 E 0 Q10149726 E 0 Q10180230 E 0 Q10185035 E 0 Q10205202 E 0 Q10252966 E 0 Q10444494 D 0 Q10624171 D 0 Q10704108 D 0 Q10750354 E 0 Q10766855 E 0 Q10827611 E 0 Q11093044 E 0 Q11934537 E 0 Q12133466 E 0 Q12264503 E 0 Q12267516 E 0 Q12304084 E 0 Q12443525 E 0 Q12543904 E 0 Q12890205 E 0 Q12891524 E 0 Q12918202 E 0 Q13005653 E 0 Q13073896 E 0 Q13163823 E 0 ⋮ ⋮ ⋮ ⋮ Q1048694 C 2048095025 Q31165 C 2048330818 Q40629 C 2049755644 Q105584 C 2049926923 Q4584301 D 2052339927 Q565 C 2052996261 Q1868372 E 2056080224 Q209330 C 2060928966 Q14005 D 2063120071 Q918 C 2063217449 Q150248 C 2068796814 Q866 C 2079749157 Q477675 C 2080785713 Q1967876 C 2084215818 Q750403 C 2084693498 Q355 C 2093900731 Q623578 C 2097991400 Q17299517 D 2105487660 Q33999 C 2108672678 Q2494649 C 2114531894 Q2597810 C 2128920607 Q193563 C 2130725560 Q423048 C 2136131564 Q37312 C 2142913121 Q54919 C 2148531382 Q36578 C 2229315598 Q30 A 2277746226 Q6581097 C 3273952711 Q5 A 5668008721 Q5296 C 12530369761
entity_id prediction page_views pop_class seqNum Q10040378 E 0 1 Q10069140 E 0 2 Q10081695 E 0 3 Q10092002 E 0 4 Q10111267 E 0 5 Q10149726 E 0 6 Q10180230 E 0 7 Q10185035 E 0 8 Q10205202 E 0 9 Q10252966 E 0 10 Q10444494 D 0 11 Q10624171 D 0 12 Q10704108 D 0 13 Q10750354 E 0 14 Q10766855 E 0 15 Q10827611 E 0 16 Q11093044 E 0 17 Q11934537 E 0 18 Q12133466 E 0 19 Q12264503 E 0 20 Q12267516 E 0 21 Q12304084 E 0 22 Q12443525 E 0 23 Q12543904 E 0 24 Q12890205 E 0 25 Q12891524 E 0 26 Q12918202 E 0 27 Q13005653 E 0 28 Q13073896 E 0 29 Q13163823 E 0 30 ⋮ ⋮ ⋮ ⋮ ⋮ Q1048694 C 2048095025 15670659 Q31165 C 2048330818 15670660 Q40629 C 2049755644 15670661 Q105584 C 2049926923 15670662 Q4584301 D 2052339927 15670663 Q565 C 2052996261 15670664 Q1868372 E 2056080224 15670665 Q209330 C 2060928966 15670666 Q14005 D 2063120071 15670667 Q918 C 2063217449 15670668 Q150248 C 2068796814 15670669 Q866 C 2079749157 15670670 Q477675 C 2080785713 15670671 Q1967876 C 2084215818 15670672 Q750403 C 2084693498 15670673 Q355 C 2093900731 15670674 Q623578 C 2097991400 15670675 Q17299517 D 2105487660 15670676 Q33999 C 2108672678 15670677 Q2494649 C 2114531894 15670678 Q2597810 C 2128920607 15670679 Q193563 C 2130725560 15670680 Q423048 C 2136131564 15670681 Q37312 C 2142913121 15670682 Q54919 C 2148531382 15670683 Q36578 C 2229315598 15670684 Q30 A 2277746226 15670685 Q6581097 C 3273952711 15670686 Q5 A 5668008721 15670687 Q5296 C 12530369761 15670688
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]$narticles;
print(paste('start_idx =', start_idx, ', end_idx = ', end_idx));
dataset[seqNum >= start_idx & seqNum <= end_idx, pop_class := rating];
prev_idx = end_idx -1;
}
dataset;
}
In [13]:
articles_by_pop = assign_pop_class(articles_by_pop,
assessment_classes, n_per_class);
[1] "start_idx = 1 , end_idx = 11301155"
[1] "start_idx = 11301155 , end_idx = 14079369"
[1] "start_idx = 14079369 , end_idx = 15638518"
[1] "start_idx = 15638518 , end_idx = 15670616"
[1] "start_idx = 15670616 , end_idx = 15670689"
In [14]:
create_dissonance_matrix = function(articledata, classes) {
d_mtrx = matrix(0, nrow=length(classes), ncol=length(classes));
rownames(d_mtrx) = classes;
colnames(d_mtrx) = classes;
for(real_rating in classes) {
for(pop_rating in classes) {
d_mtrx[real_rating, pop_rating] = length(articledata[prediction == real_rating & pop_class == pop_rating]$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 8407493 1986727 901811 5113 10 D 2150333 381546 242006 4319 10 C 733559 400534 403219 21786 51 B 9769 9405 12108 816 0 A 0 2 5 64 2
In [16]:
dissonance_matrix = create_dissonance_matrix(articles_by_pop,
assessment_classes);
In [17]:
# Total misaligned entities
(dissonance_matrix[1,1]+dissonance_matrix[2,2]+dissonance_matrix[3,3]+dissonance_matrix[4,4]+dissonance_matrix[5,5])/sum(dissonance_matrix[,])
0.586641505465491
In [18]:
# A class quality and A class views over A class quality
dissonance_matrix[5,5]/sum(dissonance_matrix[5,])
0.0273972602739726
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,])
0.0273972602739726
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,])
0.972602739726027
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])
0.972602739726027
In [22]:
prediction_e_pop_class_a <- merge(articles_by_pop[prediction == 'E' & pop_class == 'A'],quality_prediction_and_page_views, by='entity_id')[, c("entity_id","page_views.x", "number_of_revisions")]
In [23]:
head(prediction_e_pop_class_a)
entity_id page_views.x number_of_revisions Q1002972 2045659200 30 Q1200925 2045599162 192 Q156376 2046132338 83 Q1868372 2056080224 45 Q2638147 2045739408 25 Q372827 2045652543 36
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 74.4 17.6 8.0 0.0 0.0 D 77.4 13.7 8.7 0.2 0.0 C 47.0 25.7 25.9 1.4 0.0 B 30.4 29.3 37.7 2.5 0.0 A 0.0 2.7 6.8 87.7 2.7
In [26]:
round(100*prop.table(dissonance_matrix, 2), 1);
E D C B A E 74.4 71.5 57.8 15.9 13.7 D 19.0 13.7 15.5 13.5 13.7 C 6.5 14.4 25.9 67.9 69.9 B 0.1 0.3 0.8 2.5 0.0 A 0.0 0.0 0.0 0.2 2.7
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/201412_a_class_views_less_than_a_quality.tsv', row.names=FALSE, col.names=FALSE, quote=FALSE, sep='\t');
merge(articles_by_pop[(prediction == 'E' | prediction == 'D' | prediction == 'C' | prediction == 'B') & pop_class == 'A'], quality_prediction_and_page_views, by='entity_id')[, c("entity_id","pop_class", "prediction.x")]
entity_id pop_class prediction.x Q1002972 A E Q103204 A C Q1048694 A C Q105584 A C Q1063819 A C Q10726338 A D Q1123836 A D Q116933 A C Q1200925 A E Q1373513 A C Q14005 A D Q150248 A C Q1526131 A C Q156376 A E Q171186 A C Q17299517 A D Q183718 A C Q1868372 A E Q193563 A C Q1967876 A C Q209330 A C Q213678 A C Q219523 A D Q220509 A C Q223142 A C Q245966 A D Q2494649 A C Q2597810 A C Q2629164 A C Q2638147 A E ⋮ ⋮ ⋮ Q4043051 A E Q40629 A C Q41226 A C Q423048 A C Q4299858 A E Q4584301 A D Q477675 A C Q501851 A C Q51044 A C Q523660 A D Q5296 A C Q54919 A C Q565 A C Q568769 A C Q618340 A C Q620946 A C Q623578 A C Q63056 A C Q649227 A C Q6581097 A C Q6883832 A E Q7315186 A E Q732353 A C Q750403 A C Q809830 A C Q829984 A C Q866 A C Q918 A C Q9384291 A D Q953058 A D
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/201412_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/201412_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/201412_misaligned.tsv', row.names=FALSE, col.names=FALSE, quote=FALSE, sep='\t');
In [29]:
## Various ways of measuring dissonance.
## DATA ASSUMPTION: articles_by_pop from build-dissonance-table.R
## is loaded into memory.
## None/Moderate/High measure of dissonance
In [30]:
articles_by_pop[, pop_class := ordered(pop_class, assessment_classes)];
entity_id prediction page_views pop_class seqNum Q10040378 E 0 E 1 Q10069140 E 0 E 2 Q10081695 E 0 E 3 Q10092002 E 0 E 4 Q10111267 E 0 E 5 Q10149726 E 0 E 6 Q10180230 E 0 E 7 Q10185035 E 0 E 8 Q10205202 E 0 E 9 Q10252966 E 0 E 10 Q10444494 D 0 E 11 Q10624171 D 0 E 12 Q10704108 D 0 E 13 Q10750354 E 0 E 14 Q10766855 E 0 E 15 Q10827611 E 0 E 16 Q11093044 E 0 E 17 Q11934537 E 0 E 18 Q12133466 E 0 E 19 Q12264503 E 0 E 20 Q12267516 E 0 E 21 Q12304084 E 0 E 22 Q12443525 E 0 E 23 Q12543904 E 0 E 24 Q12890205 E 0 E 25 Q12891524 E 0 E 26 Q12918202 E 0 E 27 Q13005653 E 0 E 28 Q13073896 E 0 E 29 Q13163823 E 0 E 30 ⋮ ⋮ ⋮ ⋮ ⋮ Q1048694 C 2048095025 A 15670659 Q31165 C 2048330818 A 15670660 Q40629 C 2049755644 A 15670661 Q105584 C 2049926923 A 15670662 Q4584301 D 2052339927 A 15670663 Q565 C 2052996261 A 15670664 Q1868372 E 2056080224 A 15670665 Q209330 C 2060928966 A 15670666 Q14005 D 2063120071 A 15670667 Q918 C 2063217449 A 15670668 Q150248 C 2068796814 A 15670669 Q866 C 2079749157 A 15670670 Q477675 C 2080785713 A 15670671 Q1967876 C 2084215818 A 15670672 Q750403 C 2084693498 A 15670673 Q355 C 2093900731 A 15670674 Q623578 C 2097991400 A 15670675 Q17299517 D 2105487660 A 15670676 Q33999 C 2108672678 A 15670677 Q2494649 C 2114531894 A 15670678 Q2597810 C 2128920607 A 15670679 Q193563 C 2130725560 A 15670680 Q423048 C 2136131564 A 15670681 Q37312 C 2142913121 A 15670682 Q54919 C 2148531382 A 15670683 Q36578 C 2229315598 A 15670684 Q30 A 2277746226 A 15670685 Q6581097 C 3273952711 A 15670686 Q5 A 5668008721 A 15670687 Q5296 C 12530369761 A 15670688
In [31]:
dissonance_metric = c('High negative', 'Moderate negative',
'None', 'Moderate positive', 'High positive');
In [32]:
articles_by_pop[, dissonance := factor(NA, dissonance_metric)];
entity_id prediction page_views pop_class seqNum dissonance Q10040378 E 0 E 1 NA Q10069140 E 0 E 2 NA Q10081695 E 0 E 3 NA Q10092002 E 0 E 4 NA Q10111267 E 0 E 5 NA Q10149726 E 0 E 6 NA Q10180230 E 0 E 7 NA Q10185035 E 0 E 8 NA Q10205202 E 0 E 9 NA Q10252966 E 0 E 10 NA Q10444494 D 0 E 11 NA Q10624171 D 0 E 12 NA Q10704108 D 0 E 13 NA Q10750354 E 0 E 14 NA Q10766855 E 0 E 15 NA Q10827611 E 0 E 16 NA Q11093044 E 0 E 17 NA Q11934537 E 0 E 18 NA Q12133466 E 0 E 19 NA Q12264503 E 0 E 20 NA Q12267516 E 0 E 21 NA Q12304084 E 0 E 22 NA Q12443525 E 0 E 23 NA Q12543904 E 0 E 24 NA Q12890205 E 0 E 25 NA Q12891524 E 0 E 26 NA Q12918202 E 0 E 27 NA Q13005653 E 0 E 28 NA Q13073896 E 0 E 29 NA Q13163823 E 0 E 30 NA ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ Q1048694 C 2048095025 A 15670659 NA Q31165 C 2048330818 A 15670660 NA Q40629 C 2049755644 A 15670661 NA Q105584 C 2049926923 A 15670662 NA Q4584301 D 2052339927 A 15670663 NA Q565 C 2052996261 A 15670664 NA Q1868372 E 2056080224 A 15670665 NA Q209330 C 2060928966 A 15670666 NA Q14005 D 2063120071 A 15670667 NA Q918 C 2063217449 A 15670668 NA Q150248 C 2068796814 A 15670669 NA Q866 C 2079749157 A 15670670 NA Q477675 C 2080785713 A 15670671 NA Q1967876 C 2084215818 A 15670672 NA Q750403 C 2084693498 A 15670673 NA Q355 C 2093900731 A 15670674 NA Q623578 C 2097991400 A 15670675 NA Q17299517 D 2105487660 A 15670676 NA Q33999 C 2108672678 A 15670677 NA Q2494649 C 2114531894 A 15670678 NA Q2597810 C 2128920607 A 15670679 NA Q193563 C 2130725560 A 15670680 NA Q423048 C 2136131564 A 15670681 NA Q37312 C 2142913121 A 15670682 NA Q54919 C 2148531382 A 15670683 NA Q36578 C 2229315598 A 15670684 NA Q30 A 2277746226 A 15670685 NA Q6581097 C 3273952711 A 15670686 NA Q5 A 5668008721 A 15670687 NA Q5296 C 12530369761 A 15670688 NA
In [33]:
## NOTE: because pop_class is of class ordered, we can use
## expressions like "pop_class < 'C'" as expected
In [34]:
## A: None if A, Moderate if A, High elsewhere
articles_by_pop[prediction == 'A' & pop_class <= 'C',
dissonance := 'High negative'];
articles_by_pop[prediction == 'A' & pop_class == 'B',
dissonance := 'Moderate negative'];
articles_by_pop[prediction == 'A' & pop_class == 'A',
dissonance := 'None'];
entity_id prediction page_views pop_class seqNum dissonance Q10040378 E 0 E 1 NA Q10069140 E 0 E 2 NA Q10081695 E 0 E 3 NA Q10092002 E 0 E 4 NA Q10111267 E 0 E 5 NA Q10149726 E 0 E 6 NA Q10180230 E 0 E 7 NA Q10185035 E 0 E 8 NA Q10205202 E 0 E 9 NA Q10252966 E 0 E 10 NA Q10444494 D 0 E 11 NA Q10624171 D 0 E 12 NA Q10704108 D 0 E 13 NA Q10750354 E 0 E 14 NA Q10766855 E 0 E 15 NA Q10827611 E 0 E 16 NA Q11093044 E 0 E 17 NA Q11934537 E 0 E 18 NA Q12133466 E 0 E 19 NA Q12264503 E 0 E 20 NA Q12267516 E 0 E 21 NA Q12304084 E 0 E 22 NA Q12443525 E 0 E 23 NA Q12543904 E 0 E 24 NA Q12890205 E 0 E 25 NA Q12891524 E 0 E 26 NA Q12918202 E 0 E 27 NA Q13005653 E 0 E 28 NA Q13073896 E 0 E 29 NA Q13163823 E 0 E 30 NA ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ Q1048694 C 2048095025 A 15670659 NA Q31165 C 2048330818 A 15670660 NA Q40629 C 2049755644 A 15670661 NA Q105584 C 2049926923 A 15670662 NA Q4584301 D 2052339927 A 15670663 NA Q565 C 2052996261 A 15670664 NA Q1868372 E 2056080224 A 15670665 NA Q209330 C 2060928966 A 15670666 NA Q14005 D 2063120071 A 15670667 NA Q918 C 2063217449 A 15670668 NA Q150248 C 2068796814 A 15670669 NA Q866 C 2079749157 A 15670670 NA Q477675 C 2080785713 A 15670671 NA Q1967876 C 2084215818 A 15670672 NA Q750403 C 2084693498 A 15670673 NA Q355 C 2093900731 A 15670674 NA Q623578 C 2097991400 A 15670675 NA Q17299517 D 2105487660 A 15670676 NA Q33999 C 2108672678 A 15670677 NA Q2494649 C 2114531894 A 15670678 NA Q2597810 C 2128920607 A 15670679 NA Q193563 C 2130725560 A 15670680 NA Q423048 C 2136131564 A 15670681 NA Q37312 C 2142913121 A 15670682 NA Q54919 C 2148531382 A 15670683 NA Q36578 C 2229315598 A 15670684 NA Q30 A 2277746226 A 15670685 NA Q6581097 C 3273952711 A 15670686 NA Q5 A 5668008721 A 15670687 NA Q5296 C 12530369761 A 15670688 NA
entity_id prediction page_views pop_class seqNum dissonance Q10040378 E 0 E 1 NA Q10069140 E 0 E 2 NA Q10081695 E 0 E 3 NA Q10092002 E 0 E 4 NA Q10111267 E 0 E 5 NA Q10149726 E 0 E 6 NA Q10180230 E 0 E 7 NA Q10185035 E 0 E 8 NA Q10205202 E 0 E 9 NA Q10252966 E 0 E 10 NA Q10444494 D 0 E 11 NA Q10624171 D 0 E 12 NA Q10704108 D 0 E 13 NA Q10750354 E 0 E 14 NA Q10766855 E 0 E 15 NA Q10827611 E 0 E 16 NA Q11093044 E 0 E 17 NA Q11934537 E 0 E 18 NA Q12133466 E 0 E 19 NA Q12264503 E 0 E 20 NA Q12267516 E 0 E 21 NA Q12304084 E 0 E 22 NA Q12443525 E 0 E 23 NA Q12543904 E 0 E 24 NA Q12890205 E 0 E 25 NA Q12891524 E 0 E 26 NA Q12918202 E 0 E 27 NA Q13005653 E 0 E 28 NA Q13073896 E 0 E 29 NA Q13163823 E 0 E 30 NA ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ Q1048694 C 2048095025 A 15670659 NA Q31165 C 2048330818 A 15670660 NA Q40629 C 2049755644 A 15670661 NA Q105584 C 2049926923 A 15670662 NA Q4584301 D 2052339927 A 15670663 NA Q565 C 2052996261 A 15670664 NA Q1868372 E 2056080224 A 15670665 NA Q209330 C 2060928966 A 15670666 NA Q14005 D 2063120071 A 15670667 NA Q918 C 2063217449 A 15670668 NA Q150248 C 2068796814 A 15670669 NA Q866 C 2079749157 A 15670670 NA Q477675 C 2080785713 A 15670671 NA Q1967876 C 2084215818 A 15670672 NA Q750403 C 2084693498 A 15670673 NA Q355 C 2093900731 A 15670674 NA Q623578 C 2097991400 A 15670675 NA Q17299517 D 2105487660 A 15670676 NA Q33999 C 2108672678 A 15670677 NA Q2494649 C 2114531894 A 15670678 NA Q2597810 C 2128920607 A 15670679 NA Q193563 C 2130725560 A 15670680 NA Q423048 C 2136131564 A 15670681 NA Q37312 C 2142913121 A 15670682 NA Q54919 C 2148531382 A 15670683 NA Q36578 C 2229315598 A 15670684 NA Q30 A 2277746226 A 15670685 NA Q6581097 C 3273952711 A 15670686 NA Q5 A 5668008721 A 15670687 NA Q5296 C 12530369761 A 15670688 NA
entity_id prediction page_views pop_class seqNum dissonance Q10040378 E 0 E 1 NA Q10069140 E 0 E 2 NA Q10081695 E 0 E 3 NA Q10092002 E 0 E 4 NA Q10111267 E 0 E 5 NA Q10149726 E 0 E 6 NA Q10180230 E 0 E 7 NA Q10185035 E 0 E 8 NA Q10205202 E 0 E 9 NA Q10252966 E 0 E 10 NA Q10444494 D 0 E 11 NA Q10624171 D 0 E 12 NA Q10704108 D 0 E 13 NA Q10750354 E 0 E 14 NA Q10766855 E 0 E 15 NA Q10827611 E 0 E 16 NA Q11093044 E 0 E 17 NA Q11934537 E 0 E 18 NA Q12133466 E 0 E 19 NA Q12264503 E 0 E 20 NA Q12267516 E 0 E 21 NA Q12304084 E 0 E 22 NA Q12443525 E 0 E 23 NA Q12543904 E 0 E 24 NA Q12890205 E 0 E 25 NA Q12891524 E 0 E 26 NA Q12918202 E 0 E 27 NA Q13005653 E 0 E 28 NA Q13073896 E 0 E 29 NA Q13163823 E 0 E 30 NA ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ Q1048694 C 2048095025 A 15670659 NA Q31165 C 2048330818 A 15670660 NA Q40629 C 2049755644 A 15670661 NA Q105584 C 2049926923 A 15670662 NA Q4584301 D 2052339927 A 15670663 NA Q565 C 2052996261 A 15670664 NA Q1868372 E 2056080224 A 15670665 NA Q209330 C 2060928966 A 15670666 NA Q14005 D 2063120071 A 15670667 NA Q918 C 2063217449 A 15670668 NA Q150248 C 2068796814 A 15670669 NA Q866 C 2079749157 A 15670670 NA Q477675 C 2080785713 A 15670671 NA Q1967876 C 2084215818 A 15670672 NA Q750403 C 2084693498 A 15670673 NA Q355 C 2093900731 A 15670674 NA Q623578 C 2097991400 A 15670675 NA Q17299517 D 2105487660 A 15670676 NA Q33999 C 2108672678 A 15670677 NA Q2494649 C 2114531894 A 15670678 NA Q2597810 C 2128920607 A 15670679 NA Q193563 C 2130725560 A 15670680 NA Q423048 C 2136131564 A 15670681 NA Q37312 C 2142913121 A 15670682 NA Q54919 C 2148531382 A 15670683 NA Q36578 C 2229315598 A 15670684 NA Q30 A 2277746226 A 15670685 None Q6581097 C 3273952711 A 15670686 NA Q5 A 5668008721 A 15670687 None Q5296 C 12530369761 A 15670688 NA
In [35]:
## B:
articles_by_pop[prediction == 'B' & pop_class <= 'D',
dissonance := 'High negative'];
articles_by_pop[prediction == 'B' & pop_class == 'C',
dissonance := 'Moderate negative'];
articles_by_pop[prediction == 'B' & pop_class == 'B',
dissonance := 'None'];
articles_by_pop[prediction == 'B' & pop_class == 'A',
dissonance := 'Moderate positive'];
entity_id prediction page_views pop_class seqNum dissonance Q10040378 E 0 E 1 NA Q10069140 E 0 E 2 NA Q10081695 E 0 E 3 NA Q10092002 E 0 E 4 NA Q10111267 E 0 E 5 NA Q10149726 E 0 E 6 NA Q10180230 E 0 E 7 NA Q10185035 E 0 E 8 NA Q10205202 E 0 E 9 NA Q10252966 E 0 E 10 NA Q10444494 D 0 E 11 NA Q10624171 D 0 E 12 NA Q10704108 D 0 E 13 NA Q10750354 E 0 E 14 NA Q10766855 E 0 E 15 NA Q10827611 E 0 E 16 NA Q11093044 E 0 E 17 NA Q11934537 E 0 E 18 NA Q12133466 E 0 E 19 NA Q12264503 E 0 E 20 NA Q12267516 E 0 E 21 NA Q12304084 E 0 E 22 NA Q12443525 E 0 E 23 NA Q12543904 E 0 E 24 NA Q12890205 E 0 E 25 NA Q12891524 E 0 E 26 NA Q12918202 E 0 E 27 NA Q13005653 E 0 E 28 NA Q13073896 E 0 E 29 NA Q13163823 E 0 E 30 NA ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ Q1048694 C 2048095025 A 15670659 NA Q31165 C 2048330818 A 15670660 NA Q40629 C 2049755644 A 15670661 NA Q105584 C 2049926923 A 15670662 NA Q4584301 D 2052339927 A 15670663 NA Q565 C 2052996261 A 15670664 NA Q1868372 E 2056080224 A 15670665 NA Q209330 C 2060928966 A 15670666 NA Q14005 D 2063120071 A 15670667 NA Q918 C 2063217449 A 15670668 NA Q150248 C 2068796814 A 15670669 NA Q866 C 2079749157 A 15670670 NA Q477675 C 2080785713 A 15670671 NA Q1967876 C 2084215818 A 15670672 NA Q750403 C 2084693498 A 15670673 NA Q355 C 2093900731 A 15670674 NA Q623578 C 2097991400 A 15670675 NA Q17299517 D 2105487660 A 15670676 NA Q33999 C 2108672678 A 15670677 NA Q2494649 C 2114531894 A 15670678 NA Q2597810 C 2128920607 A 15670679 NA Q193563 C 2130725560 A 15670680 NA Q423048 C 2136131564 A 15670681 NA Q37312 C 2142913121 A 15670682 NA Q54919 C 2148531382 A 15670683 NA Q36578 C 2229315598 A 15670684 NA Q30 A 2277746226 A 15670685 None Q6581097 C 3273952711 A 15670686 NA Q5 A 5668008721 A 15670687 None Q5296 C 12530369761 A 15670688 NA
entity_id prediction page_views pop_class seqNum dissonance Q10040378 E 0 E 1 NA Q10069140 E 0 E 2 NA Q10081695 E 0 E 3 NA Q10092002 E 0 E 4 NA Q10111267 E 0 E 5 NA Q10149726 E 0 E 6 NA Q10180230 E 0 E 7 NA Q10185035 E 0 E 8 NA Q10205202 E 0 E 9 NA Q10252966 E 0 E 10 NA Q10444494 D 0 E 11 NA Q10624171 D 0 E 12 NA Q10704108 D 0 E 13 NA Q10750354 E 0 E 14 NA Q10766855 E 0 E 15 NA Q10827611 E 0 E 16 NA Q11093044 E 0 E 17 NA Q11934537 E 0 E 18 NA Q12133466 E 0 E 19 NA Q12264503 E 0 E 20 NA Q12267516 E 0 E 21 NA Q12304084 E 0 E 22 NA Q12443525 E 0 E 23 NA Q12543904 E 0 E 24 NA Q12890205 E 0 E 25 NA Q12891524 E 0 E 26 NA Q12918202 E 0 E 27 NA Q13005653 E 0 E 28 NA Q13073896 E 0 E 29 NA Q13163823 E 0 E 30 NA ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ Q1048694 C 2048095025 A 15670659 NA Q31165 C 2048330818 A 15670660 NA Q40629 C 2049755644 A 15670661 NA Q105584 C 2049926923 A 15670662 NA Q4584301 D 2052339927 A 15670663 NA Q565 C 2052996261 A 15670664 NA Q1868372 E 2056080224 A 15670665 NA Q209330 C 2060928966 A 15670666 NA Q14005 D 2063120071 A 15670667 NA Q918 C 2063217449 A 15670668 NA Q150248 C 2068796814 A 15670669 NA Q866 C 2079749157 A 15670670 NA Q477675 C 2080785713 A 15670671 NA Q1967876 C 2084215818 A 15670672 NA Q750403 C 2084693498 A 15670673 NA Q355 C 2093900731 A 15670674 NA Q623578 C 2097991400 A 15670675 NA Q17299517 D 2105487660 A 15670676 NA Q33999 C 2108672678 A 15670677 NA Q2494649 C 2114531894 A 15670678 NA Q2597810 C 2128920607 A 15670679 NA Q193563 C 2130725560 A 15670680 NA Q423048 C 2136131564 A 15670681 NA Q37312 C 2142913121 A 15670682 NA Q54919 C 2148531382 A 15670683 NA Q36578 C 2229315598 A 15670684 NA Q30 A 2277746226 A 15670685 None Q6581097 C 3273952711 A 15670686 NA Q5 A 5668008721 A 15670687 None Q5296 C 12530369761 A 15670688 NA
entity_id prediction page_views pop_class seqNum dissonance Q10040378 E 0 E 1 NA Q10069140 E 0 E 2 NA Q10081695 E 0 E 3 NA Q10092002 E 0 E 4 NA Q10111267 E 0 E 5 NA Q10149726 E 0 E 6 NA Q10180230 E 0 E 7 NA Q10185035 E 0 E 8 NA Q10205202 E 0 E 9 NA Q10252966 E 0 E 10 NA Q10444494 D 0 E 11 NA Q10624171 D 0 E 12 NA Q10704108 D 0 E 13 NA Q10750354 E 0 E 14 NA Q10766855 E 0 E 15 NA Q10827611 E 0 E 16 NA Q11093044 E 0 E 17 NA Q11934537 E 0 E 18 NA Q12133466 E 0 E 19 NA Q12264503 E 0 E 20 NA Q12267516 E 0 E 21 NA Q12304084 E 0 E 22 NA Q12443525 E 0 E 23 NA Q12543904 E 0 E 24 NA Q12890205 E 0 E 25 NA Q12891524 E 0 E 26 NA Q12918202 E 0 E 27 NA Q13005653 E 0 E 28 NA Q13073896 E 0 E 29 NA Q13163823 E 0 E 30 NA ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ Q1048694 C 2048095025 A 15670659 NA Q31165 C 2048330818 A 15670660 NA Q40629 C 2049755644 A 15670661 NA Q105584 C 2049926923 A 15670662 NA Q4584301 D 2052339927 A 15670663 NA Q565 C 2052996261 A 15670664 NA Q1868372 E 2056080224 A 15670665 NA Q209330 C 2060928966 A 15670666 NA Q14005 D 2063120071 A 15670667 NA Q918 C 2063217449 A 15670668 NA Q150248 C 2068796814 A 15670669 NA Q866 C 2079749157 A 15670670 NA Q477675 C 2080785713 A 15670671 NA Q1967876 C 2084215818 A 15670672 NA Q750403 C 2084693498 A 15670673 NA Q355 C 2093900731 A 15670674 NA Q623578 C 2097991400 A 15670675 NA Q17299517 D 2105487660 A 15670676 NA Q33999 C 2108672678 A 15670677 NA Q2494649 C 2114531894 A 15670678 NA Q2597810 C 2128920607 A 15670679 NA Q193563 C 2130725560 A 15670680 NA Q423048 C 2136131564 A 15670681 NA Q37312 C 2142913121 A 15670682 NA Q54919 C 2148531382 A 15670683 NA Q36578 C 2229315598 A 15670684 NA Q30 A 2277746226 A 15670685 None Q6581097 C 3273952711 A 15670686 NA Q5 A 5668008721 A 15670687 None Q5296 C 12530369761 A 15670688 NA
entity_id prediction page_views pop_class seqNum dissonance Q10040378 E 0 E 1 NA Q10069140 E 0 E 2 NA Q10081695 E 0 E 3 NA Q10092002 E 0 E 4 NA Q10111267 E 0 E 5 NA Q10149726 E 0 E 6 NA Q10180230 E 0 E 7 NA Q10185035 E 0 E 8 NA Q10205202 E 0 E 9 NA Q10252966 E 0 E 10 NA Q10444494 D 0 E 11 NA Q10624171 D 0 E 12 NA Q10704108 D 0 E 13 NA Q10750354 E 0 E 14 NA Q10766855 E 0 E 15 NA Q10827611 E 0 E 16 NA Q11093044 E 0 E 17 NA Q11934537 E 0 E 18 NA Q12133466 E 0 E 19 NA Q12264503 E 0 E 20 NA Q12267516 E 0 E 21 NA Q12304084 E 0 E 22 NA Q12443525 E 0 E 23 NA Q12543904 E 0 E 24 NA Q12890205 E 0 E 25 NA Q12891524 E 0 E 26 NA Q12918202 E 0 E 27 NA Q13005653 E 0 E 28 NA Q13073896 E 0 E 29 NA Q13163823 E 0 E 30 NA ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ Q1048694 C 2048095025 A 15670659 NA Q31165 C 2048330818 A 15670660 NA Q40629 C 2049755644 A 15670661 NA Q105584 C 2049926923 A 15670662 NA Q4584301 D 2052339927 A 15670663 NA Q565 C 2052996261 A 15670664 NA Q1868372 E 2056080224 A 15670665 NA Q209330 C 2060928966 A 15670666 NA Q14005 D 2063120071 A 15670667 NA Q918 C 2063217449 A 15670668 NA Q150248 C 2068796814 A 15670669 NA Q866 C 2079749157 A 15670670 NA Q477675 C 2080785713 A 15670671 NA Q1967876 C 2084215818 A 15670672 NA Q750403 C 2084693498 A 15670673 NA Q355 C 2093900731 A 15670674 NA Q623578 C 2097991400 A 15670675 NA Q17299517 D 2105487660 A 15670676 NA Q33999 C 2108672678 A 15670677 NA Q2494649 C 2114531894 A 15670678 NA Q2597810 C 2128920607 A 15670679 NA Q193563 C 2130725560 A 15670680 NA Q423048 C 2136131564 A 15670681 NA Q37312 C 2142913121 A 15670682 NA Q54919 C 2148531382 A 15670683 NA Q36578 C 2229315598 A 15670684 NA Q30 A 2277746226 A 15670685 None Q6581097 C 3273952711 A 15670686 NA Q5 A 5668008721 A 15670687 None Q5296 C 12530369761 A 15670688 NA
In [36]:
## C:
articles_by_pop[prediction == 'C' & pop_class == 'E',
dissonance := 'High negative'];
articles_by_pop[prediction == 'C' & pop_class == 'D',
dissonance := 'Moderate negative'];
articles_by_pop[prediction == 'C' & pop_class == 'C',
dissonance := 'None'];
articles_by_pop[prediction == 'C' & pop_class == 'B',
dissonance := 'Moderate positive'];
articles_by_pop[prediction == 'C' & pop_class == 'A',
dissonance := 'High positive'];
entity_id prediction page_views pop_class seqNum dissonance Q10040378 E 0 E 1 NA Q10069140 E 0 E 2 NA Q10081695 E 0 E 3 NA Q10092002 E 0 E 4 NA Q10111267 E 0 E 5 NA Q10149726 E 0 E 6 NA Q10180230 E 0 E 7 NA Q10185035 E 0 E 8 NA Q10205202 E 0 E 9 NA Q10252966 E 0 E 10 NA Q10444494 D 0 E 11 NA Q10624171 D 0 E 12 NA Q10704108 D 0 E 13 NA Q10750354 E 0 E 14 NA Q10766855 E 0 E 15 NA Q10827611 E 0 E 16 NA Q11093044 E 0 E 17 NA Q11934537 E 0 E 18 NA Q12133466 E 0 E 19 NA Q12264503 E 0 E 20 NA Q12267516 E 0 E 21 NA Q12304084 E 0 E 22 NA Q12443525 E 0 E 23 NA Q12543904 E 0 E 24 NA Q12890205 E 0 E 25 NA Q12891524 E 0 E 26 NA Q12918202 E 0 E 27 NA Q13005653 E 0 E 28 NA Q13073896 E 0 E 29 NA Q13163823 E 0 E 30 NA ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ Q1048694 C 2048095025 A 15670659 NA Q31165 C 2048330818 A 15670660 NA Q40629 C 2049755644 A 15670661 NA Q105584 C 2049926923 A 15670662 NA Q4584301 D 2052339927 A 15670663 NA Q565 C 2052996261 A 15670664 NA Q1868372 E 2056080224 A 15670665 NA Q209330 C 2060928966 A 15670666 NA Q14005 D 2063120071 A 15670667 NA Q918 C 2063217449 A 15670668 NA Q150248 C 2068796814 A 15670669 NA Q866 C 2079749157 A 15670670 NA Q477675 C 2080785713 A 15670671 NA Q1967876 C 2084215818 A 15670672 NA Q750403 C 2084693498 A 15670673 NA Q355 C 2093900731 A 15670674 NA Q623578 C 2097991400 A 15670675 NA Q17299517 D 2105487660 A 15670676 NA Q33999 C 2108672678 A 15670677 NA Q2494649 C 2114531894 A 15670678 NA Q2597810 C 2128920607 A 15670679 NA Q193563 C 2130725560 A 15670680 NA Q423048 C 2136131564 A 15670681 NA Q37312 C 2142913121 A 15670682 NA Q54919 C 2148531382 A 15670683 NA Q36578 C 2229315598 A 15670684 NA Q30 A 2277746226 A 15670685 None Q6581097 C 3273952711 A 15670686 NA Q5 A 5668008721 A 15670687 None Q5296 C 12530369761 A 15670688 NA
entity_id prediction page_views pop_class seqNum dissonance Q10040378 E 0 E 1 NA Q10069140 E 0 E 2 NA Q10081695 E 0 E 3 NA Q10092002 E 0 E 4 NA Q10111267 E 0 E 5 NA Q10149726 E 0 E 6 NA Q10180230 E 0 E 7 NA Q10185035 E 0 E 8 NA Q10205202 E 0 E 9 NA Q10252966 E 0 E 10 NA Q10444494 D 0 E 11 NA Q10624171 D 0 E 12 NA Q10704108 D 0 E 13 NA Q10750354 E 0 E 14 NA Q10766855 E 0 E 15 NA Q10827611 E 0 E 16 NA Q11093044 E 0 E 17 NA Q11934537 E 0 E 18 NA Q12133466 E 0 E 19 NA Q12264503 E 0 E 20 NA Q12267516 E 0 E 21 NA Q12304084 E 0 E 22 NA Q12443525 E 0 E 23 NA Q12543904 E 0 E 24 NA Q12890205 E 0 E 25 NA Q12891524 E 0 E 26 NA Q12918202 E 0 E 27 NA Q13005653 E 0 E 28 NA Q13073896 E 0 E 29 NA Q13163823 E 0 E 30 NA ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ Q1048694 C 2048095025 A 15670659 NA Q31165 C 2048330818 A 15670660 NA Q40629 C 2049755644 A 15670661 NA Q105584 C 2049926923 A 15670662 NA Q4584301 D 2052339927 A 15670663 NA Q565 C 2052996261 A 15670664 NA Q1868372 E 2056080224 A 15670665 NA Q209330 C 2060928966 A 15670666 NA Q14005 D 2063120071 A 15670667 NA Q918 C 2063217449 A 15670668 NA Q150248 C 2068796814 A 15670669 NA Q866 C 2079749157 A 15670670 NA Q477675 C 2080785713 A 15670671 NA Q1967876 C 2084215818 A 15670672 NA Q750403 C 2084693498 A 15670673 NA Q355 C 2093900731 A 15670674 NA Q623578 C 2097991400 A 15670675 NA Q17299517 D 2105487660 A 15670676 NA Q33999 C 2108672678 A 15670677 NA Q2494649 C 2114531894 A 15670678 NA Q2597810 C 2128920607 A 15670679 NA Q193563 C 2130725560 A 15670680 NA Q423048 C 2136131564 A 15670681 NA Q37312 C 2142913121 A 15670682 NA Q54919 C 2148531382 A 15670683 NA Q36578 C 2229315598 A 15670684 NA Q30 A 2277746226 A 15670685 None Q6581097 C 3273952711 A 15670686 NA Q5 A 5668008721 A 15670687 None Q5296 C 12530369761 A 15670688 NA
entity_id prediction page_views pop_class seqNum dissonance Q10040378 E 0 E 1 NA Q10069140 E 0 E 2 NA Q10081695 E 0 E 3 NA Q10092002 E 0 E 4 NA Q10111267 E 0 E 5 NA Q10149726 E 0 E 6 NA Q10180230 E 0 E 7 NA Q10185035 E 0 E 8 NA Q10205202 E 0 E 9 NA Q10252966 E 0 E 10 NA Q10444494 D 0 E 11 NA Q10624171 D 0 E 12 NA Q10704108 D 0 E 13 NA Q10750354 E 0 E 14 NA Q10766855 E 0 E 15 NA Q10827611 E 0 E 16 NA Q11093044 E 0 E 17 NA Q11934537 E 0 E 18 NA Q12133466 E 0 E 19 NA Q12264503 E 0 E 20 NA Q12267516 E 0 E 21 NA Q12304084 E 0 E 22 NA Q12443525 E 0 E 23 NA Q12543904 E 0 E 24 NA Q12890205 E 0 E 25 NA Q12891524 E 0 E 26 NA Q12918202 E 0 E 27 NA Q13005653 E 0 E 28 NA Q13073896 E 0 E 29 NA Q13163823 E 0 E 30 NA ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ Q1048694 C 2048095025 A 15670659 NA Q31165 C 2048330818 A 15670660 NA Q40629 C 2049755644 A 15670661 NA Q105584 C 2049926923 A 15670662 NA Q4584301 D 2052339927 A 15670663 NA Q565 C 2052996261 A 15670664 NA Q1868372 E 2056080224 A 15670665 NA Q209330 C 2060928966 A 15670666 NA Q14005 D 2063120071 A 15670667 NA Q918 C 2063217449 A 15670668 NA Q150248 C 2068796814 A 15670669 NA Q866 C 2079749157 A 15670670 NA Q477675 C 2080785713 A 15670671 NA Q1967876 C 2084215818 A 15670672 NA Q750403 C 2084693498 A 15670673 NA Q355 C 2093900731 A 15670674 NA Q623578 C 2097991400 A 15670675 NA Q17299517 D 2105487660 A 15670676 NA Q33999 C 2108672678 A 15670677 NA Q2494649 C 2114531894 A 15670678 NA Q2597810 C 2128920607 A 15670679 NA Q193563 C 2130725560 A 15670680 NA Q423048 C 2136131564 A 15670681 NA Q37312 C 2142913121 A 15670682 NA Q54919 C 2148531382 A 15670683 NA Q36578 C 2229315598 A 15670684 NA Q30 A 2277746226 A 15670685 None Q6581097 C 3273952711 A 15670686 NA Q5 A 5668008721 A 15670687 None Q5296 C 12530369761 A 15670688 NA
entity_id prediction page_views pop_class seqNum dissonance Q10040378 E 0 E 1 NA Q10069140 E 0 E 2 NA Q10081695 E 0 E 3 NA Q10092002 E 0 E 4 NA Q10111267 E 0 E 5 NA Q10149726 E 0 E 6 NA Q10180230 E 0 E 7 NA Q10185035 E 0 E 8 NA Q10205202 E 0 E 9 NA Q10252966 E 0 E 10 NA Q10444494 D 0 E 11 NA Q10624171 D 0 E 12 NA Q10704108 D 0 E 13 NA Q10750354 E 0 E 14 NA Q10766855 E 0 E 15 NA Q10827611 E 0 E 16 NA Q11093044 E 0 E 17 NA Q11934537 E 0 E 18 NA Q12133466 E 0 E 19 NA Q12264503 E 0 E 20 NA Q12267516 E 0 E 21 NA Q12304084 E 0 E 22 NA Q12443525 E 0 E 23 NA Q12543904 E 0 E 24 NA Q12890205 E 0 E 25 NA Q12891524 E 0 E 26 NA Q12918202 E 0 E 27 NA Q13005653 E 0 E 28 NA Q13073896 E 0 E 29 NA Q13163823 E 0 E 30 NA ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ Q1048694 C 2048095025 A 15670659 NA Q31165 C 2048330818 A 15670660 NA Q40629 C 2049755644 A 15670661 NA Q105584 C 2049926923 A 15670662 NA Q4584301 D 2052339927 A 15670663 NA Q565 C 2052996261 A 15670664 NA Q1868372 E 2056080224 A 15670665 NA Q209330 C 2060928966 A 15670666 NA Q14005 D 2063120071 A 15670667 NA Q918 C 2063217449 A 15670668 NA Q150248 C 2068796814 A 15670669 NA Q866 C 2079749157 A 15670670 NA Q477675 C 2080785713 A 15670671 NA Q1967876 C 2084215818 A 15670672 NA Q750403 C 2084693498 A 15670673 NA Q355 C 2093900731 A 15670674 NA Q623578 C 2097991400 A 15670675 NA Q17299517 D 2105487660 A 15670676 NA Q33999 C 2108672678 A 15670677 NA Q2494649 C 2114531894 A 15670678 NA Q2597810 C 2128920607 A 15670679 NA Q193563 C 2130725560 A 15670680 NA Q423048 C 2136131564 A 15670681 NA Q37312 C 2142913121 A 15670682 NA Q54919 C 2148531382 A 15670683 NA Q36578 C 2229315598 A 15670684 NA Q30 A 2277746226 A 15670685 None Q6581097 C 3273952711 A 15670686 NA Q5 A 5668008721 A 15670687 None Q5296 C 12530369761 A 15670688 NA
entity_id prediction page_views pop_class seqNum dissonance Q10040378 E 0 E 1 NA Q10069140 E 0 E 2 NA Q10081695 E 0 E 3 NA Q10092002 E 0 E 4 NA Q10111267 E 0 E 5 NA Q10149726 E 0 E 6 NA Q10180230 E 0 E 7 NA Q10185035 E 0 E 8 NA Q10205202 E 0 E 9 NA Q10252966 E 0 E 10 NA Q10444494 D 0 E 11 NA Q10624171 D 0 E 12 NA Q10704108 D 0 E 13 NA Q10750354 E 0 E 14 NA Q10766855 E 0 E 15 NA Q10827611 E 0 E 16 NA Q11093044 E 0 E 17 NA Q11934537 E 0 E 18 NA Q12133466 E 0 E 19 NA Q12264503 E 0 E 20 NA Q12267516 E 0 E 21 NA Q12304084 E 0 E 22 NA Q12443525 E 0 E 23 NA Q12543904 E 0 E 24 NA Q12890205 E 0 E 25 NA Q12891524 E 0 E 26 NA Q12918202 E 0 E 27 NA Q13005653 E 0 E 28 NA Q13073896 E 0 E 29 NA Q13163823 E 0 E 30 NA ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ Q1048694 C 2048095025 A 15670659 High positive Q31165 C 2048330818 A 15670660 High positive Q40629 C 2049755644 A 15670661 High positive Q105584 C 2049926923 A 15670662 High positive Q4584301 D 2052339927 A 15670663 NA Q565 C 2052996261 A 15670664 High positive Q1868372 E 2056080224 A 15670665 NA Q209330 C 2060928966 A 15670666 High positive Q14005 D 2063120071 A 15670667 NA Q918 C 2063217449 A 15670668 High positive Q150248 C 2068796814 A 15670669 High positive Q866 C 2079749157 A 15670670 High positive Q477675 C 2080785713 A 15670671 High positive Q1967876 C 2084215818 A 15670672 High positive Q750403 C 2084693498 A 15670673 High positive Q355 C 2093900731 A 15670674 High positive Q623578 C 2097991400 A 15670675 High positive Q17299517 D 2105487660 A 15670676 NA Q33999 C 2108672678 A 15670677 High positive Q2494649 C 2114531894 A 15670678 High positive Q2597810 C 2128920607 A 15670679 High positive Q193563 C 2130725560 A 15670680 High positive Q423048 C 2136131564 A 15670681 High positive Q37312 C 2142913121 A 15670682 High positive Q54919 C 2148531382 A 15670683 High positive Q36578 C 2229315598 A 15670684 High positive Q30 A 2277746226 A 15670685 None Q6581097 C 3273952711 A 15670686 High positive Q5 A 5668008721 A 15670687 None Q5296 C 12530369761 A 15670688 High positive
In [37]:
## D
articles_by_pop[prediction == 'D' & pop_class == 'E',
dissonance := 'Moderate negative'];
articles_by_pop[prediction == 'D' & pop_class == 'D',
dissonance := 'None'];
articles_by_pop[prediction == 'D' & pop_class == 'C',
dissonance := 'Moderate positive'];
articles_by_pop[prediction == 'D' & pop_class >= 'B',
dissonance := 'High positive'];
entity_id prediction page_views pop_class seqNum dissonance Q10040378 E 0 E 1 NA Q10069140 E 0 E 2 NA Q10081695 E 0 E 3 NA Q10092002 E 0 E 4 NA Q10111267 E 0 E 5 NA Q10149726 E 0 E 6 NA Q10180230 E 0 E 7 NA Q10185035 E 0 E 8 NA Q10205202 E 0 E 9 NA Q10252966 E 0 E 10 NA Q10444494 D 0 E 11 Moderate negative Q10624171 D 0 E 12 Moderate negative Q10704108 D 0 E 13 Moderate negative Q10750354 E 0 E 14 NA Q10766855 E 0 E 15 NA Q10827611 E 0 E 16 NA Q11093044 E 0 E 17 NA Q11934537 E 0 E 18 NA Q12133466 E 0 E 19 NA Q12264503 E 0 E 20 NA Q12267516 E 0 E 21 NA Q12304084 E 0 E 22 NA Q12443525 E 0 E 23 NA Q12543904 E 0 E 24 NA Q12890205 E 0 E 25 NA Q12891524 E 0 E 26 NA Q12918202 E 0 E 27 NA Q13005653 E 0 E 28 NA Q13073896 E 0 E 29 NA Q13163823 E 0 E 30 NA ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ Q1048694 C 2048095025 A 15670659 High positive Q31165 C 2048330818 A 15670660 High positive Q40629 C 2049755644 A 15670661 High positive Q105584 C 2049926923 A 15670662 High positive Q4584301 D 2052339927 A 15670663 NA Q565 C 2052996261 A 15670664 High positive Q1868372 E 2056080224 A 15670665 NA Q209330 C 2060928966 A 15670666 High positive Q14005 D 2063120071 A 15670667 NA Q918 C 2063217449 A 15670668 High positive Q150248 C 2068796814 A 15670669 High positive Q866 C 2079749157 A 15670670 High positive Q477675 C 2080785713 A 15670671 High positive Q1967876 C 2084215818 A 15670672 High positive Q750403 C 2084693498 A 15670673 High positive Q355 C 2093900731 A 15670674 High positive Q623578 C 2097991400 A 15670675 High positive Q17299517 D 2105487660 A 15670676 NA Q33999 C 2108672678 A 15670677 High positive Q2494649 C 2114531894 A 15670678 High positive Q2597810 C 2128920607 A 15670679 High positive Q193563 C 2130725560 A 15670680 High positive Q423048 C 2136131564 A 15670681 High positive Q37312 C 2142913121 A 15670682 High positive Q54919 C 2148531382 A 15670683 High positive Q36578 C 2229315598 A 15670684 High positive Q30 A 2277746226 A 15670685 None Q6581097 C 3273952711 A 15670686 High positive Q5 A 5668008721 A 15670687 None Q5296 C 12530369761 A 15670688 High positive
entity_id prediction page_views pop_class seqNum dissonance Q10040378 E 0 E 1 NA Q10069140 E 0 E 2 NA Q10081695 E 0 E 3 NA Q10092002 E 0 E 4 NA Q10111267 E 0 E 5 NA Q10149726 E 0 E 6 NA Q10180230 E 0 E 7 NA Q10185035 E 0 E 8 NA Q10205202 E 0 E 9 NA Q10252966 E 0 E 10 NA Q10444494 D 0 E 11 Moderate negative Q10624171 D 0 E 12 Moderate negative Q10704108 D 0 E 13 Moderate negative Q10750354 E 0 E 14 NA Q10766855 E 0 E 15 NA Q10827611 E 0 E 16 NA Q11093044 E 0 E 17 NA Q11934537 E 0 E 18 NA Q12133466 E 0 E 19 NA Q12264503 E 0 E 20 NA Q12267516 E 0 E 21 NA Q12304084 E 0 E 22 NA Q12443525 E 0 E 23 NA Q12543904 E 0 E 24 NA Q12890205 E 0 E 25 NA Q12891524 E 0 E 26 NA Q12918202 E 0 E 27 NA Q13005653 E 0 E 28 NA Q13073896 E 0 E 29 NA Q13163823 E 0 E 30 NA ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ Q1048694 C 2048095025 A 15670659 High positive Q31165 C 2048330818 A 15670660 High positive Q40629 C 2049755644 A 15670661 High positive Q105584 C 2049926923 A 15670662 High positive Q4584301 D 2052339927 A 15670663 NA Q565 C 2052996261 A 15670664 High positive Q1868372 E 2056080224 A 15670665 NA Q209330 C 2060928966 A 15670666 High positive Q14005 D 2063120071 A 15670667 NA Q918 C 2063217449 A 15670668 High positive Q150248 C 2068796814 A 15670669 High positive Q866 C 2079749157 A 15670670 High positive Q477675 C 2080785713 A 15670671 High positive Q1967876 C 2084215818 A 15670672 High positive Q750403 C 2084693498 A 15670673 High positive Q355 C 2093900731 A 15670674 High positive Q623578 C 2097991400 A 15670675 High positive Q17299517 D 2105487660 A 15670676 NA Q33999 C 2108672678 A 15670677 High positive Q2494649 C 2114531894 A 15670678 High positive Q2597810 C 2128920607 A 15670679 High positive Q193563 C 2130725560 A 15670680 High positive Q423048 C 2136131564 A 15670681 High positive Q37312 C 2142913121 A 15670682 High positive Q54919 C 2148531382 A 15670683 High positive Q36578 C 2229315598 A 15670684 High positive Q30 A 2277746226 A 15670685 None Q6581097 C 3273952711 A 15670686 High positive Q5 A 5668008721 A 15670687 None Q5296 C 12530369761 A 15670688 High positive
entity_id prediction page_views pop_class seqNum dissonance Q10040378 E 0 E 1 NA Q10069140 E 0 E 2 NA Q10081695 E 0 E 3 NA Q10092002 E 0 E 4 NA Q10111267 E 0 E 5 NA Q10149726 E 0 E 6 NA Q10180230 E 0 E 7 NA Q10185035 E 0 E 8 NA Q10205202 E 0 E 9 NA Q10252966 E 0 E 10 NA Q10444494 D 0 E 11 Moderate negative Q10624171 D 0 E 12 Moderate negative Q10704108 D 0 E 13 Moderate negative Q10750354 E 0 E 14 NA Q10766855 E 0 E 15 NA Q10827611 E 0 E 16 NA Q11093044 E 0 E 17 NA Q11934537 E 0 E 18 NA Q12133466 E 0 E 19 NA Q12264503 E 0 E 20 NA Q12267516 E 0 E 21 NA Q12304084 E 0 E 22 NA Q12443525 E 0 E 23 NA Q12543904 E 0 E 24 NA Q12890205 E 0 E 25 NA Q12891524 E 0 E 26 NA Q12918202 E 0 E 27 NA Q13005653 E 0 E 28 NA Q13073896 E 0 E 29 NA Q13163823 E 0 E 30 NA ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ Q1048694 C 2048095025 A 15670659 High positive Q31165 C 2048330818 A 15670660 High positive Q40629 C 2049755644 A 15670661 High positive Q105584 C 2049926923 A 15670662 High positive Q4584301 D 2052339927 A 15670663 NA Q565 C 2052996261 A 15670664 High positive Q1868372 E 2056080224 A 15670665 NA Q209330 C 2060928966 A 15670666 High positive Q14005 D 2063120071 A 15670667 NA Q918 C 2063217449 A 15670668 High positive Q150248 C 2068796814 A 15670669 High positive Q866 C 2079749157 A 15670670 High positive Q477675 C 2080785713 A 15670671 High positive Q1967876 C 2084215818 A 15670672 High positive Q750403 C 2084693498 A 15670673 High positive Q355 C 2093900731 A 15670674 High positive Q623578 C 2097991400 A 15670675 High positive Q17299517 D 2105487660 A 15670676 NA Q33999 C 2108672678 A 15670677 High positive Q2494649 C 2114531894 A 15670678 High positive Q2597810 C 2128920607 A 15670679 High positive Q193563 C 2130725560 A 15670680 High positive Q423048 C 2136131564 A 15670681 High positive Q37312 C 2142913121 A 15670682 High positive Q54919 C 2148531382 A 15670683 High positive Q36578 C 2229315598 A 15670684 High positive Q30 A 2277746226 A 15670685 None Q6581097 C 3273952711 A 15670686 High positive Q5 A 5668008721 A 15670687 None Q5296 C 12530369761 A 15670688 High positive
entity_id prediction page_views pop_class seqNum dissonance Q10040378 E 0 E 1 NA Q10069140 E 0 E 2 NA Q10081695 E 0 E 3 NA Q10092002 E 0 E 4 NA Q10111267 E 0 E 5 NA Q10149726 E 0 E 6 NA Q10180230 E 0 E 7 NA Q10185035 E 0 E 8 NA Q10205202 E 0 E 9 NA Q10252966 E 0 E 10 NA Q10444494 D 0 E 11 Moderate negative Q10624171 D 0 E 12 Moderate negative Q10704108 D 0 E 13 Moderate negative Q10750354 E 0 E 14 NA Q10766855 E 0 E 15 NA Q10827611 E 0 E 16 NA Q11093044 E 0 E 17 NA Q11934537 E 0 E 18 NA Q12133466 E 0 E 19 NA Q12264503 E 0 E 20 NA Q12267516 E 0 E 21 NA Q12304084 E 0 E 22 NA Q12443525 E 0 E 23 NA Q12543904 E 0 E 24 NA Q12890205 E 0 E 25 NA Q12891524 E 0 E 26 NA Q12918202 E 0 E 27 NA Q13005653 E 0 E 28 NA Q13073896 E 0 E 29 NA Q13163823 E 0 E 30 NA ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ Q1048694 C 2048095025 A 15670659 High positive Q31165 C 2048330818 A 15670660 High positive Q40629 C 2049755644 A 15670661 High positive Q105584 C 2049926923 A 15670662 High positive Q4584301 D 2052339927 A 15670663 High positive Q565 C 2052996261 A 15670664 High positive Q1868372 E 2056080224 A 15670665 NA Q209330 C 2060928966 A 15670666 High positive Q14005 D 2063120071 A 15670667 High positive Q918 C 2063217449 A 15670668 High positive Q150248 C 2068796814 A 15670669 High positive Q866 C 2079749157 A 15670670 High positive Q477675 C 2080785713 A 15670671 High positive Q1967876 C 2084215818 A 15670672 High positive Q750403 C 2084693498 A 15670673 High positive Q355 C 2093900731 A 15670674 High positive Q623578 C 2097991400 A 15670675 High positive Q17299517 D 2105487660 A 15670676 High positive Q33999 C 2108672678 A 15670677 High positive Q2494649 C 2114531894 A 15670678 High positive Q2597810 C 2128920607 A 15670679 High positive Q193563 C 2130725560 A 15670680 High positive Q423048 C 2136131564 A 15670681 High positive Q37312 C 2142913121 A 15670682 High positive Q54919 C 2148531382 A 15670683 High positive Q36578 C 2229315598 A 15670684 High positive Q30 A 2277746226 A 15670685 None Q6581097 C 3273952711 A 15670686 High positive Q5 A 5668008721 A 15670687 None Q5296 C 12530369761 A 15670688 High positive
In [38]:
## E
articles_by_pop[prediction == 'E' & pop_class == 'E',
dissonance := 'None'];
articles_by_pop[prediction == 'E' & pop_class == 'D',
dissonance := 'Moderate positive'];
articles_by_pop[prediction == 'E' & pop_class >= 'C',
dissonance := 'High positive'];
entity_id prediction page_views pop_class seqNum dissonance Q10040378 E 0 E 1 None Q10069140 E 0 E 2 None Q10081695 E 0 E 3 None Q10092002 E 0 E 4 None Q10111267 E 0 E 5 None Q10149726 E 0 E 6 None Q10180230 E 0 E 7 None Q10185035 E 0 E 8 None Q10205202 E 0 E 9 None Q10252966 E 0 E 10 None Q10444494 D 0 E 11 Moderate negative Q10624171 D 0 E 12 Moderate negative Q10704108 D 0 E 13 Moderate negative Q10750354 E 0 E 14 None Q10766855 E 0 E 15 None Q10827611 E 0 E 16 None Q11093044 E 0 E 17 None Q11934537 E 0 E 18 None Q12133466 E 0 E 19 None Q12264503 E 0 E 20 None Q12267516 E 0 E 21 None Q12304084 E 0 E 22 None Q12443525 E 0 E 23 None Q12543904 E 0 E 24 None Q12890205 E 0 E 25 None Q12891524 E 0 E 26 None Q12918202 E 0 E 27 None Q13005653 E 0 E 28 None Q13073896 E 0 E 29 None Q13163823 E 0 E 30 None ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ Q1048694 C 2048095025 A 15670659 High positive Q31165 C 2048330818 A 15670660 High positive Q40629 C 2049755644 A 15670661 High positive Q105584 C 2049926923 A 15670662 High positive Q4584301 D 2052339927 A 15670663 High positive Q565 C 2052996261 A 15670664 High positive Q1868372 E 2056080224 A 15670665 NA Q209330 C 2060928966 A 15670666 High positive Q14005 D 2063120071 A 15670667 High positive Q918 C 2063217449 A 15670668 High positive Q150248 C 2068796814 A 15670669 High positive Q866 C 2079749157 A 15670670 High positive Q477675 C 2080785713 A 15670671 High positive Q1967876 C 2084215818 A 15670672 High positive Q750403 C 2084693498 A 15670673 High positive Q355 C 2093900731 A 15670674 High positive Q623578 C 2097991400 A 15670675 High positive Q17299517 D 2105487660 A 15670676 High positive Q33999 C 2108672678 A 15670677 High positive Q2494649 C 2114531894 A 15670678 High positive Q2597810 C 2128920607 A 15670679 High positive Q193563 C 2130725560 A 15670680 High positive Q423048 C 2136131564 A 15670681 High positive Q37312 C 2142913121 A 15670682 High positive Q54919 C 2148531382 A 15670683 High positive Q36578 C 2229315598 A 15670684 High positive Q30 A 2277746226 A 15670685 None Q6581097 C 3273952711 A 15670686 High positive Q5 A 5668008721 A 15670687 None Q5296 C 12530369761 A 15670688 High positive
entity_id prediction page_views pop_class seqNum dissonance Q10040378 E 0 E 1 None Q10069140 E 0 E 2 None Q10081695 E 0 E 3 None Q10092002 E 0 E 4 None Q10111267 E 0 E 5 None Q10149726 E 0 E 6 None Q10180230 E 0 E 7 None Q10185035 E 0 E 8 None Q10205202 E 0 E 9 None Q10252966 E 0 E 10 None Q10444494 D 0 E 11 Moderate negative Q10624171 D 0 E 12 Moderate negative Q10704108 D 0 E 13 Moderate negative Q10750354 E 0 E 14 None Q10766855 E 0 E 15 None Q10827611 E 0 E 16 None Q11093044 E 0 E 17 None Q11934537 E 0 E 18 None Q12133466 E 0 E 19 None Q12264503 E 0 E 20 None Q12267516 E 0 E 21 None Q12304084 E 0 E 22 None Q12443525 E 0 E 23 None Q12543904 E 0 E 24 None Q12890205 E 0 E 25 None Q12891524 E 0 E 26 None Q12918202 E 0 E 27 None Q13005653 E 0 E 28 None Q13073896 E 0 E 29 None Q13163823 E 0 E 30 None ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ Q1048694 C 2048095025 A 15670659 High positive Q31165 C 2048330818 A 15670660 High positive Q40629 C 2049755644 A 15670661 High positive Q105584 C 2049926923 A 15670662 High positive Q4584301 D 2052339927 A 15670663 High positive Q565 C 2052996261 A 15670664 High positive Q1868372 E 2056080224 A 15670665 NA Q209330 C 2060928966 A 15670666 High positive Q14005 D 2063120071 A 15670667 High positive Q918 C 2063217449 A 15670668 High positive Q150248 C 2068796814 A 15670669 High positive Q866 C 2079749157 A 15670670 High positive Q477675 C 2080785713 A 15670671 High positive Q1967876 C 2084215818 A 15670672 High positive Q750403 C 2084693498 A 15670673 High positive Q355 C 2093900731 A 15670674 High positive Q623578 C 2097991400 A 15670675 High positive Q17299517 D 2105487660 A 15670676 High positive Q33999 C 2108672678 A 15670677 High positive Q2494649 C 2114531894 A 15670678 High positive Q2597810 C 2128920607 A 15670679 High positive Q193563 C 2130725560 A 15670680 High positive Q423048 C 2136131564 A 15670681 High positive Q37312 C 2142913121 A 15670682 High positive Q54919 C 2148531382 A 15670683 High positive Q36578 C 2229315598 A 15670684 High positive Q30 A 2277746226 A 15670685 None Q6581097 C 3273952711 A 15670686 High positive Q5 A 5668008721 A 15670687 None Q5296 C 12530369761 A 15670688 High positive
entity_id prediction page_views pop_class seqNum dissonance Q10040378 E 0 E 1 None Q10069140 E 0 E 2 None Q10081695 E 0 E 3 None Q10092002 E 0 E 4 None Q10111267 E 0 E 5 None Q10149726 E 0 E 6 None Q10180230 E 0 E 7 None Q10185035 E 0 E 8 None Q10205202 E 0 E 9 None Q10252966 E 0 E 10 None Q10444494 D 0 E 11 Moderate negative Q10624171 D 0 E 12 Moderate negative Q10704108 D 0 E 13 Moderate negative Q10750354 E 0 E 14 None Q10766855 E 0 E 15 None Q10827611 E 0 E 16 None Q11093044 E 0 E 17 None Q11934537 E 0 E 18 None Q12133466 E 0 E 19 None Q12264503 E 0 E 20 None Q12267516 E 0 E 21 None Q12304084 E 0 E 22 None Q12443525 E 0 E 23 None Q12543904 E 0 E 24 None Q12890205 E 0 E 25 None Q12891524 E 0 E 26 None Q12918202 E 0 E 27 None Q13005653 E 0 E 28 None Q13073896 E 0 E 29 None Q13163823 E 0 E 30 None ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ Q1048694 C 2048095025 A 15670659 High positive Q31165 C 2048330818 A 15670660 High positive Q40629 C 2049755644 A 15670661 High positive Q105584 C 2049926923 A 15670662 High positive Q4584301 D 2052339927 A 15670663 High positive Q565 C 2052996261 A 15670664 High positive Q1868372 E 2056080224 A 15670665 High positive Q209330 C 2060928966 A 15670666 High positive Q14005 D 2063120071 A 15670667 High positive Q918 C 2063217449 A 15670668 High positive Q150248 C 2068796814 A 15670669 High positive Q866 C 2079749157 A 15670670 High positive Q477675 C 2080785713 A 15670671 High positive Q1967876 C 2084215818 A 15670672 High positive Q750403 C 2084693498 A 15670673 High positive Q355 C 2093900731 A 15670674 High positive Q623578 C 2097991400 A 15670675 High positive Q17299517 D 2105487660 A 15670676 High positive Q33999 C 2108672678 A 15670677 High positive Q2494649 C 2114531894 A 15670678 High positive Q2597810 C 2128920607 A 15670679 High positive Q193563 C 2130725560 A 15670680 High positive Q423048 C 2136131564 A 15670681 High positive Q37312 C 2142913121 A 15670682 High positive Q54919 C 2148531382 A 15670683 High positive Q36578 C 2229315598 A 15670684 High positive Q30 A 2277746226 A 15670685 None Q6581097 C 3273952711 A 15670686 High positive Q5 A 5668008721 A 15670687 None Q5296 C 12530369761 A 15670688 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 74.4 17.6 8.0 D 0.0 77.4 13.7 8.7 0.2 C 47.0 25.7 25.9 1.4 0.0 B 59.7 37.7 2.5 0.0 0.0 A 9.6 87.7 2.7 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 2255815137 D Moderate negative 398767091 C High negative 246636114 B High negative 43539992 D None 1355140951 E Moderate positive 6878662960 C Moderate negative 1530362019 A High negative 1966082 E High positive 113653751245 C None 44909643995 D Moderate positive 18435711407 B Moderate negative 1252345270 C Moderate positive 118991212481 D High positive 71649252038 B None 3323190669 A Moderate negative 4770535873 C High positive 117154831988 A None 7945754947
In [42]:
## Calculations of total number of dissonant views per dissonance
articles_by_pop[, list(dissonant_views=sum(page_views)), by=list(dissonance)];
dissonance dissonant_views None 59789545699 Moderate negative 7952010253 High negative 292142188 Moderate positive 144305586848 High positive 302457835271
In [43]:
articles_by_pop[,sum(as.numeric(page_views))];
514797120259
In [44]:
## Proportions
100*65938379920/545180810059;
100*125047198/545180810059;
100*6713682043/545180810059;
100*120523625541/545180810059;
100*351880075357/545180810059;
12.0947727255594
0.0229368304409811
1.23145971375505
22.107092420945
64.5437383092995
In [45]:
# 87% of views are high positive
In [46]:
100*(articles_by_pop[, list(dissonant_views=sum(page_views)), by=list(dissonance)][1][,c('dissonant_views')]/articles_by_pop[,sum(as.numeric(page_views))])
dissonant_views 11.6142
In [47]:
100*(articles_by_pop[, list(dissonant_views=sum(page_views)), by=list(dissonance)][2][,c('dissonant_views')]/articles_by_pop[,sum(as.numeric(page_views))])
dissonant_views 1.544688
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 0.05674899
In [49]:
100*(articles_by_pop[, list(dissonant_views=sum(page_views)), by=list(dissonance)][4][,c('dissonant_views')]/articles_by_pop[,sum(as.numeric(page_views))])
dissonant_views 28.03155
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 58.75282
Content source: hall1467/wikidata_usage_tracking
Similar notebooks: