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_20130501.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: 1
Q100 : 1 1st Qu.: 10.00 1st Qu.:1.140e+02 B: 1645
Q1000 : 1 Median : 18.00 Median :5.850e+02 C: 341208
Q10000 : 1 Mean : 24.38 Mean :4.435e+04 D: 469187
Q100000 : 1 3rd Qu.: 31.00 3rd Qu.:2.917e+03 E:9822970
Q1000000: 1 Max. :21863.00 Max. :1.253e+10
(Other) :10635005
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 E 0 Q10624171 E 0 Q10704108 E 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 Q3822211 E 0 Q4000726 E 0 Q6451977 E 0 Q6473609 E 0 Q6916875 E 0 Q6918381 E 0 Q6918965 E 0 Q6920428 E 0 Q7158411 E 0 ⋮ ⋮ ⋮ ⋮ Q384060 D 2047954248 Q1048694 E 2048095025 Q31165 E 2048330818 Q40629 E 2049755644 Q105584 E 2049926923 Q4584301 E 2052339927 Q565 D 2052996261 Q1868372 E 2056080224 Q209330 D 2060928966 Q14005 D 2063120071 Q918 D 2063217449 Q150248 E 2068796814 Q866 D 2079749157 Q477675 E 2080785713 Q1967876 E 2084215818 Q750403 E 2084693498 Q355 D 2093900731 Q623578 E 2097991400 Q33999 C 2108672678 Q2494649 E 2114531894 Q2597810 E 2128920607 Q193563 D 2130725560 Q423048 D 2136131564 Q37312 D 2142913121 Q54919 D 2148531382 Q36578 D 2229315598 Q30 C 2277746226 Q6581097 D 3273952711 Q5 C 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 E 0 11 Q10624171 E 0 12 Q10704108 E 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 Q3822211 E 0 22 Q4000726 E 0 23 Q6451977 E 0 24 Q6473609 E 0 25 Q6916875 E 0 26 Q6918381 E 0 27 Q6918965 E 0 28 Q6920428 E 0 29 Q7158411 E 0 30 ⋮ ⋮ ⋮ ⋮ ⋮ Q384060 D 2047954248 10634982 Q1048694 E 2048095025 10634983 Q31165 E 2048330818 10634984 Q40629 E 2049755644 10634985 Q105584 E 2049926923 10634986 Q4584301 E 2052339927 10634987 Q565 D 2052996261 10634988 Q1868372 E 2056080224 10634989 Q209330 D 2060928966 10634990 Q14005 D 2063120071 10634991 Q918 D 2063217449 10634992 Q150248 E 2068796814 10634993 Q866 D 2079749157 10634994 Q477675 E 2080785713 10634995 Q1967876 E 2084215818 10634996 Q750403 E 2084693498 10634997 Q355 D 2093900731 10634998 Q623578 E 2097991400 10634999 Q33999 C 2108672678 10635000 Q2494649 E 2114531894 10635001 Q2597810 E 2128920607 10635002 Q193563 D 2130725560 10635003 Q423048 D 2136131564 10635004 Q37312 D 2142913121 10635005 Q54919 D 2148531382 10635006 Q36578 D 2229315598 10635007 Q30 C 2277746226 10635008 Q6581097 D 3273952711 10635009 Q5 C 5668008721 10635010 Q5296 C 12530369761 10635011
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]$narticles;
print(paste('start_idx =', start_idx, ', end_idx = ', end_idx));
dataset[seqNum >= start_idx & seqNum <= end_idx, pop_class := rating];
prev_idx = end_idx -1;
}
dataset;
}
In [13]:
articles_by_pop = assign_pop_class(articles_by_pop,
assessment_classes, n_per_class);
[1] "start_idx = 1 , end_idx = 9822971"
[1] "start_idx = 9822971 , end_idx = 10292158"
[1] "start_idx = 10292158 , end_idx = 10633366"
[1] "start_idx = 10633366 , end_idx = 10635011"
[1] "start_idx = 10635011 , end_idx = 10635012"
In [14]:
create_dissonance_matrix = function(articledata, classes) {
d_mtrx = matrix(0, nrow=length(classes), ncol=length(classes));
rownames(d_mtrx) = classes;
colnames(d_mtrx) = classes;
for(real_rating in classes) {
for(pop_rating in classes) {
d_mtrx[real_rating, pop_rating] = length(articledata[prediction == real_rating & pop_class == pop_rating]$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 9221471 373264 227789 446 0 D 348697 55533 64332 625 0 C 251169 40384 49081 573 1 B 1633 6 6 0 0 A 0 0 0 1 0
In [16]:
dissonance_matrix = create_dissonance_matrix(articles_by_pop,
assessment_classes);
In [17]:
# Total misaligned entities
(dissonance_matrix[1,1]+dissonance_matrix[2,2]+dissonance_matrix[3,3]+dissonance_matrix[4,4]+dissonance_matrix[5,5])/sum(dissonance_matrix[,])
0.876922929369796
In [18]:
# A class quality and A class views over A class quality
dissonance_matrix[5,5]/sum(dissonance_matrix[5,])
0
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,])
1
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])
1
In [22]:
prediction_e_pop_class_a <- merge(articles_by_pop[prediction == 'E' & pop_class == 'A'],quality_prediction_and_page_views, by='entity_id')[, c("entity_id","page_views.x", "number_of_revisions")]
In [23]:
head(prediction_e_pop_class_a)
entity_id page_views.x number_of_revisions
In [24]:
## Q: why do I get _two_ pageid columns? Solution is to do the selection
## on the joined table, not as a select _in_ the join.
## Dissonance matrix proportions by row (..., 1) and column (..., 2)
## rounded to 1 decimal places.
In [25]:
round(100*prop.table(dissonance_matrix, 1), 1);
E D C B A E 93.9 3.8 2.3 0.0 0 D 74.3 11.8 13.7 0.1 0 C 73.6 11.8 14.4 0.2 0 B 99.3 0.4 0.4 0.0 0 A 0.0 0.0 0.0 100.0 0
In [26]:
round(100*prop.table(dissonance_matrix, 2), 1);
E D C B A E 93.9 79.6 66.8 27.1 0 D 3.5 11.8 18.9 38.0 0 C 2.6 8.6 14.4 34.8 100 B 0.0 0.0 0.0 0.0 0 A 0.0 0.0 0.0 0.1 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/201305_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 Q5296 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/201305_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/201305_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/201305_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 E 0 E 11 Q10624171 E 0 E 12 Q10704108 E 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 Q3822211 E 0 E 22 Q4000726 E 0 E 23 Q6451977 E 0 E 24 Q6473609 E 0 E 25 Q6916875 E 0 E 26 Q6918381 E 0 E 27 Q6918965 E 0 E 28 Q6920428 E 0 E 29 Q7158411 E 0 E 30 ⋮ ⋮ ⋮ ⋮ ⋮ Q384060 D 2047954248 B 10634982 Q1048694 E 2048095025 B 10634983 Q31165 E 2048330818 B 10634984 Q40629 E 2049755644 B 10634985 Q105584 E 2049926923 B 10634986 Q4584301 E 2052339927 B 10634987 Q565 D 2052996261 B 10634988 Q1868372 E 2056080224 B 10634989 Q209330 D 2060928966 B 10634990 Q14005 D 2063120071 B 10634991 Q918 D 2063217449 B 10634992 Q150248 E 2068796814 B 10634993 Q866 D 2079749157 B 10634994 Q477675 E 2080785713 B 10634995 Q1967876 E 2084215818 B 10634996 Q750403 E 2084693498 B 10634997 Q355 D 2093900731 B 10634998 Q623578 E 2097991400 B 10634999 Q33999 C 2108672678 B 10635000 Q2494649 E 2114531894 B 10635001 Q2597810 E 2128920607 B 10635002 Q193563 D 2130725560 B 10635003 Q423048 D 2136131564 B 10635004 Q37312 D 2142913121 B 10635005 Q54919 D 2148531382 B 10635006 Q36578 D 2229315598 B 10635007 Q30 C 2277746226 B 10635008 Q6581097 D 3273952711 B 10635009 Q5 C 5668008721 B 10635010 Q5296 C 12530369761 A 10635011
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 E 0 E 11 NA Q10624171 E 0 E 12 NA Q10704108 E 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 Q3822211 E 0 E 22 NA Q4000726 E 0 E 23 NA Q6451977 E 0 E 24 NA Q6473609 E 0 E 25 NA Q6916875 E 0 E 26 NA Q6918381 E 0 E 27 NA Q6918965 E 0 E 28 NA Q6920428 E 0 E 29 NA Q7158411 E 0 E 30 NA ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ Q384060 D 2047954248 B 10634982 NA Q1048694 E 2048095025 B 10634983 NA Q31165 E 2048330818 B 10634984 NA Q40629 E 2049755644 B 10634985 NA Q105584 E 2049926923 B 10634986 NA Q4584301 E 2052339927 B 10634987 NA Q565 D 2052996261 B 10634988 NA Q1868372 E 2056080224 B 10634989 NA Q209330 D 2060928966 B 10634990 NA Q14005 D 2063120071 B 10634991 NA Q918 D 2063217449 B 10634992 NA Q150248 E 2068796814 B 10634993 NA Q866 D 2079749157 B 10634994 NA Q477675 E 2080785713 B 10634995 NA Q1967876 E 2084215818 B 10634996 NA Q750403 E 2084693498 B 10634997 NA Q355 D 2093900731 B 10634998 NA Q623578 E 2097991400 B 10634999 NA Q33999 C 2108672678 B 10635000 NA Q2494649 E 2114531894 B 10635001 NA Q2597810 E 2128920607 B 10635002 NA Q193563 D 2130725560 B 10635003 NA Q423048 D 2136131564 B 10635004 NA Q37312 D 2142913121 B 10635005 NA Q54919 D 2148531382 B 10635006 NA Q36578 D 2229315598 B 10635007 NA Q30 C 2277746226 B 10635008 NA Q6581097 D 3273952711 B 10635009 NA Q5 C 5668008721 B 10635010 NA Q5296 C 12530369761 A 10635011 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 E 0 E 11 NA Q10624171 E 0 E 12 NA Q10704108 E 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 Q3822211 E 0 E 22 NA Q4000726 E 0 E 23 NA Q6451977 E 0 E 24 NA Q6473609 E 0 E 25 NA Q6916875 E 0 E 26 NA Q6918381 E 0 E 27 NA Q6918965 E 0 E 28 NA Q6920428 E 0 E 29 NA Q7158411 E 0 E 30 NA ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ Q384060 D 2047954248 B 10634982 NA Q1048694 E 2048095025 B 10634983 NA Q31165 E 2048330818 B 10634984 NA Q40629 E 2049755644 B 10634985 NA Q105584 E 2049926923 B 10634986 NA Q4584301 E 2052339927 B 10634987 NA Q565 D 2052996261 B 10634988 NA Q1868372 E 2056080224 B 10634989 NA Q209330 D 2060928966 B 10634990 NA Q14005 D 2063120071 B 10634991 NA Q918 D 2063217449 B 10634992 NA Q150248 E 2068796814 B 10634993 NA Q866 D 2079749157 B 10634994 NA Q477675 E 2080785713 B 10634995 NA Q1967876 E 2084215818 B 10634996 NA Q750403 E 2084693498 B 10634997 NA Q355 D 2093900731 B 10634998 NA Q623578 E 2097991400 B 10634999 NA Q33999 C 2108672678 B 10635000 NA Q2494649 E 2114531894 B 10635001 NA Q2597810 E 2128920607 B 10635002 NA Q193563 D 2130725560 B 10635003 NA Q423048 D 2136131564 B 10635004 NA Q37312 D 2142913121 B 10635005 NA Q54919 D 2148531382 B 10635006 NA Q36578 D 2229315598 B 10635007 NA Q30 C 2277746226 B 10635008 NA Q6581097 D 3273952711 B 10635009 NA Q5 C 5668008721 B 10635010 NA Q5296 C 12530369761 A 10635011 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 E 0 E 11 NA Q10624171 E 0 E 12 NA Q10704108 E 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 Q3822211 E 0 E 22 NA Q4000726 E 0 E 23 NA Q6451977 E 0 E 24 NA Q6473609 E 0 E 25 NA Q6916875 E 0 E 26 NA Q6918381 E 0 E 27 NA Q6918965 E 0 E 28 NA Q6920428 E 0 E 29 NA Q7158411 E 0 E 30 NA ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ Q384060 D 2047954248 B 10634982 NA Q1048694 E 2048095025 B 10634983 NA Q31165 E 2048330818 B 10634984 NA Q40629 E 2049755644 B 10634985 NA Q105584 E 2049926923 B 10634986 NA Q4584301 E 2052339927 B 10634987 NA Q565 D 2052996261 B 10634988 NA Q1868372 E 2056080224 B 10634989 NA Q209330 D 2060928966 B 10634990 NA Q14005 D 2063120071 B 10634991 NA Q918 D 2063217449 B 10634992 NA Q150248 E 2068796814 B 10634993 NA Q866 D 2079749157 B 10634994 NA Q477675 E 2080785713 B 10634995 NA Q1967876 E 2084215818 B 10634996 NA Q750403 E 2084693498 B 10634997 NA Q355 D 2093900731 B 10634998 NA Q623578 E 2097991400 B 10634999 NA Q33999 C 2108672678 B 10635000 NA Q2494649 E 2114531894 B 10635001 NA Q2597810 E 2128920607 B 10635002 NA Q193563 D 2130725560 B 10635003 NA Q423048 D 2136131564 B 10635004 NA Q37312 D 2142913121 B 10635005 NA Q54919 D 2148531382 B 10635006 NA Q36578 D 2229315598 B 10635007 NA Q30 C 2277746226 B 10635008 NA Q6581097 D 3273952711 B 10635009 NA Q5 C 5668008721 B 10635010 NA Q5296 C 12530369761 A 10635011 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 E 0 E 11 NA Q10624171 E 0 E 12 NA Q10704108 E 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 Q3822211 E 0 E 22 NA Q4000726 E 0 E 23 NA Q6451977 E 0 E 24 NA Q6473609 E 0 E 25 NA Q6916875 E 0 E 26 NA Q6918381 E 0 E 27 NA Q6918965 E 0 E 28 NA Q6920428 E 0 E 29 NA Q7158411 E 0 E 30 NA ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ Q384060 D 2047954248 B 10634982 NA Q1048694 E 2048095025 B 10634983 NA Q31165 E 2048330818 B 10634984 NA Q40629 E 2049755644 B 10634985 NA Q105584 E 2049926923 B 10634986 NA Q4584301 E 2052339927 B 10634987 NA Q565 D 2052996261 B 10634988 NA Q1868372 E 2056080224 B 10634989 NA Q209330 D 2060928966 B 10634990 NA Q14005 D 2063120071 B 10634991 NA Q918 D 2063217449 B 10634992 NA Q150248 E 2068796814 B 10634993 NA Q866 D 2079749157 B 10634994 NA Q477675 E 2080785713 B 10634995 NA Q1967876 E 2084215818 B 10634996 NA Q750403 E 2084693498 B 10634997 NA Q355 D 2093900731 B 10634998 NA Q623578 E 2097991400 B 10634999 NA Q33999 C 2108672678 B 10635000 NA Q2494649 E 2114531894 B 10635001 NA Q2597810 E 2128920607 B 10635002 NA Q193563 D 2130725560 B 10635003 NA Q423048 D 2136131564 B 10635004 NA Q37312 D 2142913121 B 10635005 NA Q54919 D 2148531382 B 10635006 NA Q36578 D 2229315598 B 10635007 NA Q30 C 2277746226 B 10635008 NA Q6581097 D 3273952711 B 10635009 NA Q5 C 5668008721 B 10635010 NA Q5296 C 12530369761 A 10635011 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 E 0 E 11 NA Q10624171 E 0 E 12 NA Q10704108 E 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 Q3822211 E 0 E 22 NA Q4000726 E 0 E 23 NA Q6451977 E 0 E 24 NA Q6473609 E 0 E 25 NA Q6916875 E 0 E 26 NA Q6918381 E 0 E 27 NA Q6918965 E 0 E 28 NA Q6920428 E 0 E 29 NA Q7158411 E 0 E 30 NA ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ Q384060 D 2047954248 B 10634982 NA Q1048694 E 2048095025 B 10634983 NA Q31165 E 2048330818 B 10634984 NA Q40629 E 2049755644 B 10634985 NA Q105584 E 2049926923 B 10634986 NA Q4584301 E 2052339927 B 10634987 NA Q565 D 2052996261 B 10634988 NA Q1868372 E 2056080224 B 10634989 NA Q209330 D 2060928966 B 10634990 NA Q14005 D 2063120071 B 10634991 NA Q918 D 2063217449 B 10634992 NA Q150248 E 2068796814 B 10634993 NA Q866 D 2079749157 B 10634994 NA Q477675 E 2080785713 B 10634995 NA Q1967876 E 2084215818 B 10634996 NA Q750403 E 2084693498 B 10634997 NA Q355 D 2093900731 B 10634998 NA Q623578 E 2097991400 B 10634999 NA Q33999 C 2108672678 B 10635000 NA Q2494649 E 2114531894 B 10635001 NA Q2597810 E 2128920607 B 10635002 NA Q193563 D 2130725560 B 10635003 NA Q423048 D 2136131564 B 10635004 NA Q37312 D 2142913121 B 10635005 NA Q54919 D 2148531382 B 10635006 NA Q36578 D 2229315598 B 10635007 NA Q30 C 2277746226 B 10635008 NA Q6581097 D 3273952711 B 10635009 NA Q5 C 5668008721 B 10635010 NA Q5296 C 12530369761 A 10635011 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 E 0 E 11 NA Q10624171 E 0 E 12 NA Q10704108 E 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 Q3822211 E 0 E 22 NA Q4000726 E 0 E 23 NA Q6451977 E 0 E 24 NA Q6473609 E 0 E 25 NA Q6916875 E 0 E 26 NA Q6918381 E 0 E 27 NA Q6918965 E 0 E 28 NA Q6920428 E 0 E 29 NA Q7158411 E 0 E 30 NA ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ Q384060 D 2047954248 B 10634982 NA Q1048694 E 2048095025 B 10634983 NA Q31165 E 2048330818 B 10634984 NA Q40629 E 2049755644 B 10634985 NA Q105584 E 2049926923 B 10634986 NA Q4584301 E 2052339927 B 10634987 NA Q565 D 2052996261 B 10634988 NA Q1868372 E 2056080224 B 10634989 NA Q209330 D 2060928966 B 10634990 NA Q14005 D 2063120071 B 10634991 NA Q918 D 2063217449 B 10634992 NA Q150248 E 2068796814 B 10634993 NA Q866 D 2079749157 B 10634994 NA Q477675 E 2080785713 B 10634995 NA Q1967876 E 2084215818 B 10634996 NA Q750403 E 2084693498 B 10634997 NA Q355 D 2093900731 B 10634998 NA Q623578 E 2097991400 B 10634999 NA Q33999 C 2108672678 B 10635000 NA Q2494649 E 2114531894 B 10635001 NA Q2597810 E 2128920607 B 10635002 NA Q193563 D 2130725560 B 10635003 NA Q423048 D 2136131564 B 10635004 NA Q37312 D 2142913121 B 10635005 NA Q54919 D 2148531382 B 10635006 NA Q36578 D 2229315598 B 10635007 NA Q30 C 2277746226 B 10635008 NA Q6581097 D 3273952711 B 10635009 NA Q5 C 5668008721 B 10635010 NA Q5296 C 12530369761 A 10635011 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 E 0 E 11 NA Q10624171 E 0 E 12 NA Q10704108 E 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 Q3822211 E 0 E 22 NA Q4000726 E 0 E 23 NA Q6451977 E 0 E 24 NA Q6473609 E 0 E 25 NA Q6916875 E 0 E 26 NA Q6918381 E 0 E 27 NA Q6918965 E 0 E 28 NA Q6920428 E 0 E 29 NA Q7158411 E 0 E 30 NA ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ Q384060 D 2047954248 B 10634982 NA Q1048694 E 2048095025 B 10634983 NA Q31165 E 2048330818 B 10634984 NA Q40629 E 2049755644 B 10634985 NA Q105584 E 2049926923 B 10634986 NA Q4584301 E 2052339927 B 10634987 NA Q565 D 2052996261 B 10634988 NA Q1868372 E 2056080224 B 10634989 NA Q209330 D 2060928966 B 10634990 NA Q14005 D 2063120071 B 10634991 NA Q918 D 2063217449 B 10634992 NA Q150248 E 2068796814 B 10634993 NA Q866 D 2079749157 B 10634994 NA Q477675 E 2080785713 B 10634995 NA Q1967876 E 2084215818 B 10634996 NA Q750403 E 2084693498 B 10634997 NA Q355 D 2093900731 B 10634998 NA Q623578 E 2097991400 B 10634999 NA Q33999 C 2108672678 B 10635000 NA Q2494649 E 2114531894 B 10635001 NA Q2597810 E 2128920607 B 10635002 NA Q193563 D 2130725560 B 10635003 NA Q423048 D 2136131564 B 10635004 NA Q37312 D 2142913121 B 10635005 NA Q54919 D 2148531382 B 10635006 NA Q36578 D 2229315598 B 10635007 NA Q30 C 2277746226 B 10635008 NA Q6581097 D 3273952711 B 10635009 NA Q5 C 5668008721 B 10635010 NA Q5296 C 12530369761 A 10635011 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 E 0 E 11 NA Q10624171 E 0 E 12 NA Q10704108 E 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 Q3822211 E 0 E 22 NA Q4000726 E 0 E 23 NA Q6451977 E 0 E 24 NA Q6473609 E 0 E 25 NA Q6916875 E 0 E 26 NA Q6918381 E 0 E 27 NA Q6918965 E 0 E 28 NA Q6920428 E 0 E 29 NA Q7158411 E 0 E 30 NA ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ Q384060 D 2047954248 B 10634982 NA Q1048694 E 2048095025 B 10634983 NA Q31165 E 2048330818 B 10634984 NA Q40629 E 2049755644 B 10634985 NA Q105584 E 2049926923 B 10634986 NA Q4584301 E 2052339927 B 10634987 NA Q565 D 2052996261 B 10634988 NA Q1868372 E 2056080224 B 10634989 NA Q209330 D 2060928966 B 10634990 NA Q14005 D 2063120071 B 10634991 NA Q918 D 2063217449 B 10634992 NA Q150248 E 2068796814 B 10634993 NA Q866 D 2079749157 B 10634994 NA Q477675 E 2080785713 B 10634995 NA Q1967876 E 2084215818 B 10634996 NA Q750403 E 2084693498 B 10634997 NA Q355 D 2093900731 B 10634998 NA Q623578 E 2097991400 B 10634999 NA Q33999 C 2108672678 B 10635000 NA Q2494649 E 2114531894 B 10635001 NA Q2597810 E 2128920607 B 10635002 NA Q193563 D 2130725560 B 10635003 NA Q423048 D 2136131564 B 10635004 NA Q37312 D 2142913121 B 10635005 NA Q54919 D 2148531382 B 10635006 NA Q36578 D 2229315598 B 10635007 NA Q30 C 2277746226 B 10635008 NA Q6581097 D 3273952711 B 10635009 NA Q5 C 5668008721 B 10635010 NA Q5296 C 12530369761 A 10635011 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 E 0 E 11 NA Q10624171 E 0 E 12 NA Q10704108 E 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 Q3822211 E 0 E 22 NA Q4000726 E 0 E 23 NA Q6451977 E 0 E 24 NA Q6473609 E 0 E 25 NA Q6916875 E 0 E 26 NA Q6918381 E 0 E 27 NA Q6918965 E 0 E 28 NA Q6920428 E 0 E 29 NA Q7158411 E 0 E 30 NA ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ Q384060 D 2047954248 B 10634982 NA Q1048694 E 2048095025 B 10634983 NA Q31165 E 2048330818 B 10634984 NA Q40629 E 2049755644 B 10634985 NA Q105584 E 2049926923 B 10634986 NA Q4584301 E 2052339927 B 10634987 NA Q565 D 2052996261 B 10634988 NA Q1868372 E 2056080224 B 10634989 NA Q209330 D 2060928966 B 10634990 NA Q14005 D 2063120071 B 10634991 NA Q918 D 2063217449 B 10634992 NA Q150248 E 2068796814 B 10634993 NA Q866 D 2079749157 B 10634994 NA Q477675 E 2080785713 B 10634995 NA Q1967876 E 2084215818 B 10634996 NA Q750403 E 2084693498 B 10634997 NA Q355 D 2093900731 B 10634998 NA Q623578 E 2097991400 B 10634999 NA Q33999 C 2108672678 B 10635000 NA Q2494649 E 2114531894 B 10635001 NA Q2597810 E 2128920607 B 10635002 NA Q193563 D 2130725560 B 10635003 NA Q423048 D 2136131564 B 10635004 NA Q37312 D 2142913121 B 10635005 NA Q54919 D 2148531382 B 10635006 NA Q36578 D 2229315598 B 10635007 NA Q30 C 2277746226 B 10635008 NA Q6581097 D 3273952711 B 10635009 NA Q5 C 5668008721 B 10635010 NA Q5296 C 12530369761 A 10635011 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 E 0 E 11 NA Q10624171 E 0 E 12 NA Q10704108 E 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 Q3822211 E 0 E 22 NA Q4000726 E 0 E 23 NA Q6451977 E 0 E 24 NA Q6473609 E 0 E 25 NA Q6916875 E 0 E 26 NA Q6918381 E 0 E 27 NA Q6918965 E 0 E 28 NA Q6920428 E 0 E 29 NA Q7158411 E 0 E 30 NA ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ Q384060 D 2047954248 B 10634982 NA Q1048694 E 2048095025 B 10634983 NA Q31165 E 2048330818 B 10634984 NA Q40629 E 2049755644 B 10634985 NA Q105584 E 2049926923 B 10634986 NA Q4584301 E 2052339927 B 10634987 NA Q565 D 2052996261 B 10634988 NA Q1868372 E 2056080224 B 10634989 NA Q209330 D 2060928966 B 10634990 NA Q14005 D 2063120071 B 10634991 NA Q918 D 2063217449 B 10634992 NA Q150248 E 2068796814 B 10634993 NA Q866 D 2079749157 B 10634994 NA Q477675 E 2080785713 B 10634995 NA Q1967876 E 2084215818 B 10634996 NA Q750403 E 2084693498 B 10634997 NA Q355 D 2093900731 B 10634998 NA Q623578 E 2097991400 B 10634999 NA Q33999 C 2108672678 B 10635000 NA Q2494649 E 2114531894 B 10635001 NA Q2597810 E 2128920607 B 10635002 NA Q193563 D 2130725560 B 10635003 NA Q423048 D 2136131564 B 10635004 NA Q37312 D 2142913121 B 10635005 NA Q54919 D 2148531382 B 10635006 NA Q36578 D 2229315598 B 10635007 NA Q30 C 2277746226 B 10635008 NA Q6581097 D 3273952711 B 10635009 NA Q5 C 5668008721 B 10635010 NA Q5296 C 12530369761 A 10635011 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 E 0 E 11 NA Q10624171 E 0 E 12 NA Q10704108 E 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 Q3822211 E 0 E 22 NA Q4000726 E 0 E 23 NA Q6451977 E 0 E 24 NA Q6473609 E 0 E 25 NA Q6916875 E 0 E 26 NA Q6918381 E 0 E 27 NA Q6918965 E 0 E 28 NA Q6920428 E 0 E 29 NA Q7158411 E 0 E 30 NA ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ Q384060 D 2047954248 B 10634982 NA Q1048694 E 2048095025 B 10634983 NA Q31165 E 2048330818 B 10634984 NA Q40629 E 2049755644 B 10634985 NA Q105584 E 2049926923 B 10634986 NA Q4584301 E 2052339927 B 10634987 NA Q565 D 2052996261 B 10634988 NA Q1868372 E 2056080224 B 10634989 NA Q209330 D 2060928966 B 10634990 NA Q14005 D 2063120071 B 10634991 NA Q918 D 2063217449 B 10634992 NA Q150248 E 2068796814 B 10634993 NA Q866 D 2079749157 B 10634994 NA Q477675 E 2080785713 B 10634995 NA Q1967876 E 2084215818 B 10634996 NA Q750403 E 2084693498 B 10634997 NA Q355 D 2093900731 B 10634998 NA Q623578 E 2097991400 B 10634999 NA Q33999 C 2108672678 B 10635000 NA Q2494649 E 2114531894 B 10635001 NA Q2597810 E 2128920607 B 10635002 NA Q193563 D 2130725560 B 10635003 NA Q423048 D 2136131564 B 10635004 NA Q37312 D 2142913121 B 10635005 NA Q54919 D 2148531382 B 10635006 NA Q36578 D 2229315598 B 10635007 NA Q30 C 2277746226 B 10635008 NA Q6581097 D 3273952711 B 10635009 NA Q5 C 5668008721 B 10635010 NA Q5296 C 12530369761 A 10635011 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 E 0 E 11 NA Q10624171 E 0 E 12 NA Q10704108 E 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 Q3822211 E 0 E 22 NA Q4000726 E 0 E 23 NA Q6451977 E 0 E 24 NA Q6473609 E 0 E 25 NA Q6916875 E 0 E 26 NA Q6918381 E 0 E 27 NA Q6918965 E 0 E 28 NA Q6920428 E 0 E 29 NA Q7158411 E 0 E 30 NA ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ Q384060 D 2047954248 B 10634982 NA Q1048694 E 2048095025 B 10634983 NA Q31165 E 2048330818 B 10634984 NA Q40629 E 2049755644 B 10634985 NA Q105584 E 2049926923 B 10634986 NA Q4584301 E 2052339927 B 10634987 NA Q565 D 2052996261 B 10634988 NA Q1868372 E 2056080224 B 10634989 NA Q209330 D 2060928966 B 10634990 NA Q14005 D 2063120071 B 10634991 NA Q918 D 2063217449 B 10634992 NA Q150248 E 2068796814 B 10634993 NA Q866 D 2079749157 B 10634994 NA Q477675 E 2080785713 B 10634995 NA Q1967876 E 2084215818 B 10634996 NA Q750403 E 2084693498 B 10634997 NA Q355 D 2093900731 B 10634998 NA Q623578 E 2097991400 B 10634999 NA Q33999 C 2108672678 B 10635000 Moderate positive Q2494649 E 2114531894 B 10635001 NA Q2597810 E 2128920607 B 10635002 NA Q193563 D 2130725560 B 10635003 NA Q423048 D 2136131564 B 10635004 NA Q37312 D 2142913121 B 10635005 NA Q54919 D 2148531382 B 10635006 NA Q36578 D 2229315598 B 10635007 NA Q30 C 2277746226 B 10635008 Moderate positive Q6581097 D 3273952711 B 10635009 NA Q5 C 5668008721 B 10635010 Moderate positive Q5296 C 12530369761 A 10635011 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 E 0 E 11 NA Q10624171 E 0 E 12 NA Q10704108 E 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 Q3822211 E 0 E 22 NA Q4000726 E 0 E 23 NA Q6451977 E 0 E 24 NA Q6473609 E 0 E 25 NA Q6916875 E 0 E 26 NA Q6918381 E 0 E 27 NA Q6918965 E 0 E 28 NA Q6920428 E 0 E 29 NA Q7158411 E 0 E 30 NA ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ Q384060 D 2047954248 B 10634982 NA Q1048694 E 2048095025 B 10634983 NA Q31165 E 2048330818 B 10634984 NA Q40629 E 2049755644 B 10634985 NA Q105584 E 2049926923 B 10634986 NA Q4584301 E 2052339927 B 10634987 NA Q565 D 2052996261 B 10634988 NA Q1868372 E 2056080224 B 10634989 NA Q209330 D 2060928966 B 10634990 NA Q14005 D 2063120071 B 10634991 NA Q918 D 2063217449 B 10634992 NA Q150248 E 2068796814 B 10634993 NA Q866 D 2079749157 B 10634994 NA Q477675 E 2080785713 B 10634995 NA Q1967876 E 2084215818 B 10634996 NA Q750403 E 2084693498 B 10634997 NA Q355 D 2093900731 B 10634998 NA Q623578 E 2097991400 B 10634999 NA Q33999 C 2108672678 B 10635000 Moderate positive Q2494649 E 2114531894 B 10635001 NA Q2597810 E 2128920607 B 10635002 NA Q193563 D 2130725560 B 10635003 NA Q423048 D 2136131564 B 10635004 NA Q37312 D 2142913121 B 10635005 NA Q54919 D 2148531382 B 10635006 NA Q36578 D 2229315598 B 10635007 NA Q30 C 2277746226 B 10635008 Moderate positive Q6581097 D 3273952711 B 10635009 NA Q5 C 5668008721 B 10635010 Moderate positive Q5296 C 12530369761 A 10635011 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 E 0 E 11 NA Q10624171 E 0 E 12 NA Q10704108 E 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 Q3822211 E 0 E 22 NA Q4000726 E 0 E 23 NA Q6451977 E 0 E 24 NA Q6473609 E 0 E 25 NA Q6916875 E 0 E 26 NA Q6918381 E 0 E 27 NA Q6918965 E 0 E 28 NA Q6920428 E 0 E 29 NA Q7158411 E 0 E 30 NA ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ Q384060 D 2047954248 B 10634982 NA Q1048694 E 2048095025 B 10634983 NA Q31165 E 2048330818 B 10634984 NA Q40629 E 2049755644 B 10634985 NA Q105584 E 2049926923 B 10634986 NA Q4584301 E 2052339927 B 10634987 NA Q565 D 2052996261 B 10634988 NA Q1868372 E 2056080224 B 10634989 NA Q209330 D 2060928966 B 10634990 NA Q14005 D 2063120071 B 10634991 NA Q918 D 2063217449 B 10634992 NA Q150248 E 2068796814 B 10634993 NA Q866 D 2079749157 B 10634994 NA Q477675 E 2080785713 B 10634995 NA Q1967876 E 2084215818 B 10634996 NA Q750403 E 2084693498 B 10634997 NA Q355 D 2093900731 B 10634998 NA Q623578 E 2097991400 B 10634999 NA Q33999 C 2108672678 B 10635000 Moderate positive Q2494649 E 2114531894 B 10635001 NA Q2597810 E 2128920607 B 10635002 NA Q193563 D 2130725560 B 10635003 NA Q423048 D 2136131564 B 10635004 NA Q37312 D 2142913121 B 10635005 NA Q54919 D 2148531382 B 10635006 NA Q36578 D 2229315598 B 10635007 NA Q30 C 2277746226 B 10635008 Moderate positive Q6581097 D 3273952711 B 10635009 NA Q5 C 5668008721 B 10635010 Moderate positive Q5296 C 12530369761 A 10635011 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 E 0 E 11 NA Q10624171 E 0 E 12 NA Q10704108 E 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 Q3822211 E 0 E 22 NA Q4000726 E 0 E 23 NA Q6451977 E 0 E 24 NA Q6473609 E 0 E 25 NA Q6916875 E 0 E 26 NA Q6918381 E 0 E 27 NA Q6918965 E 0 E 28 NA Q6920428 E 0 E 29 NA Q7158411 E 0 E 30 NA ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ Q384060 D 2047954248 B 10634982 NA Q1048694 E 2048095025 B 10634983 NA Q31165 E 2048330818 B 10634984 NA Q40629 E 2049755644 B 10634985 NA Q105584 E 2049926923 B 10634986 NA Q4584301 E 2052339927 B 10634987 NA Q565 D 2052996261 B 10634988 NA Q1868372 E 2056080224 B 10634989 NA Q209330 D 2060928966 B 10634990 NA Q14005 D 2063120071 B 10634991 NA Q918 D 2063217449 B 10634992 NA Q150248 E 2068796814 B 10634993 NA Q866 D 2079749157 B 10634994 NA Q477675 E 2080785713 B 10634995 NA Q1967876 E 2084215818 B 10634996 NA Q750403 E 2084693498 B 10634997 NA Q355 D 2093900731 B 10634998 NA Q623578 E 2097991400 B 10634999 NA Q33999 C 2108672678 B 10635000 Moderate positive Q2494649 E 2114531894 B 10635001 NA Q2597810 E 2128920607 B 10635002 NA Q193563 D 2130725560 B 10635003 NA Q423048 D 2136131564 B 10635004 NA Q37312 D 2142913121 B 10635005 NA Q54919 D 2148531382 B 10635006 NA Q36578 D 2229315598 B 10635007 NA Q30 C 2277746226 B 10635008 Moderate positive Q6581097 D 3273952711 B 10635009 NA Q5 C 5668008721 B 10635010 Moderate positive Q5296 C 12530369761 A 10635011 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 E 0 E 11 NA Q10624171 E 0 E 12 NA Q10704108 E 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 Q3822211 E 0 E 22 NA Q4000726 E 0 E 23 NA Q6451977 E 0 E 24 NA Q6473609 E 0 E 25 NA Q6916875 E 0 E 26 NA Q6918381 E 0 E 27 NA Q6918965 E 0 E 28 NA Q6920428 E 0 E 29 NA Q7158411 E 0 E 30 NA ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ Q384060 D 2047954248 B 10634982 NA Q1048694 E 2048095025 B 10634983 NA Q31165 E 2048330818 B 10634984 NA Q40629 E 2049755644 B 10634985 NA Q105584 E 2049926923 B 10634986 NA Q4584301 E 2052339927 B 10634987 NA Q565 D 2052996261 B 10634988 NA Q1868372 E 2056080224 B 10634989 NA Q209330 D 2060928966 B 10634990 NA Q14005 D 2063120071 B 10634991 NA Q918 D 2063217449 B 10634992 NA Q150248 E 2068796814 B 10634993 NA Q866 D 2079749157 B 10634994 NA Q477675 E 2080785713 B 10634995 NA Q1967876 E 2084215818 B 10634996 NA Q750403 E 2084693498 B 10634997 NA Q355 D 2093900731 B 10634998 NA Q623578 E 2097991400 B 10634999 NA Q33999 C 2108672678 B 10635000 Moderate positive Q2494649 E 2114531894 B 10635001 NA Q2597810 E 2128920607 B 10635002 NA Q193563 D 2130725560 B 10635003 NA Q423048 D 2136131564 B 10635004 NA Q37312 D 2142913121 B 10635005 NA Q54919 D 2148531382 B 10635006 NA Q36578 D 2229315598 B 10635007 NA Q30 C 2277746226 B 10635008 Moderate positive Q6581097 D 3273952711 B 10635009 NA Q5 C 5668008721 B 10635010 Moderate positive Q5296 C 12530369761 A 10635011 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 E 0 E 11 NA Q10624171 E 0 E 12 NA Q10704108 E 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 Q3822211 E 0 E 22 NA Q4000726 E 0 E 23 NA Q6451977 E 0 E 24 NA Q6473609 E 0 E 25 NA Q6916875 E 0 E 26 NA Q6918381 E 0 E 27 NA Q6918965 E 0 E 28 NA Q6920428 E 0 E 29 NA Q7158411 E 0 E 30 NA ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ Q384060 D 2047954248 B 10634982 High positive Q1048694 E 2048095025 B 10634983 NA Q31165 E 2048330818 B 10634984 NA Q40629 E 2049755644 B 10634985 NA Q105584 E 2049926923 B 10634986 NA Q4584301 E 2052339927 B 10634987 NA Q565 D 2052996261 B 10634988 High positive Q1868372 E 2056080224 B 10634989 NA Q209330 D 2060928966 B 10634990 High positive Q14005 D 2063120071 B 10634991 High positive Q918 D 2063217449 B 10634992 High positive Q150248 E 2068796814 B 10634993 NA Q866 D 2079749157 B 10634994 High positive Q477675 E 2080785713 B 10634995 NA Q1967876 E 2084215818 B 10634996 NA Q750403 E 2084693498 B 10634997 NA Q355 D 2093900731 B 10634998 High positive Q623578 E 2097991400 B 10634999 NA Q33999 C 2108672678 B 10635000 Moderate positive Q2494649 E 2114531894 B 10635001 NA Q2597810 E 2128920607 B 10635002 NA Q193563 D 2130725560 B 10635003 High positive Q423048 D 2136131564 B 10635004 High positive Q37312 D 2142913121 B 10635005 High positive Q54919 D 2148531382 B 10635006 High positive Q36578 D 2229315598 B 10635007 High positive Q30 C 2277746226 B 10635008 Moderate positive Q6581097 D 3273952711 B 10635009 High positive Q5 C 5668008721 B 10635010 Moderate positive Q5296 C 12530369761 A 10635011 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 E 0 E 11 None Q10624171 E 0 E 12 None Q10704108 E 0 E 13 None 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 Q3822211 E 0 E 22 None Q4000726 E 0 E 23 None Q6451977 E 0 E 24 None Q6473609 E 0 E 25 None Q6916875 E 0 E 26 None Q6918381 E 0 E 27 None Q6918965 E 0 E 28 None Q6920428 E 0 E 29 None Q7158411 E 0 E 30 None ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ Q384060 D 2047954248 B 10634982 High positive Q1048694 E 2048095025 B 10634983 NA Q31165 E 2048330818 B 10634984 NA Q40629 E 2049755644 B 10634985 NA Q105584 E 2049926923 B 10634986 NA Q4584301 E 2052339927 B 10634987 NA Q565 D 2052996261 B 10634988 High positive Q1868372 E 2056080224 B 10634989 NA Q209330 D 2060928966 B 10634990 High positive Q14005 D 2063120071 B 10634991 High positive Q918 D 2063217449 B 10634992 High positive Q150248 E 2068796814 B 10634993 NA Q866 D 2079749157 B 10634994 High positive Q477675 E 2080785713 B 10634995 NA Q1967876 E 2084215818 B 10634996 NA Q750403 E 2084693498 B 10634997 NA Q355 D 2093900731 B 10634998 High positive Q623578 E 2097991400 B 10634999 NA Q33999 C 2108672678 B 10635000 Moderate positive Q2494649 E 2114531894 B 10635001 NA Q2597810 E 2128920607 B 10635002 NA Q193563 D 2130725560 B 10635003 High positive Q423048 D 2136131564 B 10635004 High positive Q37312 D 2142913121 B 10635005 High positive Q54919 D 2148531382 B 10635006 High positive Q36578 D 2229315598 B 10635007 High positive Q30 C 2277746226 B 10635008 Moderate positive Q6581097 D 3273952711 B 10635009 High positive Q5 C 5668008721 B 10635010 Moderate positive Q5296 C 12530369761 A 10635011 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 E 0 E 11 None Q10624171 E 0 E 12 None Q10704108 E 0 E 13 None 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 Q3822211 E 0 E 22 None Q4000726 E 0 E 23 None Q6451977 E 0 E 24 None Q6473609 E 0 E 25 None Q6916875 E 0 E 26 None Q6918381 E 0 E 27 None Q6918965 E 0 E 28 None Q6920428 E 0 E 29 None Q7158411 E 0 E 30 None ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ Q384060 D 2047954248 B 10634982 High positive Q1048694 E 2048095025 B 10634983 NA Q31165 E 2048330818 B 10634984 NA Q40629 E 2049755644 B 10634985 NA Q105584 E 2049926923 B 10634986 NA Q4584301 E 2052339927 B 10634987 NA Q565 D 2052996261 B 10634988 High positive Q1868372 E 2056080224 B 10634989 NA Q209330 D 2060928966 B 10634990 High positive Q14005 D 2063120071 B 10634991 High positive Q918 D 2063217449 B 10634992 High positive Q150248 E 2068796814 B 10634993 NA Q866 D 2079749157 B 10634994 High positive Q477675 E 2080785713 B 10634995 NA Q1967876 E 2084215818 B 10634996 NA Q750403 E 2084693498 B 10634997 NA Q355 D 2093900731 B 10634998 High positive Q623578 E 2097991400 B 10634999 NA Q33999 C 2108672678 B 10635000 Moderate positive Q2494649 E 2114531894 B 10635001 NA Q2597810 E 2128920607 B 10635002 NA Q193563 D 2130725560 B 10635003 High positive Q423048 D 2136131564 B 10635004 High positive Q37312 D 2142913121 B 10635005 High positive Q54919 D 2148531382 B 10635006 High positive Q36578 D 2229315598 B 10635007 High positive Q30 C 2277746226 B 10635008 Moderate positive Q6581097 D 3273952711 B 10635009 High positive Q5 C 5668008721 B 10635010 Moderate positive Q5296 C 12530369761 A 10635011 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 E 0 E 11 None Q10624171 E 0 E 12 None Q10704108 E 0 E 13 None 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 Q3822211 E 0 E 22 None Q4000726 E 0 E 23 None Q6451977 E 0 E 24 None Q6473609 E 0 E 25 None Q6916875 E 0 E 26 None Q6918381 E 0 E 27 None Q6918965 E 0 E 28 None Q6920428 E 0 E 29 None Q7158411 E 0 E 30 None ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ Q384060 D 2047954248 B 10634982 High positive Q1048694 E 2048095025 B 10634983 High positive Q31165 E 2048330818 B 10634984 High positive Q40629 E 2049755644 B 10634985 High positive Q105584 E 2049926923 B 10634986 High positive Q4584301 E 2052339927 B 10634987 High positive Q565 D 2052996261 B 10634988 High positive Q1868372 E 2056080224 B 10634989 High positive Q209330 D 2060928966 B 10634990 High positive Q14005 D 2063120071 B 10634991 High positive Q918 D 2063217449 B 10634992 High positive Q150248 E 2068796814 B 10634993 High positive Q866 D 2079749157 B 10634994 High positive Q477675 E 2080785713 B 10634995 High positive Q1967876 E 2084215818 B 10634996 High positive Q750403 E 2084693498 B 10634997 High positive Q355 D 2093900731 B 10634998 High positive Q623578 E 2097991400 B 10634999 High positive Q33999 C 2108672678 B 10635000 Moderate positive Q2494649 E 2114531894 B 10635001 High positive Q2597810 E 2128920607 B 10635002 High positive Q193563 D 2130725560 B 10635003 High positive Q423048 D 2136131564 B 10635004 High positive Q37312 D 2142913121 B 10635005 High positive Q54919 D 2148531382 B 10635006 High positive Q36578 D 2229315598 B 10635007 High positive Q30 C 2277746226 B 10635008 Moderate positive Q6581097 D 3273952711 B 10635009 High positive Q5 C 5668008721 B 10635010 Moderate positive Q5296 C 12530369761 A 10635011 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 93.9 3.8 2.3 D 0.0 74.3 11.8 13.7 0.1 C 73.6 11.8 14.4 0.2 0.0 B 99.6 0.4 0.0 0.0 0.0 A 0.0 100.0 0.0 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 16967441541 D Moderate negative 1412642245 C High negative 1186553912 B High negative 4269206 E Moderate positive 14829756861 C Moderate negative 1661454045 D None 2301976532 E High positive 227331534900 D Moderate positive 37779686885 C None 34463985002 B Moderate negative 10640589 C Moderate positive 34041081597 D High positive 86531533656 A Moderate negative 653480145 C High positive 12530369761
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 53733403075 Moderate negative 3738217024 High negative 1190823118 Moderate positive 86650525343 High positive 326393438317
In [43]:
articles_by_pop[,sum(as.numeric(page_views))];
471706406877
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 11.39128
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 0.7924881
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 0.2524501
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 18.36959
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 69.19419
Content source: hall1467/wikidata_usage_tracking
Similar notebooks: