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_20140801.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. : 1.0 Min. :0.000e+00 A: 47
Q100 : 1 1st Qu.: 9.0 1st Qu.:4.400e+01 B: 22002
Q1000 : 1 Median : 17.0 Median :3.150e+02 C: 1309654
Q10000 : 1 Mean : 22.2 Mean :3.390e+04 D: 1902617
Q100000 : 1 3rd Qu.: 29.0 3rd Qu.:1.800e+03 E:11719667
Q1000000: 1 Max. :21863.0 Max. :1.253e+10
(Other) :14953981
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 D 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 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 C 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 E 0 11 Q10624171 D 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 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 14953958 Q31165 C 2048330818 14953959 Q40629 C 2049755644 14953960 Q105584 C 2049926923 14953961 Q4584301 D 2052339927 14953962 Q565 C 2052996261 14953963 Q1868372 E 2056080224 14953964 Q209330 C 2060928966 14953965 Q14005 C 2063120071 14953966 Q918 C 2063217449 14953967 Q150248 C 2068796814 14953968 Q866 C 2079749157 14953969 Q477675 C 2080785713 14953970 Q1967876 C 2084215818 14953971 Q750403 C 2084693498 14953972 Q355 C 2093900731 14953973 Q623578 C 2097991400 14953974 Q17299517 D 2105487660 14953975 Q33999 C 2108672678 14953976 Q2494649 C 2114531894 14953977 Q2597810 C 2128920607 14953978 Q193563 C 2130725560 14953979 Q423048 C 2136131564 14953980 Q37312 C 2142913121 14953981 Q54919 C 2148531382 14953982 Q36578 C 2229315598 14953983 Q30 A 2277746226 14953984 Q6581097 C 3273952711 14953985 Q5 A 5668008721 14953986 Q5296 C 12530369761 14953987
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]$narticles;
print(paste('start_idx =', start_idx, ', end_idx = ', end_idx));
dataset[seqNum >= start_idx & seqNum <= end_idx, pop_class := rating];
prev_idx = end_idx -1;
}
dataset;
}
In [13]:
articles_by_pop = assign_pop_class(articles_by_pop,
assessment_classes, n_per_class);
[1] "start_idx = 1 , end_idx = 11719668"
[1] "start_idx = 11719668 , end_idx = 13622285"
[1] "start_idx = 13622285 , end_idx = 14931939"
[1] "start_idx = 14931939 , end_idx = 14953941"
[1] "start_idx = 14953941 , end_idx = 14953988"
In [14]:
create_dissonance_matrix = function(articledata, classes) {
d_mtrx = matrix(0, nrow=length(classes), ncol=length(classes));
rownames(d_mtrx) = classes;
colnames(d_mtrx) = classes;
for(real_rating in classes) {
for(pop_rating in classes) {
d_mtrx[real_rating, pop_rating] = length(articledata[prediction == real_rating & pop_class == pop_rating]$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 9577345 1371463 767420 3437 2 D 1456470 241894 201411 2838 4 C 675201 284887 334274 15253 39 B 10651 4371 6546 434 0 A 0 2 3 40 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[,])
0.679012827816421
In [18]:
# A class quality and A class views over A class quality
dissonance_matrix[5,5]/sum(dissonance_matrix[5,])
0.0425531914893617
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,])
0.0425531914893617
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,])
0.957446808510638
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])
0.957446808510638
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 Q156376 2046132338 83 Q1868372 2056080224 45
In [24]:
## Q: why do I get _two_ pageid columns? Solution is to do the selection
## on the joined table, not as a select _in_ the join.
## Dissonance matrix proportions by row (..., 1) and column (..., 2)
## rounded to 1 decimal places.
In [25]:
round(100*prop.table(dissonance_matrix, 1), 1);
E D C B A E 81.7 11.7 6.5 0.0 0.0 D 76.6 12.7 10.6 0.1 0.0 C 51.6 21.8 25.5 1.2 0.0 B 48.4 19.9 29.8 2.0 0.0 A 0.0 4.3 6.4 85.1 4.3
In [26]:
round(100*prop.table(dissonance_matrix, 2), 1);
E D C B A E 81.7 72.1 58.6 15.6 4.3 D 12.4 12.7 15.4 12.9 8.5 C 5.8 15.0 25.5 69.3 83.0 B 0.1 0.2 0.5 2.0 0.0 A 0.0 0.0 0.0 0.2 4.3
In [27]:
## Let's write the stubs out to a file
write.table(merge(articles_by_pop[(prediction == 'E' | prediction == 'D' | prediction == 'C' | prediction == 'B') & pop_class == 'A'], quality_prediction_and_page_views, by='entity_id')[, c("entity_id","pop_class", "prediction.x")],
'../../results/entity_categorization/201408_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 Q103204 A C Q1048694 A C Q105584 A C Q10726338 A D Q1123836 A C Q116933 A C Q14005 A C Q150248 A C Q156376 A E Q171186 A C Q17299517 A D Q1868372 A E Q193563 A C Q1967876 A C Q209330 A C Q223142 A C Q2494649 A C Q2597810 A C Q31165 A C Q33999 A C Q355 A C Q356 A C Q36578 A C Q37312 A C Q384060 A C Q40629 A C Q41226 A C Q423048 A C Q4584301 A D Q477675 A C Q51044 A C Q523660 A D Q5296 A C Q54919 A C Q565 A C Q568769 A C Q620946 A C Q623578 A C Q63056 A C Q6581097 A C Q750403 A C Q809830 A C Q829984 A C Q866 A C Q918 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/201408_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/201408_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/201408_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 D 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 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 14953958 Q31165 C 2048330818 A 14953959 Q40629 C 2049755644 A 14953960 Q105584 C 2049926923 A 14953961 Q4584301 D 2052339927 A 14953962 Q565 C 2052996261 A 14953963 Q1868372 E 2056080224 A 14953964 Q209330 C 2060928966 A 14953965 Q14005 C 2063120071 A 14953966 Q918 C 2063217449 A 14953967 Q150248 C 2068796814 A 14953968 Q866 C 2079749157 A 14953969 Q477675 C 2080785713 A 14953970 Q1967876 C 2084215818 A 14953971 Q750403 C 2084693498 A 14953972 Q355 C 2093900731 A 14953973 Q623578 C 2097991400 A 14953974 Q17299517 D 2105487660 A 14953975 Q33999 C 2108672678 A 14953976 Q2494649 C 2114531894 A 14953977 Q2597810 C 2128920607 A 14953978 Q193563 C 2130725560 A 14953979 Q423048 C 2136131564 A 14953980 Q37312 C 2142913121 A 14953981 Q54919 C 2148531382 A 14953982 Q36578 C 2229315598 A 14953983 Q30 A 2277746226 A 14953984 Q6581097 C 3273952711 A 14953985 Q5 A 5668008721 A 14953986 Q5296 C 12530369761 A 14953987
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 D 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 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 14953958 NA Q31165 C 2048330818 A 14953959 NA Q40629 C 2049755644 A 14953960 NA Q105584 C 2049926923 A 14953961 NA Q4584301 D 2052339927 A 14953962 NA Q565 C 2052996261 A 14953963 NA Q1868372 E 2056080224 A 14953964 NA Q209330 C 2060928966 A 14953965 NA Q14005 C 2063120071 A 14953966 NA Q918 C 2063217449 A 14953967 NA Q150248 C 2068796814 A 14953968 NA Q866 C 2079749157 A 14953969 NA Q477675 C 2080785713 A 14953970 NA Q1967876 C 2084215818 A 14953971 NA Q750403 C 2084693498 A 14953972 NA Q355 C 2093900731 A 14953973 NA Q623578 C 2097991400 A 14953974 NA Q17299517 D 2105487660 A 14953975 NA Q33999 C 2108672678 A 14953976 NA Q2494649 C 2114531894 A 14953977 NA Q2597810 C 2128920607 A 14953978 NA Q193563 C 2130725560 A 14953979 NA Q423048 C 2136131564 A 14953980 NA Q37312 C 2142913121 A 14953981 NA Q54919 C 2148531382 A 14953982 NA Q36578 C 2229315598 A 14953983 NA Q30 A 2277746226 A 14953984 NA Q6581097 C 3273952711 A 14953985 NA Q5 A 5668008721 A 14953986 NA Q5296 C 12530369761 A 14953987 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 D 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 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 14953958 NA Q31165 C 2048330818 A 14953959 NA Q40629 C 2049755644 A 14953960 NA Q105584 C 2049926923 A 14953961 NA Q4584301 D 2052339927 A 14953962 NA Q565 C 2052996261 A 14953963 NA Q1868372 E 2056080224 A 14953964 NA Q209330 C 2060928966 A 14953965 NA Q14005 C 2063120071 A 14953966 NA Q918 C 2063217449 A 14953967 NA Q150248 C 2068796814 A 14953968 NA Q866 C 2079749157 A 14953969 NA Q477675 C 2080785713 A 14953970 NA Q1967876 C 2084215818 A 14953971 NA Q750403 C 2084693498 A 14953972 NA Q355 C 2093900731 A 14953973 NA Q623578 C 2097991400 A 14953974 NA Q17299517 D 2105487660 A 14953975 NA Q33999 C 2108672678 A 14953976 NA Q2494649 C 2114531894 A 14953977 NA Q2597810 C 2128920607 A 14953978 NA Q193563 C 2130725560 A 14953979 NA Q423048 C 2136131564 A 14953980 NA Q37312 C 2142913121 A 14953981 NA Q54919 C 2148531382 A 14953982 NA Q36578 C 2229315598 A 14953983 NA Q30 A 2277746226 A 14953984 NA Q6581097 C 3273952711 A 14953985 NA Q5 A 5668008721 A 14953986 NA Q5296 C 12530369761 A 14953987 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 D 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 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 14953958 NA Q31165 C 2048330818 A 14953959 NA Q40629 C 2049755644 A 14953960 NA Q105584 C 2049926923 A 14953961 NA Q4584301 D 2052339927 A 14953962 NA Q565 C 2052996261 A 14953963 NA Q1868372 E 2056080224 A 14953964 NA Q209330 C 2060928966 A 14953965 NA Q14005 C 2063120071 A 14953966 NA Q918 C 2063217449 A 14953967 NA Q150248 C 2068796814 A 14953968 NA Q866 C 2079749157 A 14953969 NA Q477675 C 2080785713 A 14953970 NA Q1967876 C 2084215818 A 14953971 NA Q750403 C 2084693498 A 14953972 NA Q355 C 2093900731 A 14953973 NA Q623578 C 2097991400 A 14953974 NA Q17299517 D 2105487660 A 14953975 NA Q33999 C 2108672678 A 14953976 NA Q2494649 C 2114531894 A 14953977 NA Q2597810 C 2128920607 A 14953978 NA Q193563 C 2130725560 A 14953979 NA Q423048 C 2136131564 A 14953980 NA Q37312 C 2142913121 A 14953981 NA Q54919 C 2148531382 A 14953982 NA Q36578 C 2229315598 A 14953983 NA Q30 A 2277746226 A 14953984 NA Q6581097 C 3273952711 A 14953985 NA Q5 A 5668008721 A 14953986 NA Q5296 C 12530369761 A 14953987 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 D 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 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 14953958 NA Q31165 C 2048330818 A 14953959 NA Q40629 C 2049755644 A 14953960 NA Q105584 C 2049926923 A 14953961 NA Q4584301 D 2052339927 A 14953962 NA Q565 C 2052996261 A 14953963 NA Q1868372 E 2056080224 A 14953964 NA Q209330 C 2060928966 A 14953965 NA Q14005 C 2063120071 A 14953966 NA Q918 C 2063217449 A 14953967 NA Q150248 C 2068796814 A 14953968 NA Q866 C 2079749157 A 14953969 NA Q477675 C 2080785713 A 14953970 NA Q1967876 C 2084215818 A 14953971 NA Q750403 C 2084693498 A 14953972 NA Q355 C 2093900731 A 14953973 NA Q623578 C 2097991400 A 14953974 NA Q17299517 D 2105487660 A 14953975 NA Q33999 C 2108672678 A 14953976 NA Q2494649 C 2114531894 A 14953977 NA Q2597810 C 2128920607 A 14953978 NA Q193563 C 2130725560 A 14953979 NA Q423048 C 2136131564 A 14953980 NA Q37312 C 2142913121 A 14953981 NA Q54919 C 2148531382 A 14953982 NA Q36578 C 2229315598 A 14953983 NA Q30 A 2277746226 A 14953984 None Q6581097 C 3273952711 A 14953985 NA Q5 A 5668008721 A 14953986 None Q5296 C 12530369761 A 14953987 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 D 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 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 14953958 NA Q31165 C 2048330818 A 14953959 NA Q40629 C 2049755644 A 14953960 NA Q105584 C 2049926923 A 14953961 NA Q4584301 D 2052339927 A 14953962 NA Q565 C 2052996261 A 14953963 NA Q1868372 E 2056080224 A 14953964 NA Q209330 C 2060928966 A 14953965 NA Q14005 C 2063120071 A 14953966 NA Q918 C 2063217449 A 14953967 NA Q150248 C 2068796814 A 14953968 NA Q866 C 2079749157 A 14953969 NA Q477675 C 2080785713 A 14953970 NA Q1967876 C 2084215818 A 14953971 NA Q750403 C 2084693498 A 14953972 NA Q355 C 2093900731 A 14953973 NA Q623578 C 2097991400 A 14953974 NA Q17299517 D 2105487660 A 14953975 NA Q33999 C 2108672678 A 14953976 NA Q2494649 C 2114531894 A 14953977 NA Q2597810 C 2128920607 A 14953978 NA Q193563 C 2130725560 A 14953979 NA Q423048 C 2136131564 A 14953980 NA Q37312 C 2142913121 A 14953981 NA Q54919 C 2148531382 A 14953982 NA Q36578 C 2229315598 A 14953983 NA Q30 A 2277746226 A 14953984 None Q6581097 C 3273952711 A 14953985 NA Q5 A 5668008721 A 14953986 None Q5296 C 12530369761 A 14953987 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 D 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 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 14953958 NA Q31165 C 2048330818 A 14953959 NA Q40629 C 2049755644 A 14953960 NA Q105584 C 2049926923 A 14953961 NA Q4584301 D 2052339927 A 14953962 NA Q565 C 2052996261 A 14953963 NA Q1868372 E 2056080224 A 14953964 NA Q209330 C 2060928966 A 14953965 NA Q14005 C 2063120071 A 14953966 NA Q918 C 2063217449 A 14953967 NA Q150248 C 2068796814 A 14953968 NA Q866 C 2079749157 A 14953969 NA Q477675 C 2080785713 A 14953970 NA Q1967876 C 2084215818 A 14953971 NA Q750403 C 2084693498 A 14953972 NA Q355 C 2093900731 A 14953973 NA Q623578 C 2097991400 A 14953974 NA Q17299517 D 2105487660 A 14953975 NA Q33999 C 2108672678 A 14953976 NA Q2494649 C 2114531894 A 14953977 NA Q2597810 C 2128920607 A 14953978 NA Q193563 C 2130725560 A 14953979 NA Q423048 C 2136131564 A 14953980 NA Q37312 C 2142913121 A 14953981 NA Q54919 C 2148531382 A 14953982 NA Q36578 C 2229315598 A 14953983 NA Q30 A 2277746226 A 14953984 None Q6581097 C 3273952711 A 14953985 NA Q5 A 5668008721 A 14953986 None Q5296 C 12530369761 A 14953987 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 D 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 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 14953958 NA Q31165 C 2048330818 A 14953959 NA Q40629 C 2049755644 A 14953960 NA Q105584 C 2049926923 A 14953961 NA Q4584301 D 2052339927 A 14953962 NA Q565 C 2052996261 A 14953963 NA Q1868372 E 2056080224 A 14953964 NA Q209330 C 2060928966 A 14953965 NA Q14005 C 2063120071 A 14953966 NA Q918 C 2063217449 A 14953967 NA Q150248 C 2068796814 A 14953968 NA Q866 C 2079749157 A 14953969 NA Q477675 C 2080785713 A 14953970 NA Q1967876 C 2084215818 A 14953971 NA Q750403 C 2084693498 A 14953972 NA Q355 C 2093900731 A 14953973 NA Q623578 C 2097991400 A 14953974 NA Q17299517 D 2105487660 A 14953975 NA Q33999 C 2108672678 A 14953976 NA Q2494649 C 2114531894 A 14953977 NA Q2597810 C 2128920607 A 14953978 NA Q193563 C 2130725560 A 14953979 NA Q423048 C 2136131564 A 14953980 NA Q37312 C 2142913121 A 14953981 NA Q54919 C 2148531382 A 14953982 NA Q36578 C 2229315598 A 14953983 NA Q30 A 2277746226 A 14953984 None Q6581097 C 3273952711 A 14953985 NA Q5 A 5668008721 A 14953986 None Q5296 C 12530369761 A 14953987 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 D 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 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 14953958 NA Q31165 C 2048330818 A 14953959 NA Q40629 C 2049755644 A 14953960 NA Q105584 C 2049926923 A 14953961 NA Q4584301 D 2052339927 A 14953962 NA Q565 C 2052996261 A 14953963 NA Q1868372 E 2056080224 A 14953964 NA Q209330 C 2060928966 A 14953965 NA Q14005 C 2063120071 A 14953966 NA Q918 C 2063217449 A 14953967 NA Q150248 C 2068796814 A 14953968 NA Q866 C 2079749157 A 14953969 NA Q477675 C 2080785713 A 14953970 NA Q1967876 C 2084215818 A 14953971 NA Q750403 C 2084693498 A 14953972 NA Q355 C 2093900731 A 14953973 NA Q623578 C 2097991400 A 14953974 NA Q17299517 D 2105487660 A 14953975 NA Q33999 C 2108672678 A 14953976 NA Q2494649 C 2114531894 A 14953977 NA Q2597810 C 2128920607 A 14953978 NA Q193563 C 2130725560 A 14953979 NA Q423048 C 2136131564 A 14953980 NA Q37312 C 2142913121 A 14953981 NA Q54919 C 2148531382 A 14953982 NA Q36578 C 2229315598 A 14953983 NA Q30 A 2277746226 A 14953984 None Q6581097 C 3273952711 A 14953985 NA Q5 A 5668008721 A 14953986 None Q5296 C 12530369761 A 14953987 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 D 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 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 14953958 NA Q31165 C 2048330818 A 14953959 NA Q40629 C 2049755644 A 14953960 NA Q105584 C 2049926923 A 14953961 NA Q4584301 D 2052339927 A 14953962 NA Q565 C 2052996261 A 14953963 NA Q1868372 E 2056080224 A 14953964 NA Q209330 C 2060928966 A 14953965 NA Q14005 C 2063120071 A 14953966 NA Q918 C 2063217449 A 14953967 NA Q150248 C 2068796814 A 14953968 NA Q866 C 2079749157 A 14953969 NA Q477675 C 2080785713 A 14953970 NA Q1967876 C 2084215818 A 14953971 NA Q750403 C 2084693498 A 14953972 NA Q355 C 2093900731 A 14953973 NA Q623578 C 2097991400 A 14953974 NA Q17299517 D 2105487660 A 14953975 NA Q33999 C 2108672678 A 14953976 NA Q2494649 C 2114531894 A 14953977 NA Q2597810 C 2128920607 A 14953978 NA Q193563 C 2130725560 A 14953979 NA Q423048 C 2136131564 A 14953980 NA Q37312 C 2142913121 A 14953981 NA Q54919 C 2148531382 A 14953982 NA Q36578 C 2229315598 A 14953983 NA Q30 A 2277746226 A 14953984 None Q6581097 C 3273952711 A 14953985 NA Q5 A 5668008721 A 14953986 None Q5296 C 12530369761 A 14953987 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 D 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 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 14953958 NA Q31165 C 2048330818 A 14953959 NA Q40629 C 2049755644 A 14953960 NA Q105584 C 2049926923 A 14953961 NA Q4584301 D 2052339927 A 14953962 NA Q565 C 2052996261 A 14953963 NA Q1868372 E 2056080224 A 14953964 NA Q209330 C 2060928966 A 14953965 NA Q14005 C 2063120071 A 14953966 NA Q918 C 2063217449 A 14953967 NA Q150248 C 2068796814 A 14953968 NA Q866 C 2079749157 A 14953969 NA Q477675 C 2080785713 A 14953970 NA Q1967876 C 2084215818 A 14953971 NA Q750403 C 2084693498 A 14953972 NA Q355 C 2093900731 A 14953973 NA Q623578 C 2097991400 A 14953974 NA Q17299517 D 2105487660 A 14953975 NA Q33999 C 2108672678 A 14953976 NA Q2494649 C 2114531894 A 14953977 NA Q2597810 C 2128920607 A 14953978 NA Q193563 C 2130725560 A 14953979 NA Q423048 C 2136131564 A 14953980 NA Q37312 C 2142913121 A 14953981 NA Q54919 C 2148531382 A 14953982 NA Q36578 C 2229315598 A 14953983 NA Q30 A 2277746226 A 14953984 None Q6581097 C 3273952711 A 14953985 NA Q5 A 5668008721 A 14953986 None Q5296 C 12530369761 A 14953987 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 D 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 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 14953958 NA Q31165 C 2048330818 A 14953959 NA Q40629 C 2049755644 A 14953960 NA Q105584 C 2049926923 A 14953961 NA Q4584301 D 2052339927 A 14953962 NA Q565 C 2052996261 A 14953963 NA Q1868372 E 2056080224 A 14953964 NA Q209330 C 2060928966 A 14953965 NA Q14005 C 2063120071 A 14953966 NA Q918 C 2063217449 A 14953967 NA Q150248 C 2068796814 A 14953968 NA Q866 C 2079749157 A 14953969 NA Q477675 C 2080785713 A 14953970 NA Q1967876 C 2084215818 A 14953971 NA Q750403 C 2084693498 A 14953972 NA Q355 C 2093900731 A 14953973 NA Q623578 C 2097991400 A 14953974 NA Q17299517 D 2105487660 A 14953975 NA Q33999 C 2108672678 A 14953976 NA Q2494649 C 2114531894 A 14953977 NA Q2597810 C 2128920607 A 14953978 NA Q193563 C 2130725560 A 14953979 NA Q423048 C 2136131564 A 14953980 NA Q37312 C 2142913121 A 14953981 NA Q54919 C 2148531382 A 14953982 NA Q36578 C 2229315598 A 14953983 NA Q30 A 2277746226 A 14953984 None Q6581097 C 3273952711 A 14953985 NA Q5 A 5668008721 A 14953986 None Q5296 C 12530369761 A 14953987 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 D 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 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 14953958 NA Q31165 C 2048330818 A 14953959 NA Q40629 C 2049755644 A 14953960 NA Q105584 C 2049926923 A 14953961 NA Q4584301 D 2052339927 A 14953962 NA Q565 C 2052996261 A 14953963 NA Q1868372 E 2056080224 A 14953964 NA Q209330 C 2060928966 A 14953965 NA Q14005 C 2063120071 A 14953966 NA Q918 C 2063217449 A 14953967 NA Q150248 C 2068796814 A 14953968 NA Q866 C 2079749157 A 14953969 NA Q477675 C 2080785713 A 14953970 NA Q1967876 C 2084215818 A 14953971 NA Q750403 C 2084693498 A 14953972 NA Q355 C 2093900731 A 14953973 NA Q623578 C 2097991400 A 14953974 NA Q17299517 D 2105487660 A 14953975 NA Q33999 C 2108672678 A 14953976 NA Q2494649 C 2114531894 A 14953977 NA Q2597810 C 2128920607 A 14953978 NA Q193563 C 2130725560 A 14953979 NA Q423048 C 2136131564 A 14953980 NA Q37312 C 2142913121 A 14953981 NA Q54919 C 2148531382 A 14953982 NA Q36578 C 2229315598 A 14953983 NA Q30 A 2277746226 A 14953984 None Q6581097 C 3273952711 A 14953985 NA Q5 A 5668008721 A 14953986 None Q5296 C 12530369761 A 14953987 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 D 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 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 14953958 High positive Q31165 C 2048330818 A 14953959 High positive Q40629 C 2049755644 A 14953960 High positive Q105584 C 2049926923 A 14953961 High positive Q4584301 D 2052339927 A 14953962 NA Q565 C 2052996261 A 14953963 High positive Q1868372 E 2056080224 A 14953964 NA Q209330 C 2060928966 A 14953965 High positive Q14005 C 2063120071 A 14953966 High positive Q918 C 2063217449 A 14953967 High positive Q150248 C 2068796814 A 14953968 High positive Q866 C 2079749157 A 14953969 High positive Q477675 C 2080785713 A 14953970 High positive Q1967876 C 2084215818 A 14953971 High positive Q750403 C 2084693498 A 14953972 High positive Q355 C 2093900731 A 14953973 High positive Q623578 C 2097991400 A 14953974 High positive Q17299517 D 2105487660 A 14953975 NA Q33999 C 2108672678 A 14953976 High positive Q2494649 C 2114531894 A 14953977 High positive Q2597810 C 2128920607 A 14953978 High positive Q193563 C 2130725560 A 14953979 High positive Q423048 C 2136131564 A 14953980 High positive Q37312 C 2142913121 A 14953981 High positive Q54919 C 2148531382 A 14953982 High positive Q36578 C 2229315598 A 14953983 High positive Q30 A 2277746226 A 14953984 None Q6581097 C 3273952711 A 14953985 High positive Q5 A 5668008721 A 14953986 None Q5296 C 12530369761 A 14953987 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 D 0 E 12 Moderate negative 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 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 14953958 High positive Q31165 C 2048330818 A 14953959 High positive Q40629 C 2049755644 A 14953960 High positive Q105584 C 2049926923 A 14953961 High positive Q4584301 D 2052339927 A 14953962 NA Q565 C 2052996261 A 14953963 High positive Q1868372 E 2056080224 A 14953964 NA Q209330 C 2060928966 A 14953965 High positive Q14005 C 2063120071 A 14953966 High positive Q918 C 2063217449 A 14953967 High positive Q150248 C 2068796814 A 14953968 High positive Q866 C 2079749157 A 14953969 High positive Q477675 C 2080785713 A 14953970 High positive Q1967876 C 2084215818 A 14953971 High positive Q750403 C 2084693498 A 14953972 High positive Q355 C 2093900731 A 14953973 High positive Q623578 C 2097991400 A 14953974 High positive Q17299517 D 2105487660 A 14953975 NA Q33999 C 2108672678 A 14953976 High positive Q2494649 C 2114531894 A 14953977 High positive Q2597810 C 2128920607 A 14953978 High positive Q193563 C 2130725560 A 14953979 High positive Q423048 C 2136131564 A 14953980 High positive Q37312 C 2142913121 A 14953981 High positive Q54919 C 2148531382 A 14953982 High positive Q36578 C 2229315598 A 14953983 High positive Q30 A 2277746226 A 14953984 None Q6581097 C 3273952711 A 14953985 High positive Q5 A 5668008721 A 14953986 None Q5296 C 12530369761 A 14953987 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 D 0 E 12 Moderate negative 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 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 14953958 High positive Q31165 C 2048330818 A 14953959 High positive Q40629 C 2049755644 A 14953960 High positive Q105584 C 2049926923 A 14953961 High positive Q4584301 D 2052339927 A 14953962 NA Q565 C 2052996261 A 14953963 High positive Q1868372 E 2056080224 A 14953964 NA Q209330 C 2060928966 A 14953965 High positive Q14005 C 2063120071 A 14953966 High positive Q918 C 2063217449 A 14953967 High positive Q150248 C 2068796814 A 14953968 High positive Q866 C 2079749157 A 14953969 High positive Q477675 C 2080785713 A 14953970 High positive Q1967876 C 2084215818 A 14953971 High positive Q750403 C 2084693498 A 14953972 High positive Q355 C 2093900731 A 14953973 High positive Q623578 C 2097991400 A 14953974 High positive Q17299517 D 2105487660 A 14953975 NA Q33999 C 2108672678 A 14953976 High positive Q2494649 C 2114531894 A 14953977 High positive Q2597810 C 2128920607 A 14953978 High positive Q193563 C 2130725560 A 14953979 High positive Q423048 C 2136131564 A 14953980 High positive Q37312 C 2142913121 A 14953981 High positive Q54919 C 2148531382 A 14953982 High positive Q36578 C 2229315598 A 14953983 High positive Q30 A 2277746226 A 14953984 None Q6581097 C 3273952711 A 14953985 High positive Q5 A 5668008721 A 14953986 None Q5296 C 12530369761 A 14953987 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 D 0 E 12 Moderate negative 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 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 14953958 High positive Q31165 C 2048330818 A 14953959 High positive Q40629 C 2049755644 A 14953960 High positive Q105584 C 2049926923 A 14953961 High positive Q4584301 D 2052339927 A 14953962 NA Q565 C 2052996261 A 14953963 High positive Q1868372 E 2056080224 A 14953964 NA Q209330 C 2060928966 A 14953965 High positive Q14005 C 2063120071 A 14953966 High positive Q918 C 2063217449 A 14953967 High positive Q150248 C 2068796814 A 14953968 High positive Q866 C 2079749157 A 14953969 High positive Q477675 C 2080785713 A 14953970 High positive Q1967876 C 2084215818 A 14953971 High positive Q750403 C 2084693498 A 14953972 High positive Q355 C 2093900731 A 14953973 High positive Q623578 C 2097991400 A 14953974 High positive Q17299517 D 2105487660 A 14953975 NA Q33999 C 2108672678 A 14953976 High positive Q2494649 C 2114531894 A 14953977 High positive Q2597810 C 2128920607 A 14953978 High positive Q193563 C 2130725560 A 14953979 High positive Q423048 C 2136131564 A 14953980 High positive Q37312 C 2142913121 A 14953981 High positive Q54919 C 2148531382 A 14953982 High positive Q36578 C 2229315598 A 14953983 High positive Q30 A 2277746226 A 14953984 None Q6581097 C 3273952711 A 14953985 High positive Q5 A 5668008721 A 14953986 None Q5296 C 12530369761 A 14953987 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 D 0 E 12 Moderate negative 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 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 14953958 High positive Q31165 C 2048330818 A 14953959 High positive Q40629 C 2049755644 A 14953960 High positive Q105584 C 2049926923 A 14953961 High positive Q4584301 D 2052339927 A 14953962 High positive Q565 C 2052996261 A 14953963 High positive Q1868372 E 2056080224 A 14953964 NA Q209330 C 2060928966 A 14953965 High positive Q14005 C 2063120071 A 14953966 High positive Q918 C 2063217449 A 14953967 High positive Q150248 C 2068796814 A 14953968 High positive Q866 C 2079749157 A 14953969 High positive Q477675 C 2080785713 A 14953970 High positive Q1967876 C 2084215818 A 14953971 High positive Q750403 C 2084693498 A 14953972 High positive Q355 C 2093900731 A 14953973 High positive Q623578 C 2097991400 A 14953974 High positive Q17299517 D 2105487660 A 14953975 High positive Q33999 C 2108672678 A 14953976 High positive Q2494649 C 2114531894 A 14953977 High positive Q2597810 C 2128920607 A 14953978 High positive Q193563 C 2130725560 A 14953979 High positive Q423048 C 2136131564 A 14953980 High positive Q37312 C 2142913121 A 14953981 High positive Q54919 C 2148531382 A 14953982 High positive Q36578 C 2229315598 A 14953983 High positive Q30 A 2277746226 A 14953984 None Q6581097 C 3273952711 A 14953985 High positive Q5 A 5668008721 A 14953986 None Q5296 C 12530369761 A 14953987 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 D 0 E 12 Moderate negative 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 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 14953958 High positive Q31165 C 2048330818 A 14953959 High positive Q40629 C 2049755644 A 14953960 High positive Q105584 C 2049926923 A 14953961 High positive Q4584301 D 2052339927 A 14953962 High positive Q565 C 2052996261 A 14953963 High positive Q1868372 E 2056080224 A 14953964 NA Q209330 C 2060928966 A 14953965 High positive Q14005 C 2063120071 A 14953966 High positive Q918 C 2063217449 A 14953967 High positive Q150248 C 2068796814 A 14953968 High positive Q866 C 2079749157 A 14953969 High positive Q477675 C 2080785713 A 14953970 High positive Q1967876 C 2084215818 A 14953971 High positive Q750403 C 2084693498 A 14953972 High positive Q355 C 2093900731 A 14953973 High positive Q623578 C 2097991400 A 14953974 High positive Q17299517 D 2105487660 A 14953975 High positive Q33999 C 2108672678 A 14953976 High positive Q2494649 C 2114531894 A 14953977 High positive Q2597810 C 2128920607 A 14953978 High positive Q193563 C 2130725560 A 14953979 High positive Q423048 C 2136131564 A 14953980 High positive Q37312 C 2142913121 A 14953981 High positive Q54919 C 2148531382 A 14953982 High positive Q36578 C 2229315598 A 14953983 High positive Q30 A 2277746226 A 14953984 None Q6581097 C 3273952711 A 14953985 High positive Q5 A 5668008721 A 14953986 None Q5296 C 12530369761 A 14953987 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 D 0 E 12 Moderate negative 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 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 14953958 High positive Q31165 C 2048330818 A 14953959 High positive Q40629 C 2049755644 A 14953960 High positive Q105584 C 2049926923 A 14953961 High positive Q4584301 D 2052339927 A 14953962 High positive Q565 C 2052996261 A 14953963 High positive Q1868372 E 2056080224 A 14953964 NA Q209330 C 2060928966 A 14953965 High positive Q14005 C 2063120071 A 14953966 High positive Q918 C 2063217449 A 14953967 High positive Q150248 C 2068796814 A 14953968 High positive Q866 C 2079749157 A 14953969 High positive Q477675 C 2080785713 A 14953970 High positive Q1967876 C 2084215818 A 14953971 High positive Q750403 C 2084693498 A 14953972 High positive Q355 C 2093900731 A 14953973 High positive Q623578 C 2097991400 A 14953974 High positive Q17299517 D 2105487660 A 14953975 High positive Q33999 C 2108672678 A 14953976 High positive Q2494649 C 2114531894 A 14953977 High positive Q2597810 C 2128920607 A 14953978 High positive Q193563 C 2130725560 A 14953979 High positive Q423048 C 2136131564 A 14953980 High positive Q37312 C 2142913121 A 14953981 High positive Q54919 C 2148531382 A 14953982 High positive Q36578 C 2229315598 A 14953983 High positive Q30 A 2277746226 A 14953984 None Q6581097 C 3273952711 A 14953985 High positive Q5 A 5668008721 A 14953986 None Q5296 C 12530369761 A 14953987 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 D 0 E 12 Moderate negative 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 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 14953958 High positive Q31165 C 2048330818 A 14953959 High positive Q40629 C 2049755644 A 14953960 High positive Q105584 C 2049926923 A 14953961 High positive Q4584301 D 2052339927 A 14953962 High positive Q565 C 2052996261 A 14953963 High positive Q1868372 E 2056080224 A 14953964 High positive Q209330 C 2060928966 A 14953965 High positive Q14005 C 2063120071 A 14953966 High positive Q918 C 2063217449 A 14953967 High positive Q150248 C 2068796814 A 14953968 High positive Q866 C 2079749157 A 14953969 High positive Q477675 C 2080785713 A 14953970 High positive Q1967876 C 2084215818 A 14953971 High positive Q750403 C 2084693498 A 14953972 High positive Q355 C 2093900731 A 14953973 High positive Q623578 C 2097991400 A 14953974 High positive Q17299517 D 2105487660 A 14953975 High positive Q33999 C 2108672678 A 14953976 High positive Q2494649 C 2114531894 A 14953977 High positive Q2597810 C 2128920607 A 14953978 High positive Q193563 C 2130725560 A 14953979 High positive Q423048 C 2136131564 A 14953980 High positive Q37312 C 2142913121 A 14953981 High positive Q54919 C 2148531382 A 14953982 High positive Q36578 C 2229315598 A 14953983 High positive Q30 A 2277746226 A 14953984 None Q6581097 C 3273952711 A 14953985 High positive Q5 A 5668008721 A 14953986 None Q5296 C 12530369761 A 14953987 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 81.7 11.7 6.6 D 0.0 76.6 12.7 10.6 0.1 C 51.6 21.8 25.5 1.2 0.0 B 68.3 29.8 2.0 0.0 0.0 A 10.6 85.1 4.3 0.0 0.0
In [41]:
## Number of dissonant views per assessment class and amount of dissonance
articles_by_pop[, list(dissonant_views=sum(page_views)), by=list(prediction, dissonance)];
prediction dissonance dissonant_views E None 3723114501 D Moderate negative 582719703 C High negative 401645481 B High negative 33619217 E Moderate positive 7192104852 C Moderate negative 1565511320 D None 1306507799 A High negative 471760 C None 49117301543 E High positive 118418979904 D Moderate positive 19735080646 B Moderate negative 963865251 C Moderate positive 135013992662 D High positive 61722551821 B None 2460723817 A Moderate negative 4141564440 C High positive 92624394582 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 64553402607 Moderate negative 7253660714 High negative 435736458 Moderate positive 161941178160 High positive 272765926307
In [43]:
articles_by_pop[,sum(as.numeric(page_views))];
506949904246
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 12.73368
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 1.430844
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 0.08595257
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 31.94422
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 53.8053
Content source: hall1467/wikidata_usage_tracking
Similar notebooks: