Stats on ACL 2018 accepted papers

acl2018stats.sh

#!/bin/bash

# Get the data
wget -nv http://acl2018.org/conference/accepted-papers/index.html
# Keep the list of papers only
sed -i '/paper-title/!d' index.html
# Extract author lists to csv
sed 's:.*<span class="paper-authors">\([^<]*\)</span>.*:\1:;s:(, | and ):,:g' index.html | tr '[:upper:]' '[:lower:]' > authors.txt
# Author frequencies
sed 's/,/\n/g' authors.txt | sort | uniq -c | sort -n | cut -d" " -f7 | uniq -c
# First author frequencies
cut -d"," -f1 authors.txt | sort | uniq -c | sort -n | cut -d" " -f7 | uniq -c
# Extract titles
sed 's:.*<span class="paper-title">\([^<]*\)</span>.*:\1:' index.html > titles.txt
# Word frequencies (stopwords are from NLTK)
cat titles.txt | tr '[:upper:]' '[:lower:]' | sed 's/[^a-z0-9 ]//g;s/ /\n/g' | sort | uniq -c | sed -r '/ i$| me$| my$| myself$| we$| our$| ours$| ourselves$| you$| your$| yours$| yourself$| yourselves$| he$| him$| his$| himself$| she$| her$| hers$| heself$| it$| its$| itself$| they$| them$| their$| theirs$| themselves$| what$| which$| who$| whom$| this$| that$| these$| those$| am$| is$| are$| was$| were$| be$| been$| being$| have$| has$| had$| having$| do$| does$| did$| doing$| a$| an$| the$| and$| but$| if$| or$| because$| as$| until$| while$| of$| at$| by$| for$| with$| about$| against$| between$| into$| through$| during$| before$| after$| above$| below$| to$| from$| up$| down$| in$| out$| on$| off$| over$| under$| again$| further$| then$| once$| here$| there$| when$| where$| why$| how$| all$| any$| both$| each$| few$| more$| most$| other$| some$| such$| no$| nor$| not$| only$| own$| same$| so$| than$| too$| very$| s$| t$| can$| will$| just$| don$| should$| now$/d' | sort -n | tail -n15
# I used Excel for the plots