## Package version: 2.1.2
## Parallel computing: 2 of 8 threads used.
## See https://quanteda.io for tutorials and examples.
## 
## Attaching package: 'quanteda'
## The following object is masked from 'package:utils':
## 
##     View
## Loading required package: usethis
## 
## Attaching package: 'quanteda.textmodels'
## The following object is masked from 'package:quanteda':
## 
##     data_dfm_lbgexample
## 
## Attaching package: 'seededlda'
## The following object is masked from 'package:stats':
## 
##     terms
## 
## Attaching package: 'rsconnect'
## The following object is masked from 'package:devtools':
## 
##     lint
## 
## Attaching package: 'packrat'
## The following objects are masked from 'package:devtools':
## 
##     install, install_local

#create corpus

## readtext object consisting of 5 documents and 1 docvar.
## # Description: df[,3] [5 x 3]
##   doc_id       text                docvar1 
##   <chr>        <chr>               <chr>   
## 1 Karenni1.pdf "\"   An Unju\"..." Karenni1
## 2 Karenni2.pdf "\"          \"..." Karenni2
## 3 Karenni3.pdf "\"          \"..." Karenni3
## 4 Karenni4.pdf "\"       Kar\"..." Karenni4
## 5 Karenni5.pdf "\"  Thailand\"..." Karenni5

#create corpus

## [1] 5
##    docvar1
## 1 Karenni1
## 2 Karenni2
## 3 Karenni3
## 4 Karenni4
## 5 Karenni5
## Corpus consisting of 5 documents, showing 5 documents:
## 
##          Text Types Tokens Sentences  docvar1
##  Karenni1.pdf   427    941        27 Karenni1
##  Karenni2.pdf  1134   3258       109 Karenni2
##  Karenni3.pdf   394    895        42 Karenni3
##  Karenni4.pdf   239    440        14 Karenni4
##  Karenni5.pdf   489   1230        46 Karenni5

#create dfm

## Length  Class   Mode 
##   6390    dfm     S4

#Cleaning up using tokens

##              Length Class  Mode     
## Karenni1.pdf  460   -none- character
## Karenni2.pdf 1618   -none- character
## Karenni3.pdf  454   -none- character
## Karenni4.pdf  238   -none- character
## Karenni5.pdf  598   -none- character

#kwic doesn’t work with dfm, so you have to use tokens

docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
Karenni1.pdf 287 287 judg wisdom abil decision-mak believ whole countri decision*
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
Karenni2.pdf 343 343 sponsor peopl british coloni shan state risk coloni*
docname from to pre keyword post pattern
Karenni2.pdf 580 580 sinc karenni state occupi forc karenni episod occupi*
Karenni2.pdf 614 614 success burmes govern occupi karenni state exploit occupi*
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
Karenni2.pdf 629 629 make motherland free oppress govern burma popul oppress*
Karenni2.pdf 784 784 due year militari oppress karenni state locat oppress*
docname from to pre keyword post pattern
Karenni1.pdf 419 419 recent stress myanmar repress law repeal amend repress*
##                                                                          
##    [Karenni1.pdf, 841:842]     deputy Asia director |   Human Rights    |
##  [Karenni2.pdf, 1046:1047]                     rate | ethnic cleansing  |
##  [Karenni2.pdf, 1597:1598]  escape military attacks |   human rights    |
##  [Karenni2.pdf, 1875:1876]      represented members | political parties |
##  [Karenni2.pdf, 2193:2194]                    worst | ethnic cleansing  |
##  [Karenni2.pdf, 2702:2703]             economic pie | Ethnic cleansing  |
##  [Karenni2.pdf, 2961:2962]    people love democracy |   human rights    |
##                             
##  Watch recently stressed    
##   doubtful whether          
##  abuses perpetrated Tatmadaw
##   nationalities             
##   Tatmadaw led              
##   successful Karenni        
##   KNPP refuse
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern

multiword

#create dfm from first tokenized steps

#word cloud

#co-occurance

##   burma displac   peopl  leader    camp    cent    forc     per  refuge    knpp 
##   17300   14402   13082   10676   10670    9996    9960    9932    9875    9839
##  [1] "burma"     "displac"   "peopl"     "leader"    "camp"      "cent"     
##  [7] "forc"      "per"       "refuge"    "knpp"      "govern"    "burmes"   
## [13] "arm"       "thailand"  "want"      "peac"      "popul"     "democraci"
## [19] "new"       "educ"      "independ"  "junta"     "number"    "home"     
## [25] "mani"