## Package version: 2.1.2
## Parallel computing: 2 of 2 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

R Markdown

#create corpus

## readtext object consisting of 28 documents and 1 docvar.
## # Description: df[,3] [28 × 3]
##   doc_id     text                docvar1
##   <chr>      <chr>               <chr>  
## 1 Bodo1.pdf  "\"          \"..." Bodo1  
## 2 Bodo10.pdf "\"         A\"..." Bodo10 
## 3 Bodo11.pdf "\"          \"..." Bodo11 
## 4 Bodo12.pdf "\"          \"..." Bodo12 
## 5 Bodo13.pdf "\" Bodo agre\"..." Bodo13 
## 6 Bodo14.pdf "\"  Fourteen\"..." Bodo14 
## # … with 22 more rows

#create corpus

## [1] 28
##   docvar1
## 1   Bodo1
## 2  Bodo10
## 3  Bodo11
## 4  Bodo12
## 5  Bodo13
## 6  Bodo14
## Corpus consisting of 28 documents, showing 28 documents:
## 
##        Text Types Tokens Sentences docvar1
##   Bodo1.pdf   230    758        31   Bodo1
##  Bodo10.pdf   372    775        36  Bodo10
##  Bodo11.pdf   251    462        14  Bodo11
##  Bodo12.pdf   349    806        27  Bodo12
##  Bodo13.pdf   186    351        10  Bodo13
##  Bodo14.pdf   306    601        30  Bodo14
##  Bodo15.pdf   230    417        12  Bodo15
##  Bodo16.pdf   368    848        28  Bodo16
##  Bodo17.pdf   538   1208        50  Bodo17
##  Bodo18.pdf   290    719        17  Bodo18
##  Bodo19.pdf   210    718        19  Bodo19
##   Bodo2.pdf   245    446        21   Bodo2
##  Bodo20.pdf   343    860        32  Bodo20
##  Bodo21.pdf   335    598        11  Bodo21
##  Bodo22.pdf   239    732        31  Bodo22
##  Bodo23.pdf   286    648        21  Bodo23
##  Bodo24.pdf   651   1567        58  Bodo24
##  Bodo25.pdf   304    678        21  Bodo25
##  Bodo26.pdf  1259   4556       164  Bodo26
##  Bodo27.pdf   355    718        29  Bodo27
##  Bodo28.pdf   394    909        27  Bodo28
##   Bodo3.pdf   248    456        15   Bodo3
##   Bodo4.pdf   535   1287        42   Bodo4
##   Bodo5.pdf   330    710        23   Bodo5
##   Bodo6.pdf   276    505        18   Bodo6
##   Bodo7.pdf   216    342        14   Bodo7
##   Bodo8.pdf   187    312        11   Bodo8
##   Bodo9.pdf   273    533        22   Bodo9

#create dfm

## Length  Class   Mode 
##  67648    dfm     S4

#Cleaning up using tokens

##            Length Class  Mode     
## Bodo1.pdf   390   -none- character
## Bodo10.pdf  412   -none- character
## Bodo11.pdf  246   -none- character
## Bodo12.pdf  407   -none- character
## Bodo13.pdf  203   -none- character
## Bodo14.pdf  315   -none- character
## Bodo15.pdf  214   -none- character
## Bodo16.pdf  474   -none- character
## Bodo17.pdf  616   -none- character
## Bodo18.pdf  408   -none- character
## Bodo19.pdf  348   -none- character
## Bodo2.pdf   240   -none- character
## Bodo20.pdf  441   -none- character
## Bodo21.pdf  337   -none- character
## Bodo22.pdf  407   -none- character
## Bodo23.pdf  355   -none- character
## Bodo24.pdf  814   -none- character
## Bodo25.pdf  352   -none- character
## Bodo26.pdf 2196   -none- character
## Bodo27.pdf  367   -none- character
## Bodo28.pdf  463   -none- character
## Bodo3.pdf   247   -none- character
## Bodo4.pdf   617   -none- character
## Bodo5.pdf   368   -none- character
## Bodo6.pdf   271   -none- character
## Bodo7.pdf   172   -none- character
## Bodo8.pdf   169   -none- character
## Bodo9.pdf   291   -none- character

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

docname from to pre keyword post pattern
Bodo1.pdf 13 13 juli monday uni right reserv length word right
Bodo10.pdf 16 16 ht media ltd right reserv length word right
Bodo10.pdf 392 392 due disput land right publish ht syndic right
Bodo11.pdf 14 14 sunday kashmir monitor right reserv length word right
Bodo12.pdf 19 19 express distribut contify.com right reserv length word right
Bodo13.pdf 20 20 solut privat limit right reserv length word right
Bodo14.pdf 19 19 associat newspap ltd right reserv section indianews right
Bodo15.pdf 18 18 septemb saturday uni right reserv length word right
Bodo15.pdf 128 128 migrant assam champion right nativ local economi right
Bodo16.pdf 18 18 vision distribut contify.com right reserv length word right
Bodo17.pdf 21 21 august wednesday menafn.com right reserv length word right
Bodo17.pdf 604 604 hong kong compani right reserv pleas contact right
Bodo18.pdf 23 23 gmt india today right reserv length word right
Bodo19.pdf 13 13 june tuesday uni right reserv length word right
Bodo2.pdf 17 17 ltd distribut contify.com right reserv length word right
Bodo20.pdf 15 15 januari monday newswing right reserv length word right
Bodo21.pdf 19 19 coleman co ltd right reserv section times right
Bodo22.pdf 12 12 october monday uni right reserv length word right
Bodo23.pdf 17 17 ht media ltd right reserv length word right
Bodo23.pdf 201 201 fund centr land right bodo btad area right
Bodo24.pdf 20 20 media inc syndigate.info right reserv length word right
Bodo24.pdf 116 116 greater recognit bodo right ident claim sever right
Bodo24.pdf 166 166 polit autonomi econom right date back post-coloni right
Bodo24.pdf 584 584 safeguard non-bodo properti right expens indigen communiti right
Bodo24.pdf 628 628 group beyond defend right properti bodo attack right
Bodo24.pdf 750 750 potenti impact might right push independ bodo right
Bodo25.pdf 19 19 solut privat limit right reserv length word right
Bodo26.pdf 13 13 week distribut contify.com right reserv length word right
Bodo26.pdf 756 756 imagin attempt prove right autochthon land becam right
Bodo26.pdf 1229 1229 establish ident polit right carri histor retribut right
Bodo26.pdf 1690 1690 issu exclus land right control land issu right
Bodo26.pdf 1877 1877 customari law communiti right taken cognis roy right
Bodo26.pdf 1884 1884 40-44 format btc right recognis btc unlik right
Bodo26.pdf 1929 1929 schedul preserv land right section also safeguard right
Bodo26.pdf 1934 1934 also safeguard settlement right transfer inherit properti right
Bodo26.pdf 1955 1955 issu especi land right defin right son right
Bodo26.pdf 1957 1957 land right defin right son soil state right
Bodo26.pdf 1975 1975 though provis ensur right non-bodo bodo govern right
Bodo26.pdf 1987 1987 ethnic violenc bodoland right dichotomi bodo non-bodo right
Bodo27.pdf 16 16 ht media ltd right reserv length word right
Bodo28.pdf 17 17 express distribut contify.com right reserv length word right
Bodo3.pdf 17 17 associat newspap ltd right reserv section indianews right
Bodo4.pdf 15 15 tribun p ltd right reserv length word right
Bodo5.pdf 18 18 coleman co ltd right reserv section india right
Bodo5.pdf 362 362 input agenc reprint right timescontent.com load-dat decemb right
Bodo6.pdf 14 14 cmyk printech ltd right reserv length word right
Bodo7.pdf 17 17 coleman co ltd right reserv section times right
Bodo8.pdf 28 28 ltd distribut contify.com right reserv length word right
Bodo9.pdf 14 14 thursday india bloom right reserv length word right
docname from to pre keyword post pattern
Bodo10.pdf 183 183 carri arm rebellion independ bodoland ndfb origin independ
Bodo14.pdf 224 224 attack group fight independ homeland region bodo independ
Bodo14.pdf 296 296 greater region autonomi independ homeland indigen group independ
Bodo17.pdf 57 57 oppos talk goal independ bodoland indigen bodo independ
Bodo17.pdf 563 563 futil sudha ramachandran independ journalist research base independ
Bodo24.pdf 308 308 expansion occup creation independ socialist state group independ
Bodo24.pdf 752 752 might right push independ bodo territori might independ
Bodo4.pdf 232 232 faction last elect independ poll vote share independ
Bodo4.pdf 476 476 former ulfa leader independ mp naba sarania-l independ
docname from to pre keyword post pattern
Bodo2.pdf 5 5 assam bodo milit free press journal india free
docname from to pre keyword post pattern
docname from to pre keyword post pattern
Bodo11.pdf 77 77 crpc civil author decis initi fresh action decis
Bodo19.pdf 45 45 ministri taken polici decis elimin milit region decis
Bodo19.pdf 66 66 radic record admit decis strateg made low decis
Bodo19.pdf 195 195 ministri taken polici decis elimin milit region decis
Bodo19.pdf 216 216 radic record admit decis strateg made low decis
Bodo24.pdf 40 40 point new delhi decis privileg militari forc decis
Bodo26.pdf 1465 1465 singl largest parti decis govern form post-elector decis
Bodo4.pdf 281 281 apathi two controversi decis pertain januari third decis
Bodo4.pdf 300 300 indigen communiti one decis sign pact three decis
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
Bodo17.pdf 207 207 tribal brought assam coloni time work tea coloni
Bodo24.pdf 510 510 assam new delhi coloni era british brought coloni
Bodo26.pdf 439 439 histor marginalis communiti coloni post-independ period attempt coloni
Bodo26.pdf 447 447 umbrella assames nation coloni period bodo defin coloni
Bodo26.pdf 501 501 prior absu movement coloni period bodo particip coloni
Bodo26.pdf 870 870 british settl area coloni period sever dimens coloni
Bodo26.pdf 936 936 resist non-bodo sinc coloni period assames nation coloni
Bodo26.pdf 1708 1708 decad 20th centuri coloni intervent assam north- coloni
Bodo26.pdf 1721 1721 pattern demograph structur coloni saw systemat process coloni
Bodo26.pdf 1754 1754 land practis even coloni period attempt keep coloni
Bodo26.pdf 1797 1797 migrat systemat polici coloni state encourag migrat coloni
Bodo26.pdf 1818 1818 assembl land issu coloni govern introduc line coloni
Bodo26.pdf 2146 2146 tribal identiti polit coloni assam plain tribe coloni
docname from to pre keyword post pattern
Bodo26.pdf 153 153 mosqu claim area occupi construct mosqu part occupi
docname from to pre keyword post pattern
docname from to pre keyword post pattern
Bodo10.pdf 157 157 centr ndfb-s unite liber front asom-independ led liber
Bodo12.pdf 233 233 platform unite nation liber front western south liber
Bodo15.pdf 116 116 outlaw ulfa unite liber front assam essenti liber
Bodo18.pdf 303 303 milit group bodo liber tiger blt lead liber
Bodo23.pdf 317 317 deal sign bodo liber tiger led format liber
Bodo24.pdf 260 260 like ndfb bodo liber tiger blt form liber
Bodo24.pdf 302 302 ndfb origin focus liber bodoland indian expansion liber
Bodo24.pdf 617 617 includ adivasi nation liber armi aanla birsa liber
Bodo25.pdf 280 280 milit group bodo liber tiger lead format liber
Bodo26.pdf 142 142 signboard cadr ex-bodo liber tiger blt piec liber
Bodo26.pdf 1092 1092 cobra milit bengal liber tiger began retali liber
Bodo4.pdf 124 124 unite peopl parti liber uppl aiudf gana liber
Bodo4.pdf 181 181 milit outfit bodo liber tiger blt concern liber
Bodo6.pdf 142 142 ulfa ndfb kamtapur liber organis rebel group liber
Bodo9.pdf 235 235 i.k songbijit vow liber bodoland bodo tribesmen liber
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
Bodo20.pdf 311 311 central state govern equal particip crore said equal
Bodo25.pdf 201 201 next three year equal contribut rs crore equal
docname from to pre keyword post pattern
docname from to pre keyword post pattern
docname from to pre keyword post pattern
Bodo11.pdf 106 106 bow arrow follow massacr communiti member bodo massacr
Bodo11.pdf 176 176 offic assam follow massacr adivasi bodo milit massacr
Bodo12.pdf 376 376 said behind decemb massacr adivasi assam songbijit massacr
Bodo15.pdf 151 151 christian decemb involv massacr tribal past kill massacr
Bodo17.pdf 263 263 kill howev unlik massacr past target outsid massacr
Bodo21.pdf 48 48 friday bodo milit massacr bengali-speak muslim belief massacr
Bodo26.pdf 100 100 memori imag nelli massacr thousand alleg illeg massacr
Bodo26.pdf 776 776 muslim peasant brutal massacr barpeta lower assam massacr
Bodo26.pdf 1173 1173 talk cadr also massacr koch rajbongshi ndfb-p massacr
Bodo5.pdf 80 80 adivasi backlash tuesday massacr continu second day massacr
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
Bodo22.pdf 151 151 daimari warn bigger war achiev faction goal war
Bodo22.pdf 333 333 daimari warn bigger war achiev faction goal war
Bodo24.pdf 700 700 talk negoti mean war parti continu lack war
docname from to pre keyword post pattern
Bodo26.pdf 844 844 tacit support ethnic cleans sever clash soon cleans
Bodo26.pdf 1043 1043 bodo endeavour ethnic cleans non-bodo panic-stricken non-bodo cleans
Bodo27.pdf 133 133 muslim target ethnic cleans bodo-inhabit area along cleans
docname from to pre keyword post pattern 
## Tokens consisting of 28 documents and 1 docvar.
## Bodo1.pdf :
##  [1] "bodo"      "milit"     "kill"      "armi"      "personnel" "uni"      
##  [7] "unite"     "new"       "india"     "juli"      "monday"    "uni"      
## [ ... and 378 more ]
## 
## Bodo10.pdf :
##  [1] "assam"     "suspect"   "bodo"      "milit"     "fire"      "kokrajhar"
##  [7] "market"    "kill"      "hindustan" "time"      "august"    "saturday" 
## [ ... and 400 more ]
## 
## Bodo11.pdf :
##  [1] "armi"    "begin"   "all-out" "offens"  "bodo"    "milit"   "kashmir"
##  [8] "monitor" "india"   "januari" "sunday"  "kashmir"
## [ ... and 234 more ]
## 
## Bodo12.pdf :
##  [1] "bodo"    "milit"   "outfit"  "ndfb"    "s"       "shun"    "violenc"
##  [8] "join"    "peac"    "talk"    "indian"  "express"
## [ ... and 395 more ]
## 
## Bodo13.pdf :
##  [1] "bodo"      "agreement" "amit"      "shah"      "sign"      "accord"   
##  [7] "dread"     "bodo"      "milit"     "group"     "ndfb"      "publish"  
## [ ... and 191 more ]
## 
## Bodo14.pdf :
##  [1] "fourteen"   "kill"       "suspect"    "bodo"       "milit"     
##  [6] "open"       "fire"       "crowd"      "assam"      "marketplac"
## [11] "mailonlin"  "august"    
## [ ... and 303 more ]
## 
## [ reached max_ndoc ... 22 more documents ]
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

Bodo.tokens2

#create dfm from first tokenized steps

#word cloud

#co-occurance

##       btc  non-bodo    accord      land territori    tribal    muslim    demand 
##     44225     32524     26122     25595     23229     21638     19127     18602 
## communiti  conflict 
##     17974     17712
##  [1] "btc"       "non-bodo"  "accord"    "land"      "territori" "tribal"   
##  [7] "muslim"    "demand"    "communiti" "conflict"  "movement"  "immigr"   
## [13] "period"    "govern"    "schedul"   "council"   "absu"      "state"    
## [19] "clash"     "attack"    "coloni"    "polit"     "said"      "bodoland" 
## [25] "issu"