Get cooccurrence statistics.

Get cooccurrence statistics.

cooccurrences(.Object, ...)

# S4 method for corpus
cooccurrences(
  .Object,
  query,
  cqp = is.cqp,
  p_attribute = getOption("polmineR.p_attribute"),
  boundary = NULL,
  left = getOption("polmineR.left"),
  right = getOption("polmineR.right"),
  stoplist = NULL,
  positivelist = NULL,
  regex = FALSE,
  keep = NULL,
  cpos = NULL,
  method = "ll",
  mc = getOption("polmineR.mc"),
  verbose = FALSE,
  progress = FALSE,
  ...
)

# S4 method for character
cooccurrences(
  .Object,
  query,
  cqp = is.cqp,
  p_attribute = getOption("polmineR.p_attribute"),
  boundary = NULL,
  left = getOption("polmineR.left"),
  right = getOption("polmineR.right"),
  stoplist = NULL,
  positivelist = NULL,
  regex = FALSE,
  keep = NULL,
  cpos = NULL,
  method = "ll",
  mc = getOption("polmineR.mc"),
  verbose = FALSE,
  progress = FALSE,
  ...
)

# S4 method for slice
cooccurrences(
  .Object,
  query,
  cqp = is.cqp,
  left = getOption("polmineR.left"),
  right = getOption("polmineR.right"),
  p_attribute = getOption("polmineR.p_attribute"),
  boundary = NULL,
  stoplist = NULL,
  positivelist = NULL,
  keep = NULL,
  method = "ll",
  mc = FALSE,
  progress = TRUE,
  verbose = FALSE,
  ...
)

# S4 method for partition
cooccurrences(
  .Object,
  query,
  cqp = is.cqp,
  left = getOption("polmineR.left"),
  right = getOption("polmineR.right"),
  p_attribute = getOption("polmineR.p_attribute"),
  boundary = NULL,
  stoplist = NULL,
  positivelist = NULL,
  keep = NULL,
  method = "ll",
  mc = FALSE,
  progress = TRUE,
  verbose = FALSE,
  ...
)

# S4 method for subcorpus
cooccurrences(
  .Object,
  query,
  cqp = is.cqp,
  left = getOption("polmineR.left"),
  right = getOption("polmineR.right"),
  p_attribute = getOption("polmineR.p_attribute"),
  boundary = NULL,
  stoplist = NULL,
  positivelist = NULL,
  keep = NULL,
  method = "ll",
  mc = FALSE,
  progress = TRUE,
  verbose = FALSE,
  ...
)

# S4 method for context
cooccurrences(.Object, method = "ll", verbose = FALSE)

# S4 method for partition_bundle
cooccurrences(.Object, query, mc = getOption("polmineR.mc"), ...)

# S4 method for Cooccurrences
cooccurrences(.Object, query)

# S4 method for remote_corpus
cooccurrences(.Object, ...)

# S4 method for remote_subcorpus
cooccurrences(.Object, ...)

Arguments

.Object	A partition object, or a character vector with a CWB corpus.
...	Further parameters that will be passed into bigmatrix (applies only of big = TRUE).
query	A query, either a character vector to match a token, or a CQP query.
cqp	Defaults to is.cqp-function, or provide TRUE/FALSE; relevant only if query is not NULL.
p_attribute	The p-attribute of the tokens/the query.
boundary	If provided, it will be checked that the corpus positions of windows do not extend beyond the left and right boundaries of the region defined by the s-attribute where the match occurs.
left	Number of tokens to the left of the query match.
right	Number of tokens to the right of the query match.
stoplist	Exclude a query hit from analysis if stopword(s) is/are in context (relevant only if query is not NULL).
positivelist	Character vector or numeric vector: include a query hit only if token in positivelist is present. If positivelist is a character vector, it is assumed to provide regex expressions (incredibly long if the list is long) (relevant only if query is nut NULL)
regex	A logical value, whether stoplist/positivelist are interpreted as regular expressions.
keep	list with tokens to keep
cpos	integer vector with corpus positions, defaults to NULL - then the corpus positions for the whole corpus will be used
method	The statistical test(s) to use (defaults to "ll").
mc	whether to use multicore
verbose	A logical value, whether to be verbose.
progress	A logical value, whether to output progress bar.

Value

a cooccurrences-class object

References

Baker, Paul (2006): Using Corpora in Discourse Analysis. London: continuum, p. 95-120 (ch. 5).

Manning, Christopher D.; Schuetze, Hinrich (1999): Foundations of Statistical Natural Language Processing. MIT Press: Cambridge, Mass., pp. 151-189 (ch. 5).

See also

See the documentation for the ll-method for an explanation of the computation of the log-likelihood statistic.

Author

Andreas Blaette

Examples

use("polmineR")
#> ... activating corpus: GERMAPARLMINI (version: 0.0.1 | build date: 2019-02-23)
#> ... activating corpus: REUTERS
merkel <- partition("GERMAPARLMINI", interjection = "speech", speaker = ".*Merkel", regex = TRUE)
#> ... get encoding: latin1
#> ... get cpos and strucs
merkel <- enrich(merkel, p_attribute = "word")
#> ... getting counts for p-attribute(s): word
cooc <- cooccurrences(merkel, query = "Deutschland")

# use subset-method to filter results
a <- cooccurrences("REUTERS", query = "oil")
b <- subset(a, !is.na(ll))
c <- subset(b, !word %in% tm::stopwords("en"))
d <- subset(c, count_coi >= 5)
e <- subset(c, ll >= 10.83)
format(e)
#>        word count_coi count_ref exp_coi exp_ref    ll rank_ll
#> 1:   prices        27        20    9.23   37.77 33.05       1
#> 2:    crude        13         7    3.93   16.07 19.62       2
#> 3: industry         8         2    1.96    8.04 16.97       3
#> 4:   recent         5         1    1.18    4.82 11.33       4

# using pipe operator may be convenient
if (require(magrittr)){
cooccurrences("REUTERS", query = "oil") %>%
  subset(!is.na(ll)) %>%
  subset(!word %in% tm::stopwords("en")) %>%
  subset(count_coi >= 5) %>%
  subset(ll >= 10.83) %>%
  format()
}
#> Loading required package: magrittr
#>        word count_coi count_ref exp_coi exp_ref    ll rank_ll
#> 1:   prices        27        20    9.23   37.77 33.05       1
#> 2:    crude        13         7    3.93   16.07 19.62       2
#> 3: industry         8         2    1.96    8.04 16.97       3
#> 4:   recent         5         1    1.18    4.82 11.33       4
pb <- partition_bundle("GERMAPARLMINI", s_attribute = "speaker")
pb_min <- pb[[ count(pb, query = "Deutschland")[Deutschland >= 25][["partition"]] ]]
y <- cooccurrences(pb_min, query = "Deutschland")
if (interactive()) y[[1]]
if (interactive()) y[[2]]

y2 <- corpus("GERMAPARLMINI") %>%
  subset(speaker %in% c("Hubertus Heil", "Angela Dorothea Merkel")) %>%
  split(s_attribute = "speaker") %>%
  cooccurrences(query = "Deutschland")