I have several text files which I import into a corpus. Each text has several parts that are supposedly written in different days and marked with #. A week is marked with $. On each text how I can count how many words in a day and how many in a week? the text T1 has days that are marked in the end with # and I need to count the words each day has. The weeks are delimited by $ and I need to know also the number of words in a week Also I have the text T2 and T3 ...Tn the question is how I do this in R with quanteda
<T1>
(25.02.2009) This chapter thoroughly describes the idea of analyzing text “as data” with a social science focus. It traces a brief history of this approach and distinguishes it from alternative approaches to text. It identifies the key research designs and methods for various ways that scholars in political science and international relations have used text, with references to fields such as natural language processing and computational linguistics from which some of the key methods are influenced or inherited. It surveys the varieties of ways that textual data is used and analyzed, covering key methods and pointing to applications of each. It also identifies the key stages of a research design using text as data, and critically discusses the practical and epistemological challenges at each stage.
# (26.02.2009) Probabilistic methods for classifying text form a rich tradition in machine learning and natural language processing. For many important problems, however, class prediction is uninteresting because the class is known, and instead the focus shifts to estimating latent quantities related to the text, such as affect or ideology. We focus on one such problem of interest, estimating the ideological positions of 55 Irish legislators in the 1991 Dail confidence vote. To solve the Dail scaling problem and others like it, we develop a text modeling framework that allows actors to take latent positions on a “gray” spectrum between “black” and “white” polar opposites. We are able to validate results from this model by measuring the influences exhibited by individual words, and we are able to quantify the uncertainty in the scaling estimates by using a sentence-level block bootstrap. Applying our method to the Dail debate, we are able to scale the legislators between extreme pro-government and pro-opposition in a way that reveals nuances in their speeches not captured by their votes or party affiliations.
# (28.02.2009) Borrowing from automated “text as data” approaches, we show how statistical scaling models can be applied to hand-coded content analysis to improve estimates of political parties’ left-right policy positions. We apply a Bayesian item-response theory (IRT) model to category counts from coded party manifestos, treating the categories as “items” and policy positions as a latent variable. This approach also produces direct estimates of how each policy category relates to left-right ideology, without having to decide these relationships in advance based on out of sample fitting, political theory, assertion, or guesswork. This approach not only prevents the misspecification endemic to a fixed-index approach, but also works well even with items that are not specifically designed to measure ideological positioning.
# (02.03.2009) This chapter thoroughly describes the idea of analyzing text “as data” with a social science focus. It traces a brief history of this approach and distinguishes it from alternative approaches to text. It identifies the key research designs and methods for various ways that scholars in political science and international relations have used text, with references to fields such as natural language processing and computational linguistics from which some of the key methods are influenced or inherited. It surveys the varieties of ways that textual data is used and analyzed, covering key methods and pointing to applications of each. It also identifies the key stages of a research design using text as data, and critically discusses the practical and epistemological challenges at each stage. .
# (03.03.2009) Probabilistic methods for classifying text form a rich tradition in machine learning and natural language processing. For many important problems, however, class prediction is uninteresting because the class is known, and instead the focus shifts to estimating latent quantities related to the text, such as affect or ideology. We focus on one such problem of interest, estimating the ideological positions of 55 Irish legislators in the 1991 Dail confidence vote. To solve the Dail scaling problem and others like it, we develop a text modeling framework that allows actors to take latent positions on a “gray” spectrum between “black” and “white” polar opposites. We are able to validate results from this model by measuring the influences exhibited by individual words, and we are able to quantify the uncertainty in the scaling estimates by using a sentence-level block bootstrap. Applying our method to the Dail debate, we are able to scale the legislators between extreme pro-government and pro-opposition in a way that reveals nuances in their speeches not captured by their votes or party affiliations.
#
($)
(04.03.2009) Borrowing from automated “text as data” approaches, we show how statistical scaling models can be applied to hand-coded content analysis to improve estimates of political parties’ left-right policy positions. We apply a Bayesian item-response theory (IRT) model to category counts from coded party manifestos, treating the categories as “items” and policy positions as a latent variable. This approach also produces direct estimates of how each policy category relates to left-right ideology, without having to decide these relationships in advance based on out of sample fitting, political theory, assertion, or guesswork. This approach not only prevents the misspecification endemic to a fixed-index approach, but also works well even with items that are not specifically designed to measure ideological positioning.
# (05.03.2009) Probabilistic methods for classifying text form a rich tradition in machine learning and natural language processing. For many important problems, however, class prediction is uninteresting because the class is known, and instead the focus shifts to estimating latent quantities related to the text, such as affect or ideology. We focus on one such problem of interest, estimating the ideological positions of 55 Irish legislators in the 1991 Dail confidence vote. To solve the Dail scaling problem and others like it, we develop a text modeling framework that allows actors to take latent positions on a “gray” spectrum between “black” and “white” polar opposites. We are able to validate results from this model by measuring the influences exhibited by individual words, and we are able to quantify the uncertainty in the scaling estimates by using a sentence-level block bootstrap. Applying our method to the Dail debate, we are able to scale the legislators between extreme pro-government and pro-opposition in a way that reveals nuances in their speeches not captured by their votes or party affiliations.
# (06.03.2009) This chapter thoroughly describes the idea of analyzing text “as data” with a social science focus. It traces a brief history of this approach and distinguishes it from alternative approaches to text. It identifies the key research designs and methods for various ways that scholars in political science and international relations have used text, with references to fields such as natural language processing and computational linguistics from which some of the key methods are influenced or inherited. It surveys the varieties of ways that textual data is used and analyzed, covering key methods and pointing to applications of each. It also identifies the key stages of a research design using text as data, and critically discusses the practical and epistemological challenges at each stage.
# (07.03.2009) This chapter thoroughly describes the idea of analyzing text “as data” with a social science focus. It traces a brief history of this approach and distinguishes it from alternative approaches to text. It identifies the key research designs and methods for various ways that scholars in political science and international relations have used text, with references to fields such as natural language processing and computational linguistics from which some of the key methods are influenced or inherited. It surveys the varieties of ways that textual data is used and analyzed, covering key methods and pointing to applications of each. It also identifies the key stages of a research design using text as data, and critically discusses the practical and epistemological challenges at each stage.
# (08.03.2009) Probabilistic methods for classifying text form a rich tradition in machine learning and natural language processing. For many important problems, however, class prediction is uninteresting because the class is known, and instead the focus shifts to estimating latent quantities related to the text, such as affect or ideology. We focus on one such problem of interest, estimating the ideological positions of 55 Irish legislators in the 1991 Dail confidence vote. To solve the Dail scaling problem and others like it, we develop a text modeling framework that allows actors to take latent positions on a “gray” spectrum between “black” and “white” polar opposites. We are able to validate results from this model by measuring the influences exhibited by individual words, and we are able to quantify the uncertainty in the scaling estimates by using a sentence-level block bootstrap. Applying our method to the Dail debate, we are able to scale the legislators between extreme pro-government and pro-opposition in a way that reveals nuances in their speeches not captured by their votes or party affiliations.
# (09.03.2009) Borrowing from automated “text as data” approaches, we show how statistical scaling models can be applied to hand-coded content analysis to improve estimates of political parties’ left-right policy positions. We apply a Bayesian item-response theory (IRT) model to category counts from coded party manifestos, treating the categories as “items” and policy positions as a latent variable. This approach also produces direct estimates of how each policy category relates to left-right ideology, without having to decide these relationships in advance based on out of sample fitting, political theory, assertion, or guesswork. This approach not only prevents the misspecification endemic to a fixed-index approach, but also works well even with items that are not specifically designed to measure ideological positioning.
# (10.03.2009) This chapter thoroughly describes the idea of analyzing text “as data” with a social science focus. It traces a brief history of this approach and distinguishes it from alternative approaches to text. It identifies the key research designs and methods for various ways that scholars in political science and international relations have used text, with references to fields such as natural language processing and computational linguistics from which some of the key methods are influenced or inherited. It surveys the varieties of ways that textual data is used and analyzed, covering key methods and pointing to applications of each. It also identifies the key stages of a research design using text as data, and critically discusses the practical and epistemological challenges at each stage.
#
($)
Those texts look very familiar!
If I assign what you have above to txt, then you can wrap it in a quanteda corpus and then use corpus_segment() to split it on the tags.
library("quanteda")
## Package version: 1.5.0
corp <- corpus(txt) %>%
corpus_segment(pattern = "($)", valuetype = "fixed", pattern_position = "after") %>%
corpus_segment(pattern = "\\(\\d{2}\\.\\d{2}\\.\\d{4}\\)", valuetype = "regex", pattern_position = "before")
The first segmentation splits along the "weeks", but since there is no tag there, we just segment again to get the date. This produces:
sapply(head(texts(corp)), substring, 1, 100)
## text1.1.1
## "This chapter thoroughly describes the idea of analyzing text \"as data\" with a social science focus. "
## text1.1.2
## "Probabilistic methods for classifying text form a rich tradition in machine learning and natural lan"
## text1.1.3
## "Borrowing from automated \"text as data\" approaches, we show how statistical scaling models can be ap"
## text1.1.4
## "This chapter thoroughly describes the idea of analyzing text \"as data\" with a social science focus. "
## text1.1.5
## "Probabilistic methods for classifying text form a rich tradition in machine learning and natural lan"
## text1.2.1
## "Borrowing from automated \"text as data\" approaches, we show how statistical scaling models can be ap"
Better to tidy up the extracted tag and make it into an actual date, which you could later use to split into weeks or whatever other date ranges you want.
# tidy up docvars
names(docvars(corp))[1] <- "date"
docvars(corp, "date") <-
stringi::stri_replace_all_fixed(docvars(corp, "date"), c("(", ")"), c("", ""), vectorize_all = FALSE) %>%
lubridate::dmy()
summary(corp)
## Corpus consisting of 12 documents:
##
## Text Types Tokens Sentences date
## text1.1.1 83 135 6 2009-02-25
## text1.1.2 119 195 7 2009-02-26
## text1.1.3 96 137 5 2009-02-28
## text1.1.4 83 136 6 2009-03-02
## text1.1.5 119 195 7 2009-03-03
## text1.2.1 96 137 5 2009-03-04
## text1.2.2 119 195 7 2009-03-05
## text1.2.3 83 135 6 2009-03-06
## text1.2.4 83 135 6 2009-03-07
## text1.2.5 119 195 7 2009-03-08
## text1.2.6 96 137 5 2009-03-09
## text1.2.7 83 135 6 2009-03-10
##
## Source: /private/var/folders/1v/ps2x_tvd0yg0lypdlshg_vwc0000gp/T/RtmpDG9tad/reprexd97c6e16bef8/* on x86_64 by kbenoit
## Created: Sun Jul 28 11:29:45 2019
## Notes: corpus_segment.corpus(., pattern = "\\(\\d{2}\\.\\d{2}\\.\\d{4}\\)", valuetype = "regex", pattern_position = "before")