library(tidyverse)
library(rvest)
#library(textreadr)
library(janitor)
library(knitr)

“Statistical methods for assessing agreement between two methods of clinical measurement. (Lancet 327, 307–310 (1986)” by Bland, J. M. & Altman, D. G. is one of the most cited papers of all time. This analysis tracks the citation history by since the paper’s publication in the Lancet in 1986.

The search for Citations of Bland-Altman 1986 paper is from the following URL.

“http://scholar.google.com/scholar?hl=en&as_sdt=2005&sciodt=0%2C5&cites=7296362022254018043&scipsc=&as_ylo=2020&as_yhi=2020”

Using textreadr

N.B. This package is no longer on CRAN

Citations_Data <- data.frame()
YEAR_RANGE <- 1986:2023

for(i in 1:length(YEAR_RANGE)){
  
    YEAR <- YEAR_RANGE[i]
    FILE <- paste0("http://scholar.google.com/scholar?hl=en&as_sdt=2005&sciodt=0%2C5&cites=7296362022254018043&scipsc=&as_ylo=",YEAR,"&as_yhi=",YEAR)

  
    LineList <- textreadr::read_html(FILE)
    LineList <- grep("About",LineList,value=T)
    LineList <- grep("results",LineList,value=T)
    LineList <- gsub("About ","",LineList)
    LineList <- gsub("results \\(","",LineList)
    LineList <- gsub(",","",LineList) %>% str_trim() %>% as.numeric()
    Citations_Data <- Citations_Data %>% bind_rows(
  data.frame(YEAR=YEAR,Citations = LineList)
)

}

Using {rvest}

for(i in 1:length(YEAR_RANGE)){
  
  YEAR <- YEAR_RANGE[i]
  FILE <- paste0("http://scholar.google.com/scholar?hl=en&as_sdt=2005&sciodt=0%2C5&cites=7296362022254018043&scipsc=&as_ylo=",YEAR,"&as_yhi=",YEAR)
  
  LineList <- rvest::read_html(FILE) %>% 
    html_nodes("div.gs_ab_mdw") %>% 
    html_text()
  
  
  LineList <- LineList[2]
  LineList <- strsplit(LineList,"results")[[1]][1]
  LineList <- gsub("About ","",LineList) %>% str_trim() 
  Citations_Data <- Citations_Data %>% bind_rows(
    data.frame(YEAR=YEAR,Citations = LineList)
  )
}

Making some adjustments to the Data

Bland_Altman_Citation <- Citations_Data
Bland_Altman_Citation <- Bland_Altman_Citation %>% 
  mutate(Citations=as.numeric(Citations)) %>% mutate(Year_Complete =case_when(
    YEAR == 1986 ~ "No",
    YEAR %in% 1987:2022 ~ "Yes",
    YEAR == 2023 ~ "No"
  ))
Bland_Altman_Citation %>% write.csv("Bland_Altman_Citations.csv",row.names = FALSE)

Using a saved copy of the data

Repeated use of the programme may result in 429 Gateway errors.

Bland_Altman_Citation <- read_csv("Bland_Altman_Citations.csv")
Bland_Altman_Citation %>% adorn_totals("row") %>% kable()
YEAR Citations Year_Complete
1986 17 NO
1987 48 YES
1988 88 YES
1989 124 YES
1990 167 YES
1991 232 YES
1992 311 YES
1993 379 YES
1994 490 YES
1995 564 YES
1996 682 YES
1997 781 YES
1998 885 YES
1999 887 YES
2000 1110 YES
2001 1130 YES
2002 1230 YES
2003 1380 YES
2004 1430 YES
2005 1630 YES
2006 1710 YES
2007 1830 YES
2008 2030 YES
2009 2130 YES
2010 2280 YES
2011 2260 YES
2012 2580 YES
2013 2550 YES
2014 2700 YES
2015 2580 YES
2016 2530 YES
2017 2510 YES
2018 2370 YES
2019 2300 YES
2020 2350 YES
2021 2270 YES
2022 2180 YES
2023 303 NO
Total 53028 - 
Bland_Altman_Citation %>% ggplot( aes(x=as.factor(YEAR),y=Citations,fill=Year_Complete)) + 
  geom_bar(stat="identity") + 
  theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1))