Data from Web of Science.
Query: TOPIC: (privacy AND student)
Timespan: All years.
Indexes: SCI-EXPANDED, SSCI, A&HCI, CPCI-S, CPCI-SSH, BKCI-S, BKCI-SSH, ESCI, CCR-EXPANDED, IC.
setwd(here::here("data", "WoS"))
<- dir(full.names = TRUE, pattern = ".txt")
files source("col_specs.R")
<- map_dfr(files, read_csv, skip = 3, col_type = col_specs) dat
::skim(dat) skimr
Name | dat |
Number of rows | 2185 |
Number of columns | 78 |
_______________________ | |
Column type frequency: | |
character | 18 |
numeric | 60 |
________________________ | |
Group variables | None |
Variable type: character
skim_variable | n_missing | complete_rate | min | max | empty | n_unique | whitespace |
---|---|---|---|---|---|---|---|
Title | 0 | 1.00 | 4 | 238 | 0 | 2183 | 0 |
Authors | 8 | 1.00 | 6 | 360 | 0 | 2143 | 0 |
Corporate Authors | 2181 | 0.00 | 9 | 55 | 0 | 4 | 0 |
Editors | 2183 | 0.00 | 28 | 63 | 0 | 2 | 0 |
Book Editors | 1749 | 0.20 | 5 | 184 | 0 | 290 | 0 |
Source Title | 1 | 1.00 | 4 | 249 | 0 | 1390 | 0 |
Publication Date | 44 | 0.98 | 4 | 12 | 0 | 553 | 0 |
Publication Year | 4 | 1.00 | 1 | 10 | 0 | 39 | 0 |
Volume | 582 | 0.73 | 1 | 5 | 0 | 215 | 0 |
Issue | 881 | 0.60 | 1 | 5 | 0 | 56 | 0 |
Supplement | 2174 | 0.01 | 1 | 2 | 0 | 6 | 0 |
Special Issue | 2061 | 0.06 | 1 | 3 | 0 | 9 | 0 |
Beginning Page | 312 | 0.86 | 1 | 6 | 0 | 931 | 0 |
Ending Page | 315 | 0.86 | 1 | 6 | 0 | 940 | 0 |
Article Number | 1952 | 0.11 | 1 | 29 | 0 | 214 | 0 |
DOI | 610 | 0.72 | 13 | 87 | 0 | 1575 | 0 |
Conference Title | 1582 | 0.28 | 11 | 247 | 0 | 472 | 0 |
Conference Date | 1579 | 0.28 | 1 | 19 | 0 | 463 | 0 |
Variable type: numeric
skim_variable | n_missing | complete_rate | mean | sd | p0 | p25 | p50 | p75 | p100 | hist |
---|---|---|---|---|---|---|---|---|---|---|
Part Number | 2181 | 0 | 10.50 | 17.67 | 1 | 1.75 | 2.00 | 10.75 | 37.00 | ▇▁▁▁▂ |
Total Citations | 1 | 1 | 11.22 | 44.02 | 0 | 0.00 | 2.00 | 9.00 | 1370.00 | ▇▁▁▁▁ |
Average per Year | 0 | 1 | 1.28 | 3.29 | 0 | 0.00 | 0.33 | 1.32 | 51.00 | ▇▁▁▁▁ |
1965 | 0 | 1 | 0.00 | 0.02 | 0 | 0.00 | 0.00 | 0.00 | 0.82 | ▇▁▁▁▁ |
1966 | 0 | 1 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | ▁▁▇▁▁ |
1967 | 0 | 1 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | ▁▁▇▁▁ |
1968 | 0 | 1 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | ▁▁▇▁▁ |
1969 | 0 | 1 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | ▁▁▇▁▁ |
1970 | 0 | 1 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | ▁▁▇▁▁ |
1971 | 0 | 1 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | ▁▁▇▁▁ |
1972 | 0 | 1 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | ▁▁▇▁▁ |
1973 | 0 | 1 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | ▁▁▇▁▁ |
1974 | 0 | 1 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | ▁▁▇▁▁ |
1975 | 0 | 1 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | ▁▁▇▁▁ |
1976 | 0 | 1 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | ▁▁▇▁▁ |
1977 | 0 | 1 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | ▁▁▇▁▁ |
1978 | 0 | 1 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | ▁▁▇▁▁ |
1979 | 0 | 1 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | ▁▁▇▁▁ |
1980 | 0 | 1 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | ▁▁▇▁▁ |
1981 | 0 | 1 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | ▁▁▇▁▁ |
1982 | 0 | 1 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | ▁▁▇▁▁ |
1983 | 0 | 1 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | ▁▁▇▁▁ |
1984 | 0 | 1 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | ▁▁▇▁▁ |
1985 | 0 | 1 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | ▁▁▇▁▁ |
1986 | 0 | 1 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | ▁▁▇▁▁ |
1987 | 0 | 1 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | ▁▁▇▁▁ |
1988 | 0 | 1 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | ▁▁▇▁▁ |
1989 | 0 | 1 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | ▁▁▇▁▁ |
1990 | 0 | 1 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | ▁▁▇▁▁ |
1991 | 0 | 1 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | ▁▁▇▁▁ |
1992 | 0 | 1 | 0.00 | 0.00 | 0 | 0.00 | 0.00 | 0.00 | 0.00 | ▁▁▇▁▁ |
1993 | 0 | 1 | 0.00 | 0.05 | 0 | 0.00 | 0.00 | 0.00 | 2.00 | ▇▁▁▁▁ |
1994 | 0 | 1 | 0.00 | 0.04 | 0 | 0.00 | 0.00 | 0.00 | 1.00 | ▇▁▁▁▁ |
1995 | 0 | 1 | 0.01 | 0.13 | 0 | 0.00 | 0.00 | 0.00 | 4.00 | ▇▁▁▁▁ |
1996 | 0 | 1 | 0.01 | 0.30 | 0 | 0.00 | 0.00 | 0.00 | 10.00 | ▇▁▁▁▁ |
1997 | 0 | 1 | 0.02 | 0.58 | 0 | 0.00 | 0.00 | 0.00 | 24.00 | ▇▁▁▁▁ |
1998 | 0 | 1 | 0.03 | 0.66 | 0 | 0.00 | 0.00 | 0.00 | 24.00 | ▇▁▁▁▁ |
1999 | 0 | 1 | 0.04 | 0.77 | 0 | 0.00 | 0.00 | 0.00 | 25.00 | ▇▁▁▁▁ |
2000 | 0 | 1 | 0.05 | 0.91 | 0 | 0.00 | 0.00 | 0.00 | 33.00 | ▇▁▁▁▁ |
2001 | 0 | 1 | 0.05 | 0.95 | 0 | 0.00 | 0.00 | 0.00 | 38.00 | ▇▁▁▁▁ |
2002 | 0 | 1 | 0.06 | 1.18 | 0 | 0.00 | 0.00 | 0.00 | 46.00 | ▇▁▁▁▁ |
2003 | 0 | 1 | 0.07 | 1.20 | 0 | 0.00 | 0.00 | 0.00 | 49.00 | ▇▁▁▁▁ |
2004 | 0 | 1 | 0.07 | 1.15 | 0 | 0.00 | 0.00 | 0.00 | 43.00 | ▇▁▁▁▁ |
2005 | 0 | 1 | 0.10 | 1.42 | 0 | 0.00 | 0.00 | 0.00 | 59.00 | ▇▁▁▁▁ |
2006 | 0 | 1 | 0.11 | 1.25 | 0 | 0.00 | 0.00 | 0.00 | 45.00 | ▇▁▁▁▁ |
2007 | 0 | 1 | 0.14 | 1.75 | 0 | 0.00 | 0.00 | 0.00 | 70.00 | ▇▁▁▁▁ |
2008 | 0 | 1 | 0.15 | 1.51 | 0 | 0.00 | 0.00 | 0.00 | 60.00 | ▇▁▁▁▁ |
2009 | 0 | 1 | 0.18 | 1.50 | 0 | 0.00 | 0.00 | 0.00 | 51.00 | ▇▁▁▁▁ |
2010 | 0 | 1 | 0.22 | 1.64 | 0 | 0.00 | 0.00 | 0.00 | 58.00 | ▇▁▁▁▁ |
2011 | 0 | 1 | 0.29 | 2.19 | 0 | 0.00 | 0.00 | 0.00 | 75.00 | ▇▁▁▁▁ |
2012 | 0 | 1 | 0.37 | 2.24 | 0 | 0.00 | 0.00 | 0.00 | 62.00 | ▇▁▁▁▁ |
2013 | 0 | 1 | 0.48 | 2.90 | 0 | 0.00 | 0.00 | 0.00 | 83.00 | ▇▁▁▁▁ |
2014 | 0 | 1 | 0.61 | 3.15 | 0 | 0.00 | 0.00 | 0.00 | 74.00 | ▇▁▁▁▁ |
2015 | 0 | 1 | 0.79 | 3.75 | 0 | 0.00 | 0.00 | 0.00 | 77.00 | ▇▁▁▁▁ |
2016 | 0 | 1 | 0.97 | 4.06 | 0 | 0.00 | 0.00 | 0.00 | 71.00 | ▇▁▁▁▁ |
2017 | 0 | 1 | 1.11 | 4.49 | 0 | 0.00 | 0.00 | 1.00 | 86.00 | ▇▁▁▁▁ |
2018 | 0 | 1 | 1.25 | 4.46 | 0 | 0.00 | 0.00 | 1.00 | 75.00 | ▇▁▁▁▁ |
2019 | 0 | 1 | 1.69 | 5.19 | 0 | 0.00 | 0.00 | 1.00 | 103.00 | ▇▁▁▁▁ |
2020 | 0 | 1 | 1.95 | 5.24 | 0 | 0.00 | 0.00 | 2.00 | 81.00 | ▇▁▁▁▁ |
2021 | 7 | 1 | 0.42 | 1.27 | 0 | 0.00 | 0.00 | 0.00 | 20.00 | ▇▁▁▁▁ |
# Clean names
names(dat)[!str_detect(names(dat), "\\d")] <-
::make_clean_names(names(dat)[!stringr::str_detect(names(dat), "\\d")])
janitor
# format date
<- dat %>%
dat mutate(
publication_year = publication_year %>% lubridate::ymd(truncated = 2L)
)
<- dat %>%
published group_by(publication_year) %>%
summarise(n = n()) %>%
filter(publication_year < Sys.Date()) # filter out flawed year entries
ggplot(published, aes(x = publication_year, y = n)) +
geom_area(fill = "#689f38", color = "#387002", alpha = 0.6) +
scale_x_date(
limit = c(as.Date("2001-01-01"), as.Date("2020-01-01")),
date_breaks = "1 year", labels = scales::date_format("%y")
+
) labs(
title = title,
subtitle = "New Publications per Year",
caption = caption,
x = "Publication Date", y = ""
+ theme_lk )
<- dat %>%
cited select("1965":"2021") %>%
summarise(across(everything(), sum, na.rm = TRUE)) %>%
pivot_longer(everything(), names_to = "year", values_to = "cited_n") %>%
mutate(
year = year %>% lubridate::ymd(truncated = 2L)
)
ggplot(cited, aes(x = year, y = cited_n)) +
geom_area(fill = "#039be5", color = "#006db3", alpha = 0.6) +
scale_x_date(
limit = c(as.Date("2001-01-01"), as.Date("2020-01-01")),
date_breaks = "1 year", labels = scales::date_format("%y")
+
) labs(
title = title,
subtitle = "Sum of Times Cited per Year",
caption = caption,
x = "Publication Date", y = ""
+
) theme_lk