Type: Package
Title: An R Package for Evaluating Scholarly Expertise Indices for Institutional Research Assessment
Version: 1.3.1
Maintainer: Nilabhra Rohan Das <nr.das@yahoo.com>
Description: Institutional performance assessment remains a key challenge to a multitude of stakeholders. Existing indicators such as h-type indicators, g-type indicators, and many others do not reflect expertise of institutions that defines their research portfolio. The package offers functionality to compute and visualise two novel indices: the x-index and the xd-index. The x-index evaluates an institution's scholarly expertise within a specific discipline or field, while the xd-index provides a broader assessment of overall scholarly expertise considering an institution's publication pattern and strengths across coarse thematic areas. These indices offer a nuanced understanding of institutional research capabilities, aiding stakeholders in research management and resource allocation decisions. Lathabai, H.H., Nandy, A., and Singh, V.K. (2021) <doi:10.1007/s11192-021-04188-3>. Nandy, A., Lathabai, H.H., and Singh, V.K. (2023) <doi:10.5281/zenodo.8305585>. This package provides the h-, g-, x-, xd-indices, and their variants for use with standard format of Web of Science (WoS) scrapped datasets.
License: GPL-3
Depends: R (≥ 4.4.2.0)
Imports: agop (≥ 0.2.4), dplyr (≥ 1.1.4), ggplot2 (≥ 3.5.0), Matrix (≥ 1.6.1.1), stats (≥ 4.3.3), tidyr (≥ 1.3.1)
Encoding: UTF-8
RoxygenNote: 7.3.3
LazyData: true
NeedsCompilation: no
Packaged: 2026-01-12 08:01:22 UTC; nilabhra.das
Author: Nilabhra Rohan Das ORCID iD [cre, aut], Abhirup Nandy ORCID iD [aut]
Repository: CRAN
Date/Publication: 2026-01-12 08:20:02 UTC

WoSdata

Description

The list of publications and associated metadata for a scholarly institution in India queried from the Web of Science (WoS) database. All publications, totalling 2,355 distinct publications, within a time frame of 10 years, spanning from 2011 to 2020 were extracted. For these publications, additional information/metadata, namely the 'UT (Unique WoS ID)', 'Keywords Plus', 'WoS Categories', and 'Times Cited, WoS Core' fields, were also extracted.

Usage

WoSdata

Format

A data frame with 2,355 rows and 4 columns. Each row represents a unique publication:

UT.Unique.WOS.ID

Unique publication identifier.

Keywords.Plus

Indexed keywords separated by ';'s.

WoS.Categories

Indexed categories separated by ';'s.

Times.Cited.WoS.Core

Total citations as recorded in the WoS database.

Source

* [WoS](https://clarivate.com/academia-government/scientific-and-academic-research/research-discovery-and-referencing/web-of-science/)

g_index - Egghe's g-index

Description

Calculate g-index for an institution using bibliometric data from an edge list, with an optional visualisation of ranked citation scores.

Usage

g_index(df, id = NULL, cit, plot = FALSE)

Arguments

df

Data frame object containing bibliometric data. This data frame must have at least two columns: one for keywords and one for citation counts. An optional column for unique identifiers can be included. Each row in the data frame should represent a document or publication.

id

Character string specifying the name of the column in "df" that contains unique identifiers for each document. Each cell in this column must contain a single ID (unless missing) and not multiple IDs. Must be included when 'plot' parameter is set to "TRUE". Default set to NULL.

cit

Character string specifying the name of the column in "df" that contains the number of citations each document has received. Citations must be represented as integers. Each cell in this column should contain a single integer value (unless missing) representing the citation count for the corresponding document.

plot

Logical value indicating whether to generate and display a plot of the g-index calculation. Set to "TRUE" or "T" to generate the plot, and "FALSE" (default) or "F" to skip plot generation.

Value

g-index magnitude and optional plot.

Examples

# Load example data
data(WoSdata)

# Calculate g-index with plot
g_index(df = WoSdata,
        id = "UT.Unique.WOS.ID",
        cit = "Times.Cited.WoS.Core",
        plot = TRUE)

h_index - Hirsch's h-index

Description

Calculate h-index for an institution using bibliometric data from an edge list, with an optional visualisation of ranked citation scores.

Usage

h_index(df, id = NULL, cit, plot = FALSE)

Arguments

df

Data frame object containing bibliometric data. This data frame must have at least two columns: one for keywords and one for citation counts. An optional column for unique identifiers may be included. Each row in the data frame should represent a document or publication.

id

Character string specifying the name of the column in "df" that contains unique identifiers for each document. Each cell in this column must contain a single ID (unless missing) and not multiple IDs. Must be included when 'plot' parameter is set to "TRUE". Default set to NULL.

cit

Character string specifying the name of the column in "df" that contains the number of citations each document has received. Citations must be represented as integers. Each cell in this column should contain a single integer value (unless missing) representing the citation count for the corresponding document.

plot

Logical value indicating whether to generate and display a plot of the h-index calculation. Set to "TRUE" or "T" to generate the plot, and "FALSE" (default) or "F" to skip plot generation.

Value

h-index magnitude and optional plot.

Examples

# Load example data
data(WoSdata)

# Calculate h-index with produce plot
h_index(df = WoSdata,
        id = "UT.Unique.WOS.ID",
        cit = "Times.Cited.WoS.Core",
        plot = TRUE)

ivw_xd_index - Inverse Variance Weighted (IVW) Expertise Diversity (xd-) Index

Description

Calculate IVW adjusted xd-index for an institution using bibliometric data from an edge list, with an optional visualisation of ranked citation scores. The function is suitable for including inside loops when plotting parameter is set to "FALSE" or "F".

Usage

ivw_xd_index(df, cat, id, cit, vfc = NULL, type = "h", dlm = ";", plot = FALSE)

Arguments

df

Data frame object containing bibliometric data. This data frame must have at least three columns: one for categories, one for unique IDs, and one for citation counts. Each row in the data frame should represent a document or publication.

cat

Character string specifying the name of the column in "df" that contains categories. Each cell in this column may contain no categories (missing), a single category or multiple categories separated by a specified delimiter.

id

Character string specifying the name of the column in "df" that contains unique identifiers for each document. Each cell in this column must contain a single ID (unless missing) and not multiple IDs.

cit

Character string specifying the name of the column in "df" that contains the number of citations each document has received. Citations must be represented as integers. Each cell in this column should contain a single integer value (unless missing) representing the citation count for the corresponding document.

vfc

Data frame with columns 'cat' and 'var_cit'. Optionally required for using population variances.

type

"h" (default) for Hirsch's h-type index or "g" for Egghe's g-type index.

dlm

Character string specifying the delimiter used in the "cat" column to separate multiple categories within a single cell. The delimiter should be consistent across the entire "cat" column. Common delimiters include ";" (default), "/", ":", and ",".

plot

Logical value indicating whether to generate and display a plot of the xd-index calculation. Set to "TRUE" or "T" to generate the plot, and "FALSE" (default) or "F" to skip plot generation.

Value

IVW xd-index magnitude, core categories, and optional plot.

Examples

# Load example data
data(WoSdata)

# Calculate ivw xd-index with plot
ivw_xd_index(df = WoSdata,
        id = "UT.Unique.WOS.ID",
        cat = "WoS.Categories",
        cit = "Times.Cited.WoS.Core",
        plot = TRUE)

x_index - Expertise (x-) Index

Description

Calculate x-index for an institution using bibliometric data from an edge list, with an optional visualisation of ranked citation scores. The function is suitable for including inside loops when plotting parameter is set to "FALSE" or "F".

Usage

x_index(df, kw, id, cit, type = "h", dlm = ";", plot = FALSE)

Arguments

df

Data frame object containing bibliometric data. This data frame must have at least three columns: one for keywords, one for unique IDs, and one for citation counts. Each row in the data frame should represent a document or publication.

kw

Character string specifying the name of the column in "df" that contains keywords. Each cell in this column may contain no keywords (missing), a single keyword or multiple keywords separated by a specified delimiter.

id

Character string specifying the name of the column in "df" that contains unique identifiers for each document. Each cell in this column must contain a single ID (unless missing) and not multiple IDs.

cit

Character string specifying the name of the column in "df" that contains the number of citations each document has received. Citations must be represented as integers. Each cell in this column should contain a single integer value (unless missing) representing the citation count for the corresponding document.

type

"h" (default) for Hirsch's h-type index or "g" for Egghe's g-type index.

dlm

Character string specifying the delimiter used in the "kw" column to separate multiple keywords within a single cell. The delimiter should be consistent across the entire "kw" column. Common delimiters include ";" (default), "/", ":", and ",".

plot

Logical value indicating whether to generate and display a plot of the x-index calculation. Set to "TRUE" or "T" to generate the plot, and "FALSE" (default) or "F" to skip plot generation.

Value

x-index magnitude, core keywords, and optional plot.

Examples

# Load example data
data(WoSdata)

# Calculate x-index with plot
x_index(df = WoSdata,
        id = "UT.Unique.WOS.ID",
        kw = "Keywords.Plus",
        cit = "Times.Cited.WoS.Core",
        plot = TRUE)

xc_index - Category-adjusted Expertise (x-) Index

Description

Calculate the xc-index for an institution using bibliometric data from an edge list, with an optional plot visualisation. The function is suitable for including inside loops when plotting parameter is set to "FALSE" or "F".

Usage

xc_index(df, kw, cat, id, cit, type = "h", dlm = c(";", ";"), plot = FALSE)

Arguments

df

Data frame object containing bibliometric data. This data frame must have at least three columns: one for keywords, one for unique IDs, and one for citation counts. Each row in the data frame should represent a document or publication.

kw

Character string specifying the name of the column in "df" that contains keywords. Each cell in this column may contain no keywords (missing), a single keyword or multiple keywords separated by a specified delimiter.

cat

Character string specifying the name of the column in "df" that contains categories. Each cell in this column may contain no categories (missing), a single category or multiple categories separated by a specified delimiter.

id

Character string specifying the name of the column in "df" that contains unique identifiers for each document. Each cell in this column must contain a single ID (unless missing) and not multiple IDs.

cit

Character string specifying the name of the column in "df" that contains the number of citations each document has received. Citations must be represented as integers. Each cell in this column should contain a single integer value (unless missing) representing the citation count for the corresponding document.

type

"h" (default) for Hirsch's h-type index or "g" for Egghe's g-type index. Default set to "h".

dlm

Character vector specifying the delimiter used in the "kw" and "cat" columns to separate multiple keywords and categories within a single cell. The delimiter should be consistent across the entirety of the two columns. The first element in the vector is used as the delimiter for keywords, while the second element is used for categories. Common delimiters include ";", "/", ":", and ",", and example usage should be similar to 'c(";", ";")' (default), 'c(";", ",")', or 'c(",", ":")'.

plot

Logical value indicating whether to generate and display a plot of the xc-index calculation. Set to "TRUE" or "T" to generate the plot, and "FALSE" (default) or "F" to skip plot generation.

Value

xc-index magnitude, core category specific keywords and optional plot.

Examples

# Load example data
data(WoSdata)

# Calculate xc-index with plot
xc_index(df = WoSdata,
         id = "UT.Unique.WOS.ID",
         kw = "Keywords.Plus",
         cat = "WoS.Categories",
         cit = "Times.Cited.WoS.Core",
         plot = TRUE)

xd_index - Expertise Diversity (xd-) Index

Description

Calculate the xd-index (and its variants, field-normalized and fractional) for an institution using bibliometric data from an edge list, with an optional visualisation of ranked citation scores.

Usage

xd_index(
  df,
  cat,
  id,
  cit,
  mfc = NULL,
  type = "h",
  dlm = ";",
  variant = "full",
  plot = FALSE
)

Arguments

df

Data frame object containing bibliometric data. Must have at least three columns: one for categories, one for unique IDs, and one for citation counts.

cat

Character string specifying the name of the column in "df" that contains categories. Categories can be multiple separated by a delimiter.

id

Character string specifying the name of the column in "df" that contains unique identifiers for each document. Each cell in this column must contain a single ID (unless missing) and not multiple IDs.

cit

Character string specifying the name of the column in "df" that contains the number of citations each document has received. Citations must be represented as integers. Each cell in this column should contain a single integer value (unless missing) representing the citation count for the corresponding document.

mfc

Data frame with columns 'cat' and 'mean_cit'. Optionally required to utilise population means when variant set to "f".

type

"h" (default) for Hirsch's h-type index or "g" for Egghe's g-type index.

dlm

Character string specifying the delimiter used in the "cat" column to separate multiple categories within a single cell. The delimiter should be consistent across the entire "cat" column. Common delimiters include ";" (default), "/", ":", and ",".

variant

One of "full" (default), "f", or "FN".

  • "full" — Computes the unconditional xd-index.

  • "f" — Computes the fractional xd-index. If set to 'f', input data frame 'df' must include an 'inst_count' column which gives the number of institutions per publication.

  • "FN" — Computes the field-normalised xd-index. If set to 'FN', input may optionally include an 'mfc' data frame which gives the population level mean citations for different fields. If not provided, sample mean field citations will be used.

plot

Logical value indicating whether to generate and display a plot of the xd-index calculation. Set to "TRUE" or "T" to generate the plot, and "FALSE" (default) or "F" to skip plot generation.

Value

xd-index magnitude, core categories, and optional plot.

Examples

# Load example data
data(WoSdata)

# Calculate xd-index with plot
xd_index(df = WoSdata,
         id = "UT.Unique.WOS.ID",
         cat = "WoS.Categories",
         cit = "Times.Cited.WoS.Core",
         plot = TRUE)

# Calculate field-normalised xd-index with plot
xd_index(df = WoSdata,
         id = "UT.Unique.WOS.ID",
         cat = "WoS.Categories",
         cit = "Times.Cited.WoS.Core",
         variant = "FN",
         plot = TRUE)