Bibliometria
Vitor Klein Schmidt
04 dezembro, 2020
1 Observations
The network analysis ware conducted using VosViewer, in this sense we can not share through this link;
Not all analysis conducted here ware used in the paper, but we we choose to make them available for the purpose of completeness;
2 Loading the packages
library(bibliometrix)
library(tidyverse)
library(readxl)
library(knitr)
library(kableExtra)
library(htmltools)
library(rsconnect)3 Loading the final version of the databe
library(readxl)
Database <- read_excel("C:/Users/user/Desktop/Vida acadêmica/Disciplinas/Economia da Inovação/Bibliometria/Base de dados/Bibliometrix_DE_corrigido22.xlsx")
M <- Database
M <- convert2df(file = M, format = "excel")##
## Converting your wos collection into a bibliographic dataframe
##
## Done!
##
##
## Generating affiliation field tag AU_UN from C1: Done!4 Descriptive statistics
results <- biblioAnalysis(M, sep = ";")options(width=100)
S <- summary(object = results, k = 10, pause = F) # top 10##
##
## MAIN INFORMATION ABOUT DATA
##
## Timespan 2004 : 2019
## Sources (Journals, Books, etc) 264
## Documents 475
## Average years from publication 3.54
## Average citations per documents 18.34
## Average citations per year per doc 3.168
## References 25080
##
## DOCUMENT TYPES
## article 475
##
## DOCUMENT CONTENTS
## Keywords Plus (ID) 1567
## Author's Keywords (DE) 1509
##
## AUTHORS
## Authors 1135
## Author Appearances 1320
## Authors of single-authored documents 85
## Authors of multi-authored documents 1050
##
## AUTHORS COLLABORATION
## Single-authored documents 90
## Documents per Author 0.419
## Authors per Document 2.39
## Co-Authors per Documents 2.78
## Collaboration Index 2.73
##
##
## Annual Scientific Production
##
## Year Articles
## 2004 1
## 2006 2
## 2007 1
## 2008 4
## 2009 2
## 2010 8
## 2011 14
## 2012 11
## 2013 26
## 2014 23
## 2015 32
## 2016 63
## 2017 69
## 2018 104
## 2019 115
##
## Annual Percentage Growth Rate 37.20813
##
##
## Most Productive Authors
##
## Authors Articles Authors Articles Fractionalized
## 1 CARAYANNIS E 9 CARAYANNIS E 4.03
## 2 CHEN J 9 ADNER R 3.50
## 3 ADNER R 5 CHEN J 3.33
## 4 BIFULCO F 5 SAGUY I 2.17
## 5 CAMPBELL D 5 CHIDAMBARAM R 2.00
## 6 WU J 5 ETZKOWITZ H 2.00
## 7 KOMNINOS N 4 GAMIDULLAEVA L 2.00
## 8 LIU Z 4 KOMNINOS N 2.00
## 9 RITALA P 4 LUO J 2.00
## 10 SAGUY I 4 CAMPBELL D 1.87
##
##
## Top manuscripts per citations
##
## Paper DOI TC TCperYear
## 1 ADNER R, 2010, STRATEGIC MANAGE J 10.1002/smj.821 783 71.2
## 2 SCHAFFERS H, 2011, LECT NOTES COMPUT SCI 10.1007/978-3-642-20898-0_31 563 56.3
## 3 ADNER R, 2006, HARV BUS REV NA 413 27.5
## 4 GAWER A, 2014, RES POLICY 10.1016/j.respol.2014.03.006 363 51.9
## 5 CARAYANNIS E, 2009, INT J TECHNOL MANAGE 10.1504/IJTM.2009.023374 322 26.8
## 6 ZYGIARIS S, 2013, J KNOWL ECON 10.1007/s13132-012-0089-4 211 26.4
## 7 ROHRBECK R, 2009, R D MANAGE 10.1111/j.1467-9310.2009.00568.x 188 15.7
## 8 ADNER R, 2017, J MANAG 10.1177/0149206316678451 175 43.8
## 9 NAMBISAN S, 2013, ENTREP THEORY PRACT 10.1111/j.1540-6520.2012.00519.x 169 21.1
## 10 KOMNINOS N, 2013, J KNOWL ECON 10.1007/s13132-012-0083-x 154 19.2
##
##
## Corresponding Author's Countries
##
## Country Articles Freq SCP MCP MCP_Ratio
## 1 USA 56 0.2146 48 8 0.1429
## 2 CHINA 19 0.0728 13 6 0.3158
## 3 FINLAND 18 0.0690 16 2 0.1111
## 4 UNITED KINGDOM 15 0.0575 13 2 0.1333
## 5 GERMANY 14 0.0536 14 0 0.0000
## 6 SPAIN 14 0.0536 13 1 0.0714
## 7 CANADA 11 0.0421 9 2 0.1818
## 8 NETHERLANDS 11 0.0421 7 4 0.3636
## 9 BRAZIL 10 0.0383 9 1 0.1000
## 10 FRANCE 10 0.0383 7 3 0.3000
##
##
## SCP: Single Country Publications
##
## MCP: Multiple Country Publications
##
##
## Total Citations per Country
##
## Country Total Citations Average Article Citations
## 1 USA 2255 40.268
## 2 UNITED KINGDOM 744 49.600
## 3 FRANCE 493 49.300
## 4 GREECE 487 97.400
## 5 GERMANY 278 19.857
## 6 FINLAND 245 13.611
## 7 CHINA 228 12.000
## 8 NETHERLANDS 210 19.091
## 9 SPAIN 209 14.929
## 10 CANADA 205 18.636
##
##
## Most Relevant Sources
##
## Sources Articles
## 1 TECHNOLOGICAL FORECASTING AND SOCIAL CHANGE 30
## 2 TECHNOLOGY INNOVATION MANAGEMENT REVIEW 18
## 3 SUSTAINABILITY (SWITZERLAND) 16
## 4 JOURNAL OF THE KNOWLEDGE ECONOMY 14
## 5 INTERNATIONAL JOURNAL OF TECHNOLOGY MANAGEMENT 11
## 6 INTERNATIONAL JOURNAL OF INNOVATION AND TECHNOLOGY MANAGEMENT 9
## 7 JOURNAL OF TECHNOLOGY TRANSFER 9
## 8 EUROPEAN JOURNAL OF INNOVATION MANAGEMENT 7
## 9 JOURNAL OF OPEN INNOVATION: TECHNOLOGY MARKET AND COMPLEXITY 7
## 10 OMICS A JOURNAL OF INTEGRATIVE BIOLOGY 7
##
##
## Most Relevant Keywords
##
## Author Keywords (DE) Articles Keywords-Plus (ID) Articles
## 1 INNOVATION ECOSYSTEM 168 INNOVATION 101
## 2 INNOVATION 90 ECOSYSTEMS 86
## 3 ECOSYSTEM 51 ECOLOGY 32
## 4 ENTREPRENEURSHIP 33 INNOVATION ECOSYSTEMS 26
## 5 OPEN INNOVATION 31 HUMAN 24
## 6 SMART CITY 20 ARTICLE 22
## 7 BUSINESS ECOSYSTEM 16 KNOWLEDGE 21
## 8 COLLABORATION 12 TECHNOLOGY 21
## 9 SUSTAINABILITY 12 VALUE CREATION 21
## 10 LIVING LAB 11 STRATEGY 19plot(x = results, k = 10, pause = FALSE)
5 ThreeFieldsPlot
threeFieldsPlot(M, fields = c("AU", "DE", "ID"), n = c(20, 20, 20),
width = 800, height = 400)6 Scientific production
6.1 Annual Scientific Production
anos <- results$Years
anos <- as.data.frame(anos)
anos %>% count(anos)## anos n
## 1 2004 1
## 2 2006 2
## 3 2007 1
## 4 2008 4
## 5 2009 2
## 6 2010 8
## 7 2011 14
## 8 2012 11
## 9 2013 26
## 10 2014 23
## 11 2015 32
## 12 2016 63
## 13 2017 69
## 14 2018 104
## 15 2019 115anos2 <-as.data.frame(list(2004:2019))
colnames(anos2) <- "Ano"
anos2$Freq <- list(1,0,2,1,4,2,8,14,11,26,23,32,63,69,105,115)
anos2$Freq <- as.numeric(anos2$Freq)
g1 <- anos2 %>% ggplot(aes(y = Freq, x = Ano)) +
geom_line(col = "Lightblue") +
geom_area(fill ="Lightblue") +
scale_x_continuous(breaks = c(2004,2006,2008,2010,2012,2014,2016,2018)) +
theme_bw(base_size = 10) +
theme(text=element_text(family= "Times New Roman", face="bold"), plot.title = element_text(hjust = 0.5)) +
labs(title = "2a") + xlab("Years") + ylab("Number of articles")
g1
6.2 Average Article Citations per Year
AACY <- cbind(results$TCperYear, results$Years)
colnames(AACY) <- c("TCperYear", "Years")
AACY <- as.data.frame(AACY)
AACY <- tapply(AACY$TCperYear, AACY$Years, mean)
AACY <- as.data.frame(AACY)
colnames(AACY) <- "AvgCitations"
AACY$Years <- list(2004,2006,2007,2008,2009,2010,2011,2012,2013,2014,2015,2016,2017,2018,2019)
AACY$Years <- as.numeric(AACY$Years)
g2 <- AACY %>% ggplot(aes(x = Years, y = AvgCitations)) +
geom_line(col = "Lightblue") +
geom_area(fill ="Lightblue") +
scale_x_continuous(breaks = c(2004,2006,2008,2010,2012,2014,2016,2018)) +
theme_bw(base_size = 10) +
theme(text=element_text(family= "Times New Roman", face="bold"), plot.title = element_text(hjust = 0.5)) +
labs(title = "2b") + xlab("Years") + ylab("Citation")
g2
library(gridExtra)
grid.arrange(g1,g2, ncol = 2)
6.3 Average Total Citation
ATC <- cbind(results$TotalCitation, results$Years)
colnames(ATC) <- c("TCperYear", "Years")
ATC <- as.data.frame(ATC)
ATC <- tapply(ATC$TCperYear, ATC$Years, mean)
ATC <- as.data.frame(ATC)
ATC$Years <- list(2004,2006,2007,2008,2009,2010,2011,2012,2013,2014,2015,2016,2017,2018,2019)
ATC$Years <- as.numeric(ATC$Years)
ATC %>% ggplot(aes(x = Years, y = ATC)) +
geom_line(col = "Lightblue") +
geom_area(fill ="Lightblue") +
scale_x_continuous(breaks = c(2004,2006,2008,2010,2012,2014,2016,2018)) +
theme_bw(base_size = 10) +
theme(text=element_text(family= "Times New Roman", face="bold"), plot.title = element_text(hjust = 0.5)) +
labs(title = "Average Total Citation") + xlab("Years") + ylab("Citation")
7 Scientific production of journals
7.1 Journals with more articles
MRS <- read.csv("C:/Users/user/Desktop/Vida acadêmica/Disciplinas/Economia da Inovação/Bibliometria/Tabelas 3/3 Most_Relevant_Sources.csv")
str(MRS)## 'data.frame': 50 obs. of 2 variables:
## $ Sources : chr "TECHNOLOGICAL FORECASTING AND SOCIAL CHANGE" "TECHNOLOGY INNOVATION MANAGEMENT REVIEW" "SUSTAINABILITY (SWITZERLAND)" "JOURNAL OF THE KNOWLEDGE ECONOMY" ...
## $ Articles: int 30 18 16 14 11 9 9 7 7 7 ...MRS2 <- transform(MRS, Sources = reorder(Sources, Articles))
MRS2 <- MRS2 %>% head(10)
MRS2 <- transform(MRS2, Sources = reorder(Sources, Articles))
g3 <- MRS2 %>% ggplot(aes(y = Sources, weight = Articles, fill = Articles)) +
geom_bar(show.legend = F) +
scale_fill_continuous(low = "Lightblue", high = "Darkblue") +
scale_x_continuous(breaks = c(0,5,10,15,20,25,30,35)) +
theme_bw(base_size = 10) +
theme(text=element_text(family= "Times New Roman", face="bold"), plot.title = element_text(hjust = 0.5)) +
labs(title = "5a") + xlab("Number of articles") + ylab("Source")
g3
7.2 Most Cited Sources
MCS <- read.csv("C:/Users/user/Desktop/Vida acadêmica/Disciplinas/Economia da Inovação/Bibliometria/Tabelas 3/4 Most_Cited_Sources.csv")
str(MCS)## 'data.frame': 50 obs. of 2 variables:
## $ Sources : chr "STRATEGIC MANAGE J" "RES POLICY" "ORGAN SCI" "ACAD MANAGE REV" ...
## $ Articles: int 300 189 128 120 105 105 91 81 81 76 ...MCS <- transform(MCS, Sources = reorder(Sources, Articles))
MCS <- MCS %>% head(18)
MCS <- MCS[-c(5,7,9,10,11,13,15,16),]
g4 <- MCS %>% ggplot(aes(y = Sources, weight = Articles, fill = Articles)) +
geom_bar(show.legend = F) +
scale_fill_continuous(low = "Lightblue", high = "Darkblue") +
scale_x_continuous(breaks = c(0,50,100,150,200,250,300,350)) +
theme_bw(base_size = 10) +
theme(text=element_text(family= "Times New Roman", face="bold"), plot.title = element_text(hjust = 0.5)) +
labs(title = "5b") + xlab("Number of citations") + ylab("Source")
g4
7.3 Bradford Law
BR <- bradford(M)
BR$graph
7.4 Source Impact
SI <- read.csv("C:/Users/user/Desktop/Vida acadêmica/Disciplinas/Economia da Inovação/Bibliometria/Tabelas 3/6 Source_Impact.csv")
str(SI)## 'data.frame': 25 obs. of 7 variables:
## $ Source : chr "TECHNOLOGICAL FORECASTING AND SOCIAL CHANGE" "TECHNOLOGY INNOVATION MANAGEMENT REVIEW" "SUSTAINABILITY (SWITZERLAND)" "JOURNAL OF THE KNOWLEDGE ECONOMY" ...
## $ h_index : int 12 7 5 6 6 4 7 4 4 4 ...
## $ g_index : int 19 11 9 14 11 5 9 7 7 7 ...
## $ m_index : num 1.714 1.167 1.25 0.545 0.5 ...
## $ TC : int 423 147 89 546 467 35 208 73 56 75 ...
## $ NP : int 30 18 16 14 11 9 9 7 7 7 ...
## $ PY_start: int 2014 2015 2017 2010 2009 2015 2010 2015 2016 2017 ...SI <- transform(SI, Source = reorder(Source , h_index))
SI <- SI %>% head(10)
SI <- transform(SI, Source = reorder(Source , h_index))
g6 <- SI %>% ggplot(aes(y = Source, weight = h_index, fill = h_index)) +
geom_bar(show.legend = F) +
scale_fill_continuous(low = "Lightblue", high = "Darkblue") +
scale_x_continuous(breaks = c(0,1,2,3,4,5,6,7,8,9,10,11,12,13)) +
theme_bw(base_size = 10) +
theme(text=element_text(family= "Times New Roman", face="bold"), plot.title = element_text(hjust = 0.5)) +
labs(title = "5c") + xlab("H Index") + ylab("Source")
g6
7.5 Source Dynamics
SD <- read.csv("C:/Users/user/Desktop/Vida acadêmica/Disciplinas/Economia da Inovação/Bibliometria/Tabelas 3/7 Source_Dynamics.csv")
str(SD)## 'data.frame': 16 obs. of 6 variables:
## $ Year : int 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 ...
## $ SUSTAINABILITY..SWITZERLAND. : int 0 0 0 0 0 0 0 0 0 0 ...
## $ TECHNOLOGICAL.FORECASTING.AND.SOCIAL.CHANGE : int 0 0 0 0 0 0 0 0 0 0 ...
## $ INTERNATIONAL.JOURNAL.OF.TECHNOLOGY.MANAGEMENT: int 0 0 0 0 0 1 0 0 0 1 ...
## $ JOURNAL.OF.THE.KNOWLEDGE.ECONOMY : int 0 0 0 0 0 0 1 1 0 3 ...
## $ TECHNOLOGY.INNOVATION.MANAGEMENT.REVIEW : int 0 0 0 0 0 0 0 0 0 0 ...library(reshape2)
library(directlabels)
library(ggrepel)
library(grid)
SD <- melt(SD, id.vars = c("Year"))
str(SD)## 'data.frame': 80 obs. of 3 variables:
## $ Year : int 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 ...
## $ variable: Factor w/ 5 levels "SUSTAINABILITY..SWITZERLAND.",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ value : int 0 0 0 0 0 0 0 0 0 0 ...SD$value <- as.numeric(SD$value)
SD$Year <- as.numeric(SD$Year)
library(stringi)
SD$variable2 <- stri_replace_all(SD[,2], " ", fixed=".")
g7 <- SD %>% ggplot(aes(y = value, x = Year, color = variable2)) +
geom_line() +
geom_point() +
scale_x_continuous(breaks = c(2004,2008,2012,2016,2019)) +
labs(title = "5d") + xlab("Year") + ylab("Anual Occurrences") +
guides(color = guide_legend(title = "Journal")) +
theme_bw(base_size = 10) +
theme(text=element_text(family= "Times New Roman", face="bold"), plot.title = element_text(hjust = 0.5),
legend.title = element_text(color = "black", size = 10),
legend.text = element_text(color = "black", size = 6))
g7
gridExtra::grid.arrange(g3, g4, g6, g7, ncol = 2, nrow = 2)
8 Authors’ analysis
8.1 Authors with more publications
AMP <- read.csv("C:/Users/user/Desktop/Vida acadêmica/Disciplinas/Economia da Inovação/Bibliometria/Tabelas 3/8 Most_Productive_Authors.csv")
str(AMP)## 'data.frame': 20 obs. of 4 variables:
## $ Authors : chr "CARAYANNIS E" "CHEN J" "ADNER R" "BIFULCO F" ...
## $ Articles : int 9 9 5 5 5 5 4 4 4 4 ...
## $ Authors.Frac : chr "CARAYANNIS E" "ADNER R" "CHEN J" "SAGUY I" ...
## $ Articles.Fractionalized: num 4.03 3.5 3.33 2.17 2 ...AMP$Articles <- as.numeric(AMP$Articles)
AMP <- transform(AMP, Authors = reorder(Authors , Articles))
AMP <- AMP %>% head(10)
g8 <- AMP %>% ggplot(aes(y = Authors, weight = Articles, fill = Articles)) +
geom_bar(show.legend = F) +
scale_fill_continuous(low = "Lightblue", high = "Darkblue") +
scale_x_continuous(breaks = c(0,1,2,3,4,5,6,7,8,9,10)) +
theme_bw(base_size = 10) +
theme(text=element_text(family= "Times New Roman", face="bold"), plot.title = element_text(hjust = 0.5)) +
labs(title = "3b") + xlab("Publications") + ylab("Author")
g8
8.2 Most cited authors locally
# Most_Local_Cited_Authors #
MLCA <- read.csv("C:/Users/user/Desktop/Vida acadêmica/Disciplinas/Economia da Inovação/Bibliometria/Tabelas 3/9 Most_Local_Cited_Authors.csv", sep = ";")
str(MLCA)## 'data.frame': 24 obs. of 2 variables:
## $ Authors : chr "ADNER" "CHESBROUGH" "CARAYANNIS" "ETZKOWITZ" ...
## $ Citations: int 315 192 183 145 131 99 98 90 89 84 ...MLCA$Citations <- as.numeric(MLCA$Citations)
MLCA <- transform(MLCA, Authors = reorder(Authors , Citations))
MLCA <- MLCA %>% head(10)
g9 <- MLCA %>% ggplot(aes(y = Authors, weight = Citations, fill = Citations)) +
geom_bar(show.legend = F) +
scale_fill_continuous(low = "Lightblue", high = "Darkblue") +
scale_x_continuous(breaks = c(0,50,100,150,200,250, 300)) +
theme_bw(base_size = 10) +
theme(text=element_text(family= "Times New Roman", face="bold"), plot.title = element_text(hjust = 0.5)) +
labs(title = "3a") + xlab("Citations") + ylab("Author")
g9
8.3 Productivity over time
topAU <- authorProdOverTime(M, k = 10, graph = TRUE)
# Tabela de produtividade
head(topAU$dfAU)## Author year freq TC TCpY
## 1 ADNER R 2006 1 413 27.53333
## 2 ADNER R 2010 1 783 71.18182
## 3 ADNER R 2016 1 103 20.60000
## 4 ADNER R 2017 1 175 43.75000
## 5 ADNER R 2019 1 0 0.00000
## 6 BIFULCO F 2016 2 2 0.40000# Plotando k = 10#
M$TC = as.numeric(M$TC)
M$PY = as.numeric(M$PY)
AU = names(tableTag(M, "AU"))
k = min(10, length(AU))
AU = AU[1:k]
df = data.frame(Author = "NA", year = NA, TI = "NA", SO = "NA",
DOI = "NA", TC = NA, TCpY = NA, stringsAsFactors = FALSE)
Y = as.numeric(substr(Sys.time(), 1, 4))
if (!("DI" %in% names(M))) {
M$DI = "NA"
}
for (i in 1:length(AU)) {
ind = which(regexpr(AU[i], M$AU) > -1)
TCpY = M$TC[ind]/(Y - M$PY[ind] + 1)
dfAU = data.frame(Author = rep(AU[i], length(ind)),
year = M$PY[ind], TI = M$TI[ind], SO = M$SO[ind],
DOI = M$DI[ind], TC = M$TC[ind], TCpY = TCpY, stringsAsFactors = TRUE)
df = rbind(df, dfAU)
}
df = df[-1, ]
df2 <- dplyr::group_by(df, .data$Author, .data$year) %>%
dplyr::summarise(freq = length(.data$year), TC = sum(.data$TC),
TCpY = sum(.data$TCpY))
df2 = as.data.frame(df2)
df2$Author = factor(df2$Author, levels = AU[1:k])
g10 <- ggplot(df2, aes(x = .data$Author, y = .data$year, text = paste("Author: ",
df2$Author, "\nYear: ", df2$year, "\nN. of Articles: ",
df2$freq, "\nTotal Citations per Year: ", round(TCpY,
2)))) + geom_point(aes(alpha = df2$TCpY, size = df2$freq),
color = "dodgerblue4") + scale_size(range = c(2, 6)) +
scale_alpha(range = c(0.3, 1)) + scale_y_continuous(breaks = seq(min(df2$year),
max(df2$year), by = 2)) + guides(size = guide_legend(order = 1,
"N.Articles"), alpha = guide_legend(order = 2, "TC per Year")) +
theme_bw(base_size = 10) +
theme(legend.position = "right", text = element_text(color = "#444444", family= "Times New Roman", face="bold"),
plot.title = element_text(hjust = 0.5),
panel.background = element_rect(fill = "white"),
panel.grid.minor = element_line(color = "gray"),
panel.grid.major = element_line(color = "gray"),
axis.title = element_text(size = 10, color = "black", face = "bold"),
axis.title.y = element_text(vjust = 0.5, angle = 90, face = "bold"),
axis.title.x = element_text(hjust = 0.5, face = "bold", colour = "black"),
axis.text.x = element_text(face = "bold"),
axis.text.y = element_text(face = "bold")) +
labs(title = "3d", x = "Author", y = "Year") +
geom_line(aes(x = df2$Author, y = df2$year, group = df2$Author), size = 1, color = "firebrick", alpha = 0.3) +
scale_x_discrete(limits = rev(levels(df2$Author))) + coord_flip()
plot(g10)
8.4 Lotka Law
L <- lotka(results)
# Distribuição de autoria
L$AuthorProd## N.Articles N.Authors Freq
## 1 1 1002 0.882819383
## 2 2 107 0.094273128
## 3 3 14 0.012334802
## 4 4 6 0.005286344
## 5 5 4 0.003524229
## 6 9 2 0.001762115# Coeficiente Beta
L$Beta## [1] 2.999011# Constante
L$C## [1] 0.5899561# Ajuste de bondade
L$R2## [1] 0.9438491# Valor de P para o teste K-S
L$p.value## [1] 0.4413066# Distribuição observada
Observed=L$AuthorProd[,3]
# Distribuição teórica para um Beta = 2 (3.008399) | Ajustar o Beta para o valor correto no artigo
Theoretical=10^(log10(L$C)-3.008399*log10(L$AuthorProd[,1]))
plot(L$AuthorProd[,1],Theoretical,type="l",col="red",ylim=c(0, 1), xlab="Articles",ylab="Freq. of Authors",main="Scientific Productivity")
lines(L$AuthorProd[,1],Observed,col="blue")
legend(x="topright",c("Theoretical (B=3.008)","Observed"),col=c("red","blue"),lty = c(1,1,1),cex=0.6,bty="n")
L$artigos <- L$AuthorProd[,1]
L <- as.data.frame(L)
L %>% ggplot(aes(x = artigos)) +
geom_line(aes(y = Observed, colour = "Observed"), size = 1L) +
geom_line(aes(y = Theoretical, colour = "Theoretical(beta = 3.008"), size = 1L) +
theme_bw(base_size = 10) +
theme(text=element_text(family= "Times New Roman", face="bold"), plot.title = element_text(hjust = 0.5)) +
guides(colour = guide_legend(title="Legend")) +
scale_y_continuous(labels = scales::percent_format()) +
labs(title = "The frequency distribution of the scientific production") + xlab("Articles") + ylab("% of authors")
8.5 Author Impact
# Índice-H - Em elementos, colocar o nome do autor
indices <- Hindex(M, field = "author", elements="ADNER R", sep = ";", years = 10)
# Índice
indices$H## Author h_index g_index m_index TC NP PY_start
## 1 ADNER R 3 4 0.2727273 1061 4 2010# Citações do autor
indices$CitationList## [[1]]
## Authors Journal Year TotalCitation
## 1 ADNER R;FEILER D ORGANIZATION SCIENCE 2019 0
## 2 ADNER R;KAPOOR R STRATEGIC MANAGEMENT JOURNAL 2016 103
## 4 ADNER R JOURNAL OF MANAGEMENT 2017 175
## 3 ADNER R;KAPOOR R STRATEGIC MANAGEMENT JOURNAL 2010 783# Índice H para os top 10 autores
authors <- gsub(","," ",names(results$Authors)[1:10])
indices <- Hindex(M, field = "author", elements=authors, sep = ";", years = 50)
indicesH <- as.data.frame(indices$H)
indicesH <- transform(indicesH, Author = reorder(Author , h_index))
g12 <- indicesH %>% ggplot(aes(y = Author, weight = h_index, fill = h_index)) +
geom_bar(show.legend = F) +
scale_fill_continuous(low = "Lightblue", high = "Darkblue") +
scale_x_continuous(breaks = c(1,2,3,4,5,6)) +
theme_bw(base_size = 10) +
theme(text=element_text(family= "Times New Roman", face="bold"), plot.title = element_text(hjust = 0.5)) +
labs(title = "3c") + xlab("H Index") + ylab("Author")
g12
gridExtra::grid.arrange(g9 ,g8, g12, g10, ncol = 2, nrow = 2)
9 Most Relevant Affiliations
# 13 Most_Relevant_Affiliations #
Affiliations <- as.data.frame(results$Affiliations[1:22])
Affiliations <- Affiliations[-c(10,19),]
Affiliations <- transform(Affiliations, AFF = reorder(AFF , Freq))
Affiliations <- Affiliations %>% head(12)
Affiliations %>% ggplot(aes(y = AFF, weight = Freq, fill = Freq)) +
geom_bar(show.legend = F) +
scale_fill_continuous(low = "Lightblue", high = "Darkblue") +
scale_x_continuous(breaks = c(0,2,4,6,8,10,12,14,16,18)) +
theme_minimal() +
labs(title = "Most Relevant Affiliations") + xlab("Number of articles") + ylab("Affiliations")
10 Países
10.1 Most Productive Countries
MPC <- cbind(results$Countries, results$CountryCollaboration)
MPC <- transform(MPC, Tab = reorder(Tab, Freq))
MPC <- filter(MPC, Freq >= 10)
MPC %>% ggplot(aes(y = Tab, weight = Freq, fill = Freq)) +
geom_bar(show.legend = F) +
scale_fill_continuous(low = "Lightblue", high = "Darkblue") +
scale_x_continuous(breaks = c(0,10,20,30,40,50,60,70,80,90,100)) +
theme_bw(base_size = 10) +
theme(text=element_text(family= "Times New Roman", face="bold"), plot.title = element_text(hjust = 0.5)) +
labs(title = "Most Productive Countries") + xlab("Number of articles") + ylab("Country")
10.2 Most Cited Countries
MCC <- read.csv("C:/Users/user/Desktop/Vida acadêmica/Disciplinas/Economia da Inovação/Bibliometria/Tabelas 3/16 Most_Cited_Countries.csv")
MCC <- transform(MCC, Country = reorder(Country , Total.Citations))
MCC <- MCC %>% head(15)
MCC %>% ggplot(aes(y = Country, weight = Total.Citations, fill = Total.Citations)) +
geom_bar(show.legend = F) +
scale_fill_continuous(low = "Lightblue", high = "Darkblue") +
scale_x_continuous(breaks = c(0,300,600,900,1200,1500,1800,2100,2400)) +
theme_bw(base_size = 10) +
theme(text=element_text(family= "Times New Roman", face="bold"), plot.title = element_text(hjust = 0.5)) +
labs(title = "Most Cited Countries") + xlab("Number of citations") + ylab("Countries")
11 Article citations
11.1 Most global cited articles
# Top citações em artigos locais (dentro da base)
CR <- localCitations(M, sep = ";")##
## WOS DB:
## Searching local citations (LCS) by reference items (SR) and DOIs...
##
## Analyzing 27052 reference items...
##
## Found 23 documents with no empty Local Citations (LCS)CR$Papers[1:10,]## Paper DOI Year LCS GCS
## 15 ADNER R, 2010, STRATEGIC MANAGE J 10.1002/smj.821 2010 36 783
## 143 ADNER R, 2016, STRATEGIC MANAGE J 10.1002/smj.2363 2016 19 103
## 69 RITALA P, 2013, INT J TECHNOL MANAGE 10.1504/IJTM.2013.056900 2013 9 65
## 49 NAMBISAN S, 2013, ENTREP THEORY PRACT 10.1111/j.1540-6520.2012.00519.x 2013 7 169
## 88 GAWER A, 2014, RES POLICY 10.1016/j.respol.2014.03.006 2014 6 363
## 51 LETEN B, 2013, CALIF MANAGE REV 10.1525/cmr.2013.55.4.51 2013 5 40
## 62 ALEXY O, 2013, ACAD MANAGE REV 10.5465/amr.2011.0193 2013 4 154
## 76 STILL K, 2014, INT J TECHNOL MANAGE 10.1504/IJTM.2014.064606 2014 3 29
## 344 JARVI K, 2018, RES POLICY 10.1016/j.respol.2018.05.007 2018 3 12
## 352 DATTEE B, 2018, ACAD MANAGE J 10.5465/amj.2015.0869 2018 3 35CR$Papers[1:10,]$GCS## [1] 783 103 65 169 363 40 154 29 12 35MGCD <- read.csv("C:/Users/user/Desktop/Vida acadêmica/Disciplinas/Economia da Inovação/Bibliometria/Tabelas 3/17 Most_Global_Cited_Documents.csv")
str(MGCD)## 'data.frame': 20 obs. of 3 variables:
## $ Paper : chr "ADNER R, 2010, STRATEGIC MANAGE J" "SCHAFFERS H, 2011, LECT NOTES COMPUT SCI" "ADNER R, 2006, HARV BUS REV" "GAWER A, 2014, RES POLICY" ...
## $ Total.Citations: int 783 563 413 363 322 211 188 175 169 154 ...
## $ TC.per.Year : num 71.2 56.3 27.5 51.9 26.8 ...MGCD <- transform(MGCD, Paper = reorder(Paper, Total.Citations))
MGCD <- MGCD %>% head(15)
MGCD %>% ggplot(aes(y = Paper, weight = Total.Citations, fill = Total.Citations)) +
geom_bar(show.legend = F) +
scale_fill_continuous(low = "Lightblue", high = "Darkblue") +
scale_x_continuous(breaks = c(0,100,200,300,400,500,600,700)) +
theme_bw(base_size = 10) +
theme(text=element_text(family= "Times New Roman", face="bold"), plot.title = element_text(hjust = 0.5)) +
labs(title = "Most Cited Articles") + xlab("Number of citations") + ylab("Articles")
11.2 Most local cited documents
CR <- citations(M, field = "article", sep = ";")
cbind(CR$Cited[1:10]) # top 10 artigos mais citados localmente## [,1]
## ADNER R, 2010, STRATEGIC MANAGE J, V31, P306, DOI 10.1002/SMJ.821 36
## ADNER, R., KAPOOR, R., VALUE CREATION IN INNOVATION ECOSYSTEMS: HOW THE STRUCTURE OF TECHNOLOGICAL INTERDEPENDENCE AFFECTS FIRM PERFORMANCE IN NEW TECHNOLOGY GENERATIONS (2010) STRATEGIC MANAGEMENT JOURNAL, 31 (3), PP. 306-333 23
## MOORE JF, 1993, HARVARD BUS REV, V71, P75 20
## ADNER R, 2016, STRATEGIC MANAGE J, V37, P625, DOI 10.1002/SMJ.2363 19
## ADNER, R., MATCH YOUR INNOVATION STRATEGY TO YOUR INNOVATION ECOSYSTEM (2006) HARVARD BUSINESS REVIEW, 84 (4), PP. 98-107 19
## EISENHARDT KM, 1989, ACAD MANAGE REV, V14, P532, DOI 10.2307/258557 18
## IANSITI M, 2004, HARVARD BUS REV, V82, P68 17
## MOORE, J.F., PREDATORS AND PREY: A NEW ECOLOGY OF COMPETITION (1993) HARVARD BUSINESS REVIEW, 71 (3), PP. 75-86 17
## ADNER R, 2006, HARVARD BUS REV, V84, P98 16
## MOORE J. F., 1996, DEATH COMPETITION LE 15CR <- localCitations(M, sep = ";")##
## WOS DB:
## Searching local citations (LCS) by reference items (SR) and DOIs...
##
## Analyzing 27052 reference items...
##
## Found 23 documents with no empty Local Citations (LCS)MLCD <- as.data.frame(CR$Papers[1:10,])
MLCD <- transform(MLCD, Paper = reorder(Paper, LCS))
MLCD %>% ggplot(aes(y = Paper, weight = LCS, fill = LCS)) +
geom_bar(show.legend = F) +
scale_fill_continuous(low = "Lightblue", high = "Darkblue") +
scale_x_continuous(breaks = c(1,5,10,15,20,25,30,35,40)) +
theme_bw(base_size = 10) +
theme(text=element_text(family= "Times New Roman", face="bold"), plot.title = element_text(hjust = 0.5)) +
labs(title = "Most Local Cited Documents") + xlab("Local citations") + ylab("Documents")
11.3 Rank of dominance (Kumar e Kumar, 2008)
DF <- dominance(results, k = 10)
DF$DomFac <- DF$`Dominance Factor`
DF <- transform(DF, Author = reorder(Author, DomFac))
DF %>% ggplot(aes(y = Author, weight = DomFac, fill = DomFac)) +
geom_bar(show.legend = F) +
scale_fill_continuous(low = "Lightblue", high = "Darkblue") +
scale_x_continuous(breaks = c(0,0.25,0.50,0.75,1)) +
theme_bw(base_size = 10) +
theme(text=element_text(family= "Times New Roman", face="bold"), plot.title = element_text(hjust = 0.5)) +
labs(title = "Most Dominant Authors") + xlab("Dominance Factor") + ylab("Author")
12 Words
12.1 Most Frequent Words
MFW <- read.csv("C:/Users/user/Desktop/Vida acadêmica/Disciplinas/Economia da Inovação/Bibliometria/Tabelas 3/21 Most_Frequent_Words.csv")
str(MFW)## 'data.frame': 50 obs. of 2 variables:
## $ Words : chr "innovation ecosystem" "innovation" "ecosystem" "entrepreneurship" ...
## $ Occurrences: int 168 90 51 33 31 20 16 12 12 11 ...MFW$Words <- toupper(MFW$Words)
MFW <- transform(MFW, Words = reorder(Words, Occurrences))
MFW <- MFW %>% head(20)
g20 <- MFW %>% ggplot(aes(y = Words, weight = Occurrences, fill = Occurrences)) +
geom_bar(show.legend = F) +
scale_fill_continuous(low = "Lightblue", high = "Darkblue") +
scale_x_continuous(breaks = c(0,20,40,60,80,100,120,140,160,180)) +
theme_bw(base_size = 10) +
theme(text=element_text(family= "Times New Roman", face="bold"), plot.title = element_text(hjust = 0.5)) +
labs(title = "6a") + xlab("Occurrences") + ylab("Author Keywords")
g20
12.2 Word Cloud
library(tidytext)
palavras <- read.csv("C:/Users/user/Desktop/Vida acadêmica/Disciplinas/Economia da Inovação/Bibliometria/Tabelas 3/21 Most_Frequent_Words.csv", sep = ",")
library(RColorBrewer)
library(wordcloud)
library(wordcloud2)
set.seed(123)
wordcloud2(palavras, color = "random-dark",
backgroundColor = "white", minRotation = 0,
maxRotation = 0, minSize = 5, rotateRatio = 1,
shape = 'circle')palavras <- transform(palavras, Words = reorder(Words , Occurrences))
library(tidyverse)
library(ggsci)
ggplot(palavras, aes(y = Words, weight = Occurrences, fill = Occurrences)) +
geom_bar(show.legend = F) +
scale_fill_continuous(low = "Lightblue", high = "Darkblue") +
theme_bw(base_size = 10) +
theme(text=element_text(family= "Times New Roman", face="bold"), plot.title = element_text(hjust = 0.5))
12.3 Word Dynamics
WD <- read.csv("C:/Users/user/Desktop/Vida acadêmica/Disciplinas/Economia da Inovação/Bibliometria/Tabelas 3/22 Word_Dynamics.csv")
library(reshape2)
library(directlabels)
library(ggrepel)
WD <- melt(WD, id.vars = c("Year"))
str(WD)## 'data.frame': 160 obs. of 3 variables:
## $ Year : int 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 ...
## $ variable: Factor w/ 10 levels "INNOVATION.ECOSYSTEM",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ value : int 0 0 0 0 0 0 1 3 2 7 ...WD$value <- as.numeric(WD$value)
WD$Year <- as.numeric(WD$Year)
library(stringi)
WD$variable2 <- stri_replace_all(WD[,2], " ", fixed = ".")
g22 <- WD %>% ggplot(aes(y = value, x = Year, color = variable2)) +
geom_line() +
geom_point() +
scale_x_continuous(breaks = c(2004,2008,2012,2016,2019)) +
labs(title = "6b") + xlab("Year") + ylab("Anual Occurrences") +
guides(color = guide_legend(title = "Keyword")) +
theme_bw(base_size = 10) +
theme(text=element_text(family= "Times New Roman", face="bold"), plot.title = element_text(hjust = 0.5),
legend.title = element_text(color = "black", size = 12),
legend.text = element_text(color = "black", size = 8))
g22
gridExtra::grid.arrange(g20, g22, ncol = 2)
13 Topics
13.1 Thematic map
theme_set(theme_bw(base_size = 10))
MT <- thematicMap(M, field = "DE", n = 250, minfreq = 5, stemming = F, size = 0.2,
n.labels = 2, repel = TRUE)
MT$map
13.2 Thematic evolution
ET <- thematicEvolution(M, field = "DE", years = 2014, n = 500, minFreq = 10, size = 10,
stemming = T, n.labels = 1, repel = TRUE)
plotThematicEvolution(ET$Nodes,ET$Edges)13.3 MCA
CS <- conceptualStructure(M,field="DE", method="MCA",
minDegree = 9, clust = 3,
stemming=T,
labelsize = 8,
documents=15, graph = T)
13.4 Histography
histResults <- histNetwork(M, sep = ";")##
## WOS DB:
## Searching local citations (LCS) by reference items (SR) and DOIs...
##
## Analyzing 27052 reference items...
##
## Found 23 documents with no empty Local Citations (LCS)net <- histPlot(histResults, n = 20, size = 10, title_as_label = F)
##
## Legend
##
## Label DOI Year
## 1 ADNER R, 2010, STRATEGIC MANAGE J DOI 10.1002/SMJ.821 10.1002/smj.821 2010
## 2 NAMBISAN S, 2013, ENTREP THEORY PRACT DOI 10.1111/J.1540-6520.2012.00519.X 10.1111/j.1540-6520.2012.00519.x 2013
## 3 LETEN B, 2013, CALIF MANAGE REV DOI 10.1525/CMR.2013.55.4.51 10.1525/cmr.2013.55.4.51 2013
## 4 ALEXY O, 2013, ACAD MANAGE REV DOI 10.5465/AMR.2011.0193 10.5465/amr.2011.0193 2013
## 5 RITALA P, 2013, INT J TECHNOL MANAGE DOI 10.1504/IJTM.2013.056900 10.1504/IJTM.2013.056900 2013
## 6 STILL K, 2014, INT J TECHNOL MANAGE DOI 10.1504/IJTM.2014.064606 10.1504/IJTM.2014.064606 2014
## 7 GAWER A, 2014, RES POLICY DOI 10.1016/J.RESPOL.2014.03.006 10.1016/j.respol.2014.03.006 2014
## 8 RONG K, 2015, INT J PROD ECON DOI 10.1016/J.IJPE.2014.09.003 10.1016/j.ijpe.2014.09.003 2015
## 9 ADNER R, 2016, STRATEGIC MANAGE J DOI 10.1002/SMJ.2363 10.1002/smj.2363 2016
## 10 VISNJIC I, 2016, CALIF MANAGE REV DOI 10.1177/0008125616683955 10.1177/0008125616683955 2016
## 11 AMIT R, 2017, STRATEG ENTREP J DOI 10.1002/SEJ.1256 10.1002/sej.1256 2017
## 12 RITALA P, 2017, TECHNOVATION DOI 10.1016/J.TECHNOVATION.2017.01.004 10.1016/j.technovation.2017.01.004 2017
## 13 OZALP H, 2018, J MANAGE STUD DOI 10.1111/JOMS.12351 10.1111/joms.12351 2018
## 14 JARVI K, 2018, RES POLICY DOI 10.1016/J.RESPOL.2018.05.007 10.1016/j.respol.2018.05.007 2018
## 15 DATTEE B, 2018, ACAD MANAGE J DOI 10.5465/AMJ.2015.0869 10.5465/amj.2015.0869 2018
## LCS GCS
## 1 36 783
## 2 7 169
## 3 5 40
## 4 4 154
## 5 9 65
## 6 3 29
## 7 6 363
## 8 2 61
## 9 19 103
## 10 1 19
## 11 1 29
## 12 2 32
## 13 1 14
## 14 3 12
## 15 3 35