It creates an Evolution thematic map based on co-word network analysis and clustering. The methodology is inspired by the proposal of Cobo et al. (2011).
thematicEvolution(..., weighted = FALSE)
is a sequence of names of thematic maps created by thematicMap
function.
is a logical. If FALSE, a thematic nexus is measures by the classical inclusion index (calculated using the number of keywords). If TRUE, the inclusion index is calculated considering the occurrences of keywords.
a list containing:
nets |
The thematic nexus graph for each comparison |
thematicEvolution
starts from two or more thematic maps created by thematicMap
function.
thematicMap
function to create a thematic map based on co-word network analysis and clustering.
cocMatrix
to compute a bibliographic bipartite network.
networkPlot
to plot a bibliographic network.
# NOT RUN {
data(scientometrics)
years=c(2000)
list_df=timeslice(scientometrics, breaks = years)
M1=list_df[[1]]
M2=list_df[[2]]
NetMatrix1 <- biblioNetwork(M1, analysis = "co-occurrences",
network = "keywords", sep = ";")
S1 <- normalizeSimilarity(NetMatrix1, type = "association")
net1 <- networkPlot(S1, n = 50, Title = "co-occurrence network",type="fruchterman",
labelsize = 0.7, halo = FALSE, cluster = "walktrap",remove.isolates=FALSE,
remove.multiple=FALSE, noloops=TRUE, weighted=TRUE)
res1 <- thematicMap(net1, NetMatrix1, S1)
#plot(res1$map)
NetMatrix2 <- biblioNetwork(M2, analysis = "co-occurrences",
network = "keywords", sep = ";")
S2 <- normalizeSimilarity(NetMatrix2, type = "association")
net2 <- networkPlot(S2, n = 50, Title = "co-occurrence network",type="fruchterman",
labelsize = 0.7, halo = FALSE, cluster = "walktrap",remove.isolates=FALSE,
remove.multiple=FALSE, noloops=TRUE, weighted=TRUE)
res2 <- thematicMap(net2, NetMatrix2, S2)
#plot(res2$map)
nexus <- thematicEvolution(res1,res2,weighted=FALSE)
# }
Run the code above in your browser using DataLab