# Plot a word cloud
quanteda::textplot_wordcloud(
# Load the DFM object
mydfm,
# Define the minimum number the words have to occur
min_count = 3,
# Define the maximum number the words can occur
max_words = 500,
# Define a color
color = wes_palette("Darjeeling1")
)

# This code is heavily inspired by Julia Silge's blog post
# (https://juliasilge.com/blog/sherlock-holmes-stm/)

# This code is heavily inspired by this blog post:
# (https://www.mzes.uni-mannheim.de/socialsciencedatalab/article/advancing-text-mining/)

data %>%
# Generate the country name for each country using the 
# `countrycode()` command
dplyr::mutate(countryname = countrycode(ccode, "iso3c", "country.name")) %>%
# Filter and only select specific countries that we want to compare
dplyr::filter(countryname %in% c(
"Germany",
"France",
"United Kingdom",
"Norway",
"Spain",
"Sweden"
)) %>%
# Now comes the plotting part :-)
ggplot() +
# We do a bar plot that has the years on the x-axis and the level of the 
# net-sentiment on the y-axis
# We also color it so that all the net-sentiments greater 0 get a 
# different color
geom_col(aes(
x = year,
y = net_perc,
fill = (net_perc > 0)
)) +
# Here we define the colors as well as the labels and title of the legend
scale_fill_manual(
name = "Sentiment",
labels = c("Negative", "Positive"),
values = c("#C93312", "#446455")
) +
# Now we add the axes labels
xlab("Time") +
ylab("Net sentiment") +
# And do a facet_wrap by country to get a more meaningful visualization
facet_wrap(~ countryname)

# Inspired here: https://bit.ly/37MCEHg
# Get the 30 top features from the DFM
freq_feature <- topfeatures(mydfm, 30)
# Create a data.frame for ggplot
data <- data.frame(list(
term = names(freq_feature),
frequency = unname(freq_feature)
))
# Plot the plot
data %>%
# Call ggplot
ggplot() +
# Add geom_segment (this will give us the lines of the lollipops)
geom_segment(aes(
x = reorder(term, frequency),
xend = reorder(term, frequency),
y = 0,
yend = frequency
), color = "grey") +
# Call a point plot with the terms on the x-axis 
# and the frequency on the y-axis
geom_point(aes(x = reorder(term, frequency), y = frequency)) +
# Flip the plot
coord_flip() +
# Add labels for the axes
xlab("") +
ylab("Absolute frequency of the features")

data %>%
# Generate the continent for each country using the `countrycode()` command
dplyr::mutate(continent = countrycode(ccode, "iso3c", "continent",
custom_match = c("YUG" = "Europe"))) %>%
# We group by continent and year to generate the average sentiment by 
# continent and and year 
group_by(continent, year) %>%
dplyr::mutate(avg = mean(net_perc)) %>%
# We now plot it
ggplot() +
# Using a line chart with year on the x-axis, the average sentiment 
# by continent on the y-axis and colored by continent
geom_line(aes(x = year, y = avg, col = continent)) +
# Define the colors
scale_color_manual(name = "", values = wes_palette("Darjeeling1")) +
# Label the axes
xlab("Time") +
ylab("Average net sentiment")