Pandemic Data

---

1. Importing

covid_data <- read.csv("figure-data.csv", stringsAsFactors = FALSE)

colnames(covid_data) <- c("Date", "Social_Media", "Twitter", "Big_Data", 
                          "Google_Trend", "Facebook", "Cell_Phone", "Call_Detail_Records")

head(covid_data)

---

2. Summary table

totals_summary <- covid_data %>%
  summarize(
    Social_Media = max(Social_Media, na.rm = TRUE),
    Twitter = max(Twitter, na.rm = TRUE),
    Big_Data = max(Big_Data, na.rm = TRUE),
    Google_Trend = max(Google_Trend, na.rm = TRUE),
    Facebook = max(Facebook, na.rm = TRUE),
    Cell_Phone = max(Cell_Phone, na.rm = TRUE)
  )

print(totals_summary)

##   Social_Media Twitter Big_Data Google_Trend Facebook Cell_Phone
## 1          530     206      129           78       72         20

---

3. Thoughts

Social Media more generally was cited most in pandemic related research articles.

---

4. Chart for ya moneyyyy

plot_data <- data.frame(
  Source = c("Social Media", "Twitter", "Big Data", "Google Trend", "Facebook", "Cell Phone"),
  Total_Articles = c(
    max(covid_data$Social_Media, na.rm = TRUE),
    max(covid_data$Twitter, na.rm = TRUE),
    max(covid_data$Big_Data, na.rm = TRUE),
    max(covid_data$Google_Trend, na.rm = TRUE),
    max(covid_data$Facebook, na.rm = TRUE),
    max(covid_data$Cell_Phone, na.rm = TRUE)
  )
)

p <- ggplot(data = plot_data, aes(x = reorder(Source, -Total_Articles), y = Total_Articles, fill = Source)) +
  geom_col(show.legend = FALSE) +
  geom_text(aes(label = Total_Articles), vjust = -0.5, size = 3.5) +
  scale_fill_brewer(palette = "Set2") +
  labs(
    title = "COVID-19 Articles by Source (Feb–Sep 2020)",
    x = "Source",
    y = "Published Articles"
  ) +
  theme_minimal() +
  theme(panel.grid.major.x = element_blank())

print(p)