Report 5

############################################################
# STEP 1: Install and Load Packages
############################################################
if (!require("tidyverse")) install.packages("tidyverse")
if (!require("httr2")) install.packages("httr2")
if (!require("lubridate")) install.packages("lubridate")
if (!require("kableExtra")) install.packages("kableExtra")
if (!require("plotly")) install.packages("plotly")
library(tidyverse)
library(httr2)
library(lubridate)
library(kableExtra)
library(plotly)

############################################################
# STEP 2: Verify Media Cloud API Key
############################################################
if (!nzchar(Sys.getenv("MEDIACLOUD_KEY"))) {
  stop(
    "No Media Cloud API key was found.\n",
    "Please save your key to .Renviron first."
  )
}

############################################################
# STEP 3: Define Two Topics
############################################################
topics <- c(
  "Artificial Intelligence" = "\"artificial intelligence\"",
  "Climate Change" = "\"climate change\""
)

############################################################
# STEP 4: Define the Date Range
############################################################
start_date <- "2026-01-01"
end_date <- "2026-09-01"

############################################################
# STEP 5: Create a Function to Download Daily Story Counts
############################################################
get_counts <- function(query) {
  Sys.sleep(35)
  response <-
    request("https://search.mediacloud.org/api/search/count-over-time") |>
    req_headers(Authorization = paste("Token", Sys.getenv("MEDIACLOUD_KEY"))) |>
    req_url_query(
      q = query,
      start = start_date,
      end = end_date,
      platform = "onlinenews-mediacloud",
      cs = 34412234
    ) |>
    req_perform()
  results <- response |> resp_body_json()
  map_dfr(results$count_over_time$counts, as_tibble) |>
    mutate(date = as.Date(date))
}

############################################################
# STEP 6: Download Data for Both Topics
############################################################
topic_data <-
  imap_dfr(topics, function(search_query, topic_name) {
    message("Downloading: ", topic_name)
    get_counts(search_query) |> mutate(topic = topic_name)
  })

############################################################
# STEP 7: Examine the Downloaded Data
############################################################
head(topic_data)
glimpse(topic_data)

############################################################
# STEP 8: Calculate Weekly Story Counts
############################################################
weekly_counts <-
  topic_data |>
  mutate(week = floor_date(date, unit = "week")) |>
  group_by(topic, week) |>
  summarise(stories = sum(count), .groups = "drop")

############################################################
# STEP 9: Display Weekly Counts
############################################################
weekly_counts |>
  arrange(topic, week) |>
  kbl(caption = "Weekly Media Cloud Story Counts") |>
  kable_styling(full_width = FALSE, bootstrap_options = c("striped", "hover"))

############################################################
# STEP 10: Summarize Total Coverage
############################################################
topic_summary <-
  weekly_counts |>
  group_by(topic) |>
  summarise(
    Total_Stories = sum(stories),
    Weekly_Minimum = min(stories),
    Weekly_Maximum = max(stories),
    Weekly_Mean = round(mean(stories), 2),
    .groups = "drop"
  ) |>
  arrange(desc(Total_Stories))

Summary_Table <- topic_summary |>
  kbl(caption = "Coverage Summary by Topic") |>
  kable_styling(full_width = FALSE, bootstrap_options = c("striped", "hover"))
Summary_Table

############################################################
# STEP 11: Create a Line Graph
############################################################
Line_Graph <- weekly_counts |>
  ggplot(aes(x = week, y = stories, color = topic)) +
  geom_line(linewidth = 1) +
  geom_point(size = 2) +
  labs(
    title = "Weekly Media Coverage Volume",
    subtitle = "Comparison of Two Topics",
    x = "Week",
    y = "Number of Stories",
    color = "Topic"
  ) +
  theme_minimal()
Line_Graph

############################################################
# STEP 12: Save Results as a CSV File
############################################################
write_csv(weekly_counts, "weekly_story_counts.csv")
############################################################
# STEP 13: Create an Interactive plotly Line Graph
############################################################

Plotly_Line <- weekly_counts |>
  filter(
    week >= as.Date(start_date),
    week + 6 <= as.Date(end_date)
  ) |>
  plot_ly(
    x = ~week,
    y = ~stories,
    color = ~topic,
    colors = "Set1",
    type = "scatter",
    mode = "lines+markers",
    hovertemplate = paste0(
      "<b>%{fullData.name}</b><br>",
      "Stories: %{y:,}<br>",
      "Week of: %{x|%b %d, %Y}",
      "<extra></extra>"
    )
  ) |>
  layout(
    title = "Weekly Media Coverage Volume",
    hovermode = "x unified",
    xaxis = list(title = "Week"),
    yaxis = list(title = "Number of Stories", tickformat = ","),
    legend = list(title = list(text = "Topic")),
    margin = list(t = 80)
  )

Plotly_Line