# A tibble: 1 × 4
movie_count mean_popularity mean_vote_count mean_vote_average
<int> <dbl> <dbl> <dbl>
1 9827 40.3 1393. 6.44Final Project - The Hunger Games Movie Analysis
1 - Area of Interest: The Hunger Games Movies
1.1
The area of interest I am going to be studying is The Hunger Games Movie. Suzanne Collins, the author of the book series that the movies are based on recently, in 2020, released a prequel of the original book trilogy that was released 2008-10. The movie that accompanied the prequel was just released, and this has caused me to re-watch all of the old movies.
The questions I am looking to analyze which movies in the series are most liked and if a sentiment analysis of some reviews would reflect this. I am also very curious about how the new movie has been received because it was released so much later than the original trilogy.
1.2
The first dataset I am using is a Kaggle Movies data set that pulled popular movie data from The Movie Data Base (TMDB). I am interested in comparing The Hunger Games Movies to one another as well as other movies.
link: https://www.kaggle.com/datasets/disham993/9000-movies-dataset/data
1.3
Data Dictionary:
Release_Date: Date when the movie was released.Title: Name of the movie.Overview: Brief summary of the movie.Popularity: It is a very important metric computed by TMDB developers based on the number of views per day, votes per day, number of users marked it as “favorite” and “watchlist” for the data, release date and more other metrics.Vote_Count: Total votes received from the viewers.Vote_Average: Average rating based on vote count and the number of viewers out of 10.Original_Language: Original language of the movies. Dubbed version is not considered to be original language.Genre: Categories the movie it can be classified as.Poster_Url: Url of the movie poster.
2 - Descriptive Analysis
First, I want to get an overall understanding of the data we are working with by doing a few summary statistics:
Compare Hunger Games Movies to Each Other
Popularity:
First, I want to test the overall popularity of only the Hunger Games books. In order to do this I am going to create a barplot that shows the different movies and their popularity score:
Interpretation:
As you can see from the barplots, The Hunger Games: Mockingjay - Part 1 has a much higher popularity compared to the other movies. I think this is very interesting because you would expect Mockingjay Part 1 and 2 to have similar popularity scores. The first Hunger Games movie has the lowest. Compared to the average popularity score of the data set (from summary table: 40.33), all movies are well above the popularity average compared to the rest of the dataset.
Vote Average:
Next, I want to test the overall popularity of only the Hunger Games books. In order to do this I am going to create a barplot that shows the different movies and their vote average (the voting is 1-10) :
Interpretation:
As you can see from the vote total barplot, all movies have over the average total votes (1392.81) so they should be pretty accurate due to the high amount of votes.
As you can see from the vote average barplot, The Hunger Games: Catching Fire (the second movie) has the highest voting average at a 7.4/10. The Hunger Games is next with a 7.2/10. Both Mockingjays are next with part 2 at 6.9/10 and part 1 at a 6.8/10. I find it very interesting that the movie with the highest popularity score, has the lowest vote rating average. Compared to the overall dataset (from summary table: 6.44), all movies are just above the voting average.
Compare Hunger Games Movies to Other Movies in Dataset
Genres:
First, I want to analyze the genres that each movie fits under, see if they differ, and compare it to other movies with similar genres.
# A tibble: 4 × 2
Title Genre
<chr> <chr>
1 The Hunger Games: Mockingjay - Part 1 Science Fiction, Adventure, Thriller
2 The Hunger Games: Mockingjay - Part 2 Action, Adventure, Science Fiction
3 The Hunger Games: Catching Fire Adventure, Action, Science Fiction
4 The Hunger Games Science Fiction, Adventure, Fantasy 
Interpretation:
From the table, we can see that all of the Hunger Games movies have science fiction as a genre (a few other common ones like action, adventure). I created a boxplot that shows the voting average (1/10) based on the genre. All of the genre voting averages look pretty similar around the voting averages for The Hunger Games movies shown earlier. The movies are voted pretty averagely in the categories they are in.
Divergent:
Another very similar dystopian book turned to movie series that came out around the same time as The Hunger Games, is the Divergent Series. I want to compare the movies to one another:
Interpretation:
From the barplots, you can see that the first movie in the Divergent series (Divergent) is voted higher than the first movie of the hunger games series (The Hunger Games). In the Divergent series, the ratings seem to decrease as the movies go on, whereas for The Hunger Games, some of the later movies have higher popularity than the movies just prior to it. This is interesting because there was a fourth Divergent series book that was never made into a movie because the last movie released (Allegiant) did not do as well as anticipated. The Hunger Games on the other hand just released a new movie based on the last book released.
3 - Secondary Data Source
3.1
The second dataset I am using is a The Hunger Games Movies user reviews on IMDb. I am interested in seeing how movie watchers feel about all of The Hunger Games movies and compare them to one another using a sentiment score analysis by using the NRC lexicon.
I also created a visualization of just the original hunger games movies (not including “The Ballad of Songbirds & Snakes”):
Interpretation:
As you can see in the bar graph, the 5 movies appear in a row with each of their sentiment scores and the top words that appear in the reviews:
When comparing movie 1 (The Hunger Games) and movie 2 (Catching Fire), book 2 has many more positive words with higher sentiment scores compared to movie 1. In movie 1, there is a lot of emphasis on killing and violence, where as in movie 2 there seems to be more focus on love and excellence. It seems like those reviewing movie 1 were much more focused on the sad and negative parts of the film where in movie 2, there is more of a positive, joyful, and trusting focus. This would make sense because Catching Fire had a slightly higher average vote rating than The Hunger Games.
When looking at Mocking Jay part 1 vs part 2: Part 1 looks like it has much higher sentiment scores on sentiments like ‘fearful’, ‘negative’, and ‘disgust’ and Part 2 seems to have much higher sentiments scores on sentiments like ‘positive’. This would make sense because Mocking Jay Part 2 had a slightly higher average vote rating than Part 1.
In the The Ballad of Songbirds & Snakes, it seems like there is a major emphasis on the word bad, which leads me to believe these reviews were not very impressed by the prequel compared to the other movies. As the movie progress, it seems that the reviewers seem less and less impressed based on positivity and negativity sentiment. It would have been interesting to be able to compare the average vote rating for this movie compared to the original movies, but it unfortunately was not in the Kaggle dataset (the movie was released last month).