Sentiment Analysis

Questions

How do the reviews to each movie compare to each other? What sort of things were people saying about each movie? How to people fell about the movie as time passed?

Data

Using review data scraped from IMDB on the movies Barbie and Oppenheimer.

# A tibble: 2,878 × 3
# Groups:   movie [2]
   movie       word            n
   <chr>       <chr>       <int>
 1 Barbie      movie          76
 2 Oppenheimer oppenheimer    73
 3 Oppenheimer movie          70
 4 Barbie      barbie         64
 5 Oppenheimer film           53
 6 Barbie      helpful        50
 7 Oppenheimer helpful        50
 8 Oppenheimer nolan          45
 9 Barbie      film           34
10 Oppenheimer time           32
# ℹ 2,868 more rows

Sentiment of Movies

# A tibble: 4 × 3
# Groups:   movie [2]
  movie       sentiment     n
  <chr>       <chr>     <int>
1 Oppenheimer negative    167
2 Oppenheimer positive    164
3 Barbie      negative    135
4 Barbie      positive    120

Both movies seemed to have a negative sentiment. This is really interesting because they were both highly anticipated movies with star stubbed casts and world class directors. Barbie has a slightly higher ratio of negative reviews.

What was being said about each movie?

From what the reviews say, we can get an idea of what each movie did well. Oppenheimer seems to be a more artistic movie, where people admire the work. Words like “brilliant”, “amazing”, and “masterpiece” were used to describe the movie. Whereas Barbie seems to be a more fun and enjoyable movie. Words like “fun”, “humor”, and “creative” were used to describe it. We can also see what people did not like about them. Oppenheimer seemed to bit too intense and confusing for people. Some people thought Barbie was stereotypical and not well written.

As time went on, different effects happened to the movies. Oppenheimer started extremely high, but as time goes on and the movies has been out longer, the reviews get worse and worse until the positivity scores are negative. Barbie on the other hand, didn’t start out nearly as strong as Oppenheimer, but it’s high ratings stayed somewhat consistent. Time overall had a worse effect on Oppenheimer.

Conslusion

Both movies were great movies by great directors. However, both movies were loved for different reasons. They were clearly made for two different demographics and should be held to two different standards. While Oppenheimer seemed initially incredible, as more time passed, the public opinion seemed to shift.

--- title: "Sentiment Analysis" toc: true format: html: html-math-method: katex code-tools: TRUE self-contained: TRUE execute: warning: FALSE message: FALSE echo: FALSE --- ```{r} library(tidyverse) library(tidyverse) library(lubridate) library(tidytext) library(textdata) ``` ```{r} movies <- read_csv("https://myxavier-my.sharepoint.com/:x:/g/personal/welchd3_xavier_edu/EQ-J9ULYojpCujoav94RBBcBqROjnH8Jqz0gXqGIPKH9-Q?download=1") ``` ## Questions How do the reviews to each movie compare to each other? What sort of things were people saying about each movie? How to people fell about the movie as time passed? ## Data Using review data scraped from IMDB on the movies Barbie and Oppenheimer. ```{r} movies <- movies %>% mutate(review_id = row_number()) movies$date <- as.Date(strptime(movies$date, format = "%d %B %Y")) movies <- movies[order(movies$date), ] tidy_movies <- movies %>% unnest_tokens(word, review) %>% anti_join(stop_words) ``` ```{r} tidy_movies %>% group_by(movie, word) %>% summarize(n = n()) %>% arrange(-n) ``` ```{r} bing <- get_sentiments("bing") movies_counts <- tidy_movies %>% group_by(movie, word) %>% summarize(n = n()) %>% inner_join(bing) ``` ## Sentiment of Movies ```{r} movies_counts %>% group_by(movie,sentiment) %>% summarize(n = n()) %>% arrange(-n) ``` Both movies seemed to have a negative sentiment. This is really interesting because they were both highly anticipated movies with star stubbed casts and world class directors. Barbie has a slightly higher ratio of negative reviews. ## What was being said about each movie? ```{r} movies_counts %>% group_by(movie) %>% filter(n>3) %>% mutate(n = ifelse(sentiment == "negative", -n, n)) %>% mutate(word = reorder(word, n)) %>% ggplot(aes(word, n)) + geom_col() + coord_flip() + facet_wrap(~movie, ncol = 2) + geom_text(aes(label = signif(n, digits = 3)), nudge_y = 8) + labs(title = "Positive and Negative Words for Barbie and Oppenheimer", subtitle = "Only words appearing at least 5 times are shown") ``` From what the reviews say, we can get an idea of what each movie did well. Oppenheimer seems to be a more artistic movie, where people admire the work. Words like "brilliant", "amazing", and "masterpiece" were used to describe the movie. Whereas Barbie seems to be a more fun and enjoyable movie. Words like "fun", "humor", and "creative" were used to describe it. We can also see what people did not like about them. Oppenheimer seemed to bit too intense and confusing for people. Some people thought Barbie was stereotypical and not well written. ```{r} tidy_movies %>% filter(review_id != 49) %>% inner_join(bing) %>% group_by(movie, date, sentiment) %>% summarize(n = n()) %>% spread(sentiment, n, fill = 0) %>% mutate(sentiment = positive - negative) %>% ggplot(aes(x = date, y = sentiment, fill = movie)) + geom_col(position = "dodge") + scale_fill_manual(values = c("#c08206","#00263e")) + labs(title = "Brewery Positivity Scores by Date", subtitle = "Positivity score is the total number of positive words minus total negative words", y = "Total Positivity Score", x = "Date", fill = "Movie")+ theme(axis.text.x = element_text(angle = 45, hjust = 1)) ``` As time went on, different effects happened to the movies. Oppenheimer started extremely high, but as time goes on and the movies has been out longer, the reviews get worse and worse until the positivity scores are negative. Barbie on the other hand, didn't start out nearly as strong as Oppenheimer, but it's high ratings stayed somewhat consistent. Time overall had a worse effect on Oppenheimer. ## Conslusion Both movies were great movies by great directors. However, both movies were loved for different reasons. They were clearly made for two different demographics and should be held to two different standards. While Oppenheimer seemed initially incredible, as more time passed, the public opinion seemed to shift.