The musical, Hamilton, has many emotions throughout, focusing on war, revolution, love, time, and betrayal. Created by Lin-Manuel Miranda, the musical intertwines the life of Alexander Hamilton, one of America’s Founding Fathers, with a diverse cast that brings historical figures to life through a unique blend of hip-hop, R&B, and traditional show tunes; the narrative unfolds in a way that highlights not only Hamilton’s rise from humble beginnings as an orphan in the Caribbean but also his pivotal role in shaping the nation’s financial systems and political landscape during the Revolutionary War and the early years of the United States. In Act I, Hamilton rises from his humble beginnings to become a key figure in the American Revolution, driven by ambition and determination. In Act II, he faces personal and political challenges as his ambition leads to conflict, scandals, and his downfall. From this, we can hypothesize that Act I will reflect a more positive sentiment, as well as the female characters, compared to the male.
This project will test this hypothesis through sentiment analysis of the musical’s lyrics, exploring average sentiment scores of individual songs, acts, and characters, with particular attention to gender differences and emotional shifts across the narrative. It will also look into the words “Alexander Hamilton,” showing the connection between characters and more about him.
The project begins by loading necessary packages, tokenizing the lyrics, filtering out common stop words, and counting word frequencies to identify prominent themes.
# A tibble: 2,464 × 2
word n
<chr> <int>
1 da 89
2 wait 81
3 time 77
4 hamilton 75
5 hey 69
6 burr 63
7 shot 58
8 sir 56
9 alexander 50
10 whoa 42
# ℹ 2,454 more rows
Being a musical, there are a lot of words that do not contribute to the meaning of the show, or overall sentiment. Once musical words were taken out, I created a word cloud using the top 180 words.
Here, we can see our hypothesis is proven true. With the average sentiment of Act I being higher than Act II. Looking at the songs that showed the highest and lowest sentiment, I was curious as to what words dragged that so much.
In “Best of Wives and Best of Women,” Eliza expresses her love and support for Alexander Hamilton as they face personal and political challenges, capturing the depth of their relationship and her unwavering strength. “Hurricane” portrays Hamilton’s introspective moment as he reflects on his tumultuous life and the consequences of his choices, blending themes of regret and determination with a sense of urgency.
Code
ham_sentiment |>summarise(title, speaker, value, word) |>filter(title %in%"Best of Wives and Best of Women") |>ggplot(aes(word, value, fill = value)) +geom_col() +coord_flip() +labs(title ="Words with Sentiment Value \n in 'Best Of Wives and Best of Women'",y ="Value",x =NULL) +theme(legend.position ="none") -> word_bestofwivesggplotly(word_bestofwives)ham_sentiment |>summarise(title, speaker, value, word) |>filter(title %in%"Hurricane") |>ggplot(aes(word, value, fill = value)) +geom_col() +coord_flip() +labs(title ="Words with Sentiment Value \n in 'Hurricane'",y ="Value",x =NULL) +theme(legend.position ="none") -> word_hurricaneggplotly(word_hurricane)
The positive words surround the theme of love and caring, while the negative words focus on death and destruction.
Sentiment by Character and Gender
From here, we can look at each character in the show to see who speaks more positively, and negatively. I broke the characters by gender, Male, Female, and Mixed (for the ensemble).
Here, it is interesting to see how many characters have an overall positive sentiment, and how the two most negative speakers are females. Even though this is true, looking at the gender average, the positive females make up for “WOMEN” and “PEGGY.”
I wanted to then take a closer look at the Principle Characters in the show using ggplot mapping to compare the characters to each other. In the code below, I find the standard error of each character’s sentiment score by taking the standard deviation and diving it by the number of times they speak - this gives a sense of the variability in sentiment for each speaker.
The Schuyler sisters—Angelica, Eliza, and Peggy—are central characters in “Hamilton,” each representing distinct traits and strengths. Angelica is witty and fiercely intelligent, serving as a confidante to both her sisters and Hamilton, while Eliza embodies warmth and loyalty, ultimately becoming Hamilton’s devoted wife. Peggy, the youngest, is less developed compared to her sisters. In the chart, we can see that out of the principle characters, Angelica (in pink) speaks the most positive, while Peggy (in yellow) is the most negative.
Code
ham_sentiment |>filter(speaker %in%"ANGELICA") |>ggplot(aes(reorder(word, value), value, fill = value, text =paste("word:", word, "<br>","value:", value))) +geom_col() +coord_flip() +labs(title ="Words with Sentiment Value \n Spoken by Angelica",y ="Value",x =NULL) -> word_angelicaggplotly(word_angelica, tooltip ="text", height =650)ham_sentiment |>filter(speaker %in%"PEGGY") |>ggplot(aes(reorder(word, value), value, fill = value,text =paste("word:", word, "<br>","value:", value))) +geom_col() +coord_flip() +labs(title ="Words with Sentiment Value \n Spoken by Peggy",y ="Value",x =NULL) -> word_peggyggplotly(word_peggy, tooltip ="text")
Peggy’s negative average is brought down heavily by three words of “bad,” “violence,” and “war.” She does not speak a lot, which makes the words she does say impact heavily when calculating this sentiment. Looking at Angelica, who stays alive and active throughout the whole show, her words are more dispersed. Angelica speakers highly when saying words such as “win,” “fun,” “praise,” “happy,” “rich,” “freedom,” and satisfied.” She is more negative when saying words like “leave,” “suffering,” “regret,” and “hunger.”
Alexander Hamilton
Alexander Hamilton is the focus of this production, although most of the musical is narrated by Aaron Burr. I wanted to focus on the phrase and name, Alexander Hamilton, to see different observations.
I began by creating bigrams, to get the phrase “Alexander Hamilton” together and to see the words that came before and after “Hamilton.”
bigrams_filtered |>filter(word1 =="alexander", word2 =="hamilton") |>count(speaker, sort =TRUE) |>ggplot(aes(speaker,n, fill = n, text =paste("character:", speaker, "<br>","number:", n))) +geom_col() +labs(title ="People who say 'Alexander Hamilton'", x ="Speaker", y ="Number of Times Said") -> alexander_hamggplotly(alexander_ham, tooltip ="text")
Looking at the count of the phrase “Alexander Hamilton,” we can see different characters’ relationships with him. It is interesting to see that no principle in the production ever says his full name. The repetition also symbolizes how central he is to the story.
This next sections analyze the words that appear before and after “Hamilton.” These can give clues about what qualities or actions are most associated with him:
# A tibble: 12 × 3
word1 speaker n
<chr> <chr> <int>
1 alexander COMPANY 8
2 alexander HAMILTON 6
3 alexander JEFFERSON 2
4 alexander WASHINGTON 2
5 secretary WASHINGTON 2
6 alexander BURR 1
7 fires BURR 1
8 hires BURR 1
9 monsieur LAFAYETTE 1
10 recess WASHINGTON 1
11 walk WASHINGTON 1
12 watched BURR 1
# A tibble: 10 × 3
word2 speaker n
<chr> <chr> <int>
1 arrived BURR 1
2 drew BURR 1
3 examine BURR 1
4 forgets JEFFERSON 1
5 ha MEN & WOMEN 1
6 john ENSEMBLE 1
7 publishes BURR 1
8 sit BURR 1
9 sits JEFFERSON 1
10 wrote BURR 1
We can see from this count event more about the relationships between Hamilton and others. The words before “Hamilton” tell you about his role as secretary. Burr saying “fires” and “hires” suggest moments where Hamilton is taking signification actions, such as hiring or firing individuals. These words indicate pivotal moments where Hamilton’s decisions have serious implications for those around him, further fueling Burr’s anger.
Looking at the works after “Hamilton” show the actions associated with him and how other characters describe him. Burr mentions that Hamilton “arrived,” “drew,” “publishes,” “sit,” and “examine,” reflecting Hamilton’s decisive actions in pivotal moments like the duel, his public disclosures, and his contemplative nature, often narrated by Burr with a sense of rivalry and impending doom. Jefferson says Hamilton “forgets” and “sits,” which may reflect his criticism of Hamilton’s political approach, implying that Hamilton overlooks important values. The ensemble collectively says “ha,” which could be a reaction to a particularly dramatic or emotional moment involving Hamilton, possibly underscoring the tension or humor in a scene.
Conclusion
When looking at the words in Hamilton, you can pick apart each song and character to determine the sentiment of each. Taking a look at the hypothesis, it was shown to be true - Act I sentiment is higher than Act II, and female characters, on average, were more positive than the males. Throughout, it was interesting to see which words stood out. The positive and negative words that stood out are the ones that encapsulate the themes of the musical. There is love, hatred, desire, death, and war, happening in almost every scene, which can be seen through the graphs. The word frequency analysis highlights key phrases and sentiments expressed by characters like Angelica and Peggy, while the bigram analysis shows that “Alexander Hamilton” is frequently referenced, underscoring his central role. Overall, these findings illuminate the emotional landscape of the musical, the distinct voices of its characters, and the interplay between gender and sentiment throughout the narrative.
The Schuyler sisters—Angelica, Eliza, and Peggy—are central characters in “Hamilton,” each representing distinct traits and strengths. Angelica is witty and fiercely intelligent, serving as a confidante to both her sisters and Hamilton, while Eliza embodies warmth and loyalty, ultimately becoming Hamilton’s devoted wife. Peggy, the youngest, is less developed compared to her sisters. In the chart, we can see that out of the principle characters, Angelica (in pink) speaks the most positive, while Peggy (in yellow) is the most negative.