Info 2201

The main question is that the most common words in movies sorted by different genres are the same or not? Is there a certain word that appears repeatedly in movie script?

For the animation, Coco and Toy story do not have many meaningful words in the script. However, on the speed racer, the character names appear frequently. On the Toy Story, they use many mood words such oh, no. I predict that in this movie, they have more arguments among the main characters, and they tried to convince each other. That’s why it has more mood words than the other two movies. From the top 15 words, I also can see the main topic of the film, what does the film mainly talk about. Speed Racer talks about race and car, toy story talks about the toy, especially about clockwork spring or remote-controlled toy, and coco talks about family. But overall, from the animation movie, the scripts are not quite the same. They still have some differences based on different core story they showed in the film.

For the action and crime movies’ script, the most common words seem related to the character names on the film, such as Joe, Lee, Isabella. For the three films, only some character pronouns frequently appear, such as I’m, we. The gateway doesn’t have any meaningful words in top 15 common words. Therefore, in this genre, I rarely saw some strong relationship among those films. But in Rush Hour 2, the characters have more roles than the others. There seems to be nothing in common except character names.

For this genre, horror movies, the pronouns also appear the most frequently compared to other types of words. However, I can’t see there have some other relationships among those movies. These three movie scripts seem not very related even they belong to the same genre.

Based on these analyses, I expected that it should be some words that appear very often, such as love, family in animation; run, come in horror movie; go, dead in action and crime movie. Because these words are matched the theme of the movie, and I usually heard them in the film. I am surprised that there are no certain words that I imagined appeared repeatedly. In contrast, pronouns and some other meaningless words are the most common type of words in the movie. I think it might cause by genre of film. Inaction and crime movies, it might be more emphasis on action or crime. I also looked up the different films come from the same source, to see if there are some relationship, but still, the finding is too inaccurate or have biased when the commonalities are not visible. In conclusion, I will say there might not have a relationship in a different movie because they are independent, and shot by various directors, and screenwriters’ preferences might include various too.

My full code is showing below.

Info 1201

In my final project, my overall question is what words are singer usually used? For the rappers, are they use more similar words because of rhythm, and more substantial lyrics than other singers? Are positive words being more similar or negative words? The reason why I chose this topic is that I heard a lot of hip-hop songs and I noticed they usually use same words for rhythm, and the lyrics are generally larger than other types of songs such as pop, so they don’t have variety words to use. Therefore, I want to check is the hip-pop singers usually use the same words or not, or all type of singers use the same words, such as like and love.

As a result, it’s has a bit discrepancy from what I am expected. In general, the words of singer using is similar if the words that appear most frequently. The same type of singers usually uses the same words. However, there are certain defects in my project, such as the number of samples is unusually small because I don’t have that much data set. In the future, I want to get the data set by using because using other people’s data might result in some unnecessary problems, such as the locations of lyrics are various. Also, with those data, I can compare more lyrics from different types of singers, and more singers from the same genre to limit the bias. A sufficient number of samples can support my point of view.

My full code is showing below.