What makes songs popular

Many popular songs are energetic, though not necessarily dance songs. Because the correlation here is not too high, low energy songs do have some potential to be more popular.

Most popular songs today have either electronic or electric instruments in them. It is very rare that a piece of music played by a chamber orchestra or purely acoustic band becomes immensely popular. This makes some sense, as energy is definitely influenced by the volume at which the music is being played.

Dance songs are usually happier and in a major key. Thus, from this data, it would be better for an artist to create a high-energy song with either electric instruments or electronic songs to have the best chance of generating the most popularity. To see how each feature is affecting the popularity, please refer to my GitHub repository link at the end.

In order to select the most appropriate features for the model, I am making use of the yellow brick Feature Correlation Visualizer. The graph shows five features are with negative correlation and nine features with positive correlation. This is a bit of a problematic categorical feature to insert in a model and will be dropped. With the help of Sklearn classes, this split can be made and fitted to the following model types:.

From the below plot, seems to the best fit. Python code implementation for the Decision Tree Regressor model. Using GridSearchCV to find the optimal hyperparameters for the decision tree to predict song popularity and improve accuracy, the code below is the snippet I used to find out the best parameters to tune the model.

The stars have to align to get a song to the top of the chart. Moral of the story? It takes a lot of luck and a lot of good things go into what makes a song a hit. AND, the songwriter can only control 1 and can only impact 2 to some degree. So, the smart songwriter invests the VAST majority of his or her time in writing better songs.

Writing a better song each day than you wrote the day before is the best way the only way I know of to really have a hit song someday. Enter your email address to get started! In my experience, here is what makes a song a hit: The songwriter writes a song that is catchy, compelling and commercial.

The song gets into the right hands. The right artist is matched with the song. A great recording is made of the song. They are just connectives between larger themes.

We started wondering, why might that be? We started doing different analyses to try to figure it out. For example, we started with a data set of around 2, songs over three years. We went to the Billboard charts, scraped what songs were popular in different years and controlled for a variety of things like radio airplay, genre, artists and the content. It seemed to be something a little bit more nuanced.

I think this is quite interesting because this gets to the core of why we like cultural products. Why do we like books and songs and movies in the first place? Sometimes, we like to be transported to other places. We watch a sci-fi movie because we want to be transported to something outside our own lives. But other times, we [consume] these things and enjoy them because they make our own lives in some way better.

They help us see our own relationships, our own social connections, as deeper and different as they might be otherwise. Who do I love? I remember singing that song in my head to my girlfriend at the time and thinking about how much I cared about her. It activates that self in our own lives that makes us feel more connected to the song.

How do you actually go about studying this kind of thing? There are hundreds of reasons why songs are successful. As I mentioned, we tried to control for various things, like a certain artist might be liked more, certain genres might be more or less popular, and more radio airplay is going to help songs be successful.

We did that in the field, but then we also did some experiments. We started with something really simple. How much does it enable you to imagine a personal other in your own life? And that leads them to like the song more. And they like it more because it encourages them to think about someone in their own life that they feel that way towards.

Knowledge Wharton: Are there lessons here for marketers beyond the music industry? Berger: I think there are a few interesting things that come out of this paper. There have been lots of people over time who have argued they can understand why songs succeed. I think natural language processing is a really neat avenue to understand why some songs succeed and some fail, and how we can impact that.

Beyond the music industry, I think this has a lot of interesting implications. You often see a lot of second-person pronouns used in very successful online content because it encourages us to pay attention. I want to know the implication of this for me.