• If you are citizen of an European Union member nation, you may not use this service unless you are at least 16 years old.

  • Buried in cloud files? We can help with Spring cleaning!

    Whether you use Dropbox, Drive, G-Suite, OneDrive, Gmail, Slack, Notion, or all of the above, Dokkio will organize your files for you. Try Dokkio (from the makers of PBworks) for free today.

  • Dokkio (from the makers of PBworks) was #2 on Product Hunt! Check out what people are saying by clicking here.


Mapping Lyrical Sentiment

Page history last edited by Alan Liu 7 years, 6 months ago

Mapping Lyrical Sentiment


Team Members: Samantha Urena and Megan Carter

Group Annotated Bibliographies: Samantha Urena and Megan Carter

Group Research Reports: Samantha Urena and Megan Carter

Links: Positive Story Map, Negative Story Map, Neutral Story Map, Home Story Map





The project’s objective was to observe the overall sentiment different kinds of places created by analyzing song lyrics about six specific cities and song lyrics about the more vague concept of “home”. 



Using Spotify, we charted the top six songs about six specific cities. We looked at three cities in California (Los Angeles, San Francisco, and San Diego) and three cities in New York (New York, Brooklyn, and Manhattan). Using Sentiment Analysis, we plugged in the lyrics to each of these songs and added and subtracted the sentiment of each stanza (whether it was positive, negative, or neutral) until we ended with the overall sentiment of the song. After compiling the sentiment of the song lyrics, we charted it on one of three maps (a positive map, a negative map, or a neutral map). By looking at any of the individual maps, one can observe the immediate sentiment an artist feels towards a particular place.


Again using Spotify, we charted the top twelve songs about “home”. Using Sentiment Analysis, we plugged in the lyrics to each of these songs and added and subtracted the sentiment of each stanza (whether it was positive, negative, or neutral) until we ended with the overall sentiment of the song.



The three cities observed in California each have a different overall sentiment. Los Angeles has an overall positive sentiment, San Diego has an overall negative sentiment, and San Francisco has an overall mixed sentiment (half of the songs are positive while the other half are negative). All three cities are characterized by their location on the gold coast; at least one song per city includes lyrics about the ocean. Los Angeles is characterized by its heat and sun and by the bustling city life. Its music is characterized by upbeat rock sounds; steady drums, driving bass, and gritty guitar riffs. San Diego is characterized as a city one visits, but does not stay. The music is a mix of some acoustic sounds, acoustic pop, pop rock, and rap. A mixed bag of genre matching the overall feeling of uncertainty the city evokes. The weather and landmarks of the city characterize songs about San Francisco. Every single song looked at includes mentions or alludes to either the Golden Gate Bridge or the well-known fog that rolls into the city.


Songs about home are characterized more about feelings towards a place than facts about a place. “Home” is marked by relationships with loved ones rather than interactions with weather and landmarks like so many songs about cities are characterized by. 



The results of our project produced an interesting comparison between the themes that emerged between songs written about a specific place (for the purposes of this project, a city) versus a song written about the more vague concept of "home". Songs written about cities often talked explicitly about the city and how that places enhances certain preexisting feelings they have, and works to produce new ones. Additionally, many times there is mention of popular physical attractions in certain cities and how they work to shape certain feelings. At the same time, each artist experiences these places and things differently, and ultimately, a common place has the ability to create a difference in sentiment. Songs about home also contain consistent themes, but seemed to speak much more about relationships and the notion of being with a person and how they make the artist feel at home, regardless of where they are physically. In this way, home can be anywhere, as long as they are with the person who makes them feel at home. The overarching conclusion is that songs composed about certain cities are more about all of the possibilities - relational, individual, etc. - that can occur in that place, whereas songs written about home are more about the feeling the artist has with a certain person and less about the physical place they find themselves in. 


Closing Thoughts

The sentiment analysis used for the purposes of this project was useful to provide an initial examination and interpretation for the song lyrics inputted into the device. In the context of this project, there are many ways this project could be expanded on. For instance, more cities within the United States and internationally could be explored, with additional analysis conducted to compare and contrast themes between them. A comparative examination of themes found initially within this pilot project and in further research can thus be performed. Additionally, our group originally considered analyzing poetry instead of song lyrics, but eventually shifted our focus to only lyrics given the time constraint of the course. That being said, poetry would be a realm worth investigating. The sentiment analysis tool could and should still remain the primary tool of analysis, with others added as needed.




  • Blake, Robert W. “Poets on Poetry: The Morality of Poetry” The English Journal, Vol. 81, No. 1 (Jan., 1992), pp. 16-20 Stable URL:http://www.jstor.org/stable/818330 
  • Dorris, Michael. “Home” The Threepenny Review, No. 54 (Summer, 1993), pp. 16-17 Stable URL: http://www.jstor.org/stable/4384210 
  • Goba, Ronald J.  “Poetry and the Senses” The Clearing House, Vol. 44, No. 3 (Nov., 1969), pp. 149-151 Stable URL: http://www.jstor.org/stable/30183994 
  • Krystine Irene Batcho. “Nostalgia and the Emotional Tone and Content of Song Lyrics” American Journal of Psychology, Vol. 120, No. 3 (Fall, 2007) pp. 361-38 Stable URL: http://www.jstor.org/stable/20445410
  • Reynolds, Nedra “Ethos as Location: New Sites for Understanding Discursive Authority” Rhetoric Review, Vol. 11, No. 2 (Spring, 1993), pp. 325-338 Stable URL: http://www.jstor.org/stable/465805
  • Devitt, Amy J. "Writing Genres" Rhetoric Review, Vol. 24, No. 3 (2005), pp. 342-345 Stable URL:http://www.jstor.org/stable/20176669
  • Etzkorn, Peter K. "Social Context of Songwriting in the United States" Ethnomusicology, Vol. 7, No. 2 (May, 1963), pp. 96-106 Stable URL:http://www.jstor.org/stable/924545  
  • Mayer, Rudolf, Neumayer, Robert, & Rauber, Andreas, Proceedings of the Ninth International Conference of Music Information Retrieval, 2008. Print.   
  • Weber, Robert Philip, "Basic Content Analysis", Journal of the American Statistical AssociationVol. 82, No. 397 (Mar., 1987), pp. 354-355 Stable URL: http://www.jstor.org/stable/2289192 


Comments (0)

You don't have permission to comment on this page.