Exploring the Evolutionary Change in Bollywood Lyrics over the Last Two Decades

Bollywood songs have experienced a considerable change in terms of lyrics over the past decades. Long ago, bollywood songs contained mostly Hindi words, but nowadays lyricists use lots of English words to express themselves. Till date, we are not aware of any systematic quantitative analysis of how it has changed and how the evolution took place over the years. In this paper, we analysed the evolution of bollywood songs' lyrics over the past two decades. We study how the number of words and foreign words evolved over the past 20 years. The top 20 words used mostly while composing songs and the most occurring character are identified. Our dataset is composed of 300 bollywood lyrics. Based on the dataset, we show that the number of words and foreign words over the past two decades has been increasing. Our study reveals that the word "hai" (is) and the foreign word "baby" are the most widely used while writing the lyrics and the letter "a" has the highest frequency.