Influence of English Language Words in Tamil Film Song Lyrics Corpus: A Machine Learning Approach

The use of English words in Tamil lyrics has significantly increased in recent years due to globalisation, Western cultural exposure, and the evolution of the Tamil music industry. Traditionally, Tamil lyrics used pure Tamil words, which were well-received in the early 1960s. However, the younger generation's exposure to Western influences and English-speaking media has led to a greater incorporation of English words in Tamil lyrics, reflecting broader cultural and societal changes. This blending of languages has made it difficult to classify the language of these compositions accurately. To address this, this study proposes a machine learning model to handle code-switching and multilingual text for identifying English words in Tamil lyrics. The objectives include testing the hypothesis that modern lyrics contain more English words than earlier compositions and using an unsupervised machine learning algorithm to cluster lyricists based on their use of English and other foreign language elements. By leveraging natural language processing (NLP) methods and machine learning techniques, the study aims to analyse language usage patterns in Tamil lyrics and explore the relationship between language, culture, and society in contemporary music.