Addition of Code Mixed Features to Enhance the Sentiment Prediction of Song Lyrics

TL;DR

This paper enhances sentiment prediction of song lyrics by incorporating code-mixed features, specifically for Telugu-English songs, achieving a 4-5% accuracy improvement over traditional methods.

Contribution

It introduces code-mixing features and a language identification tool to improve sentiment classification of code-mixed song lyrics.

Findings

Achieved 4-5% higher accuracy with new features

Developed a Telugu-English code-mixed dataset

Demonstrated the impact of code-mixing on sentiment analysis

Abstract

Sentiment analysis, also called opinion mining, is the field of study that analyzes people's opinions,sentiments, attitudes and emotions. Songs are important to sentiment analysis since the songs and mood are mutually dependent on each other. Based on the selected song it becomes easy to find the mood of the listener, in future it can be used for recommendation. The song lyric is a rich source of datasets containing words that are helpful in analysis and classification of sentiments generated from it. Now a days we observe a lot of inter-sentential and intra-sentential code-mixing in songs which has a varying impact on audience. To study this impact we created a Telugu songs dataset which contained both Telugu-English code-mixed and pure Telugu songs. In this paper, we classify the songs based on its arousal as exciting or non-exciting. We develop a language identification tool and introduce code-mixing features obtained from it as additional features. Our system with these additional features attains 4-5% accuracy greater than traditional approaches on our dataset.