# Tollywood Emotions: Annotation of Valence-Arousal in Telugu Song Lyrics

arXiv: https://arxiv.org/abs/2303.09364 · HTML: https://mlsanity.com/paper/2303.09364/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 30 references that are in the map.
- First posted on arXiv 16 Mar 2023.

## Builds on (most cited first, 6 of 6)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Cross-cultural Mood Perception in Pop Songs and its Alignment with Mood Detection Algorithms](https://mlsanity.com/paper/2108.00768/) (2021)
- [Static and Dynamic Measures of Active Music Listening as Indicators of Depression Risk](https://mlsanity.com/paper/2009.13685/) (2020)
- [Addition of Code Mixed Features to Enhance the Sentiment Prediction of Song Lyrics](https://mlsanity.com/paper/1806.03821/) (2018)

## Built on by (most cited first, 2 of 2)

- [Are We There Yet? A Brief Survey of Music Emotion Prediction Datasets, Models and Outstanding Challenges](https://mlsanity.com/paper/2406.08809/) (2024)
- [A Hybrid Framework for Song Lyric Annotation Based on Human-LLM Alignment](https://mlsanity.com/paper/2606.29273/) (2026)

## Abstract (arXiv)

Emotion recognition from a given music track has heavily relied on acoustic features, social tags, and metadata but is seldom focused on lyrics. There are no datasets of Indian language songs that contain both valence and arousal manual ratings of lyrics. We present a new manually annotated dataset of Telugu songs' lyrics collected from Spotify with valence and arousal annotated on a discrete scale. A fairly high inter-annotator agreement was observed for both valence and arousal. Subsequently, we create two music emotion recognition models by using two classification techniques to identify valence, arousal and respective emotion quadrant from lyrics. Support vector machine (SVM) with term frequency-inverse document frequency (TF-IDF) features and fine-tuning the pre-trained XLMRoBERTa (XLM-R) model were used for valence, arousal and quadrant classification tasks. Fine-tuned XLMRoBERTa performs better than the SVM by improving macro-averaged F1-scores of 54.69%, 67.61%, 34.13% to 77.90%, 80.71% and 58.33% for valence, arousal and quadrant classifications, respectively, on 10-fold cross-validation. In addition, we compare our lyrics annotations with Spotify's annotations of valence and energy (same as arousal), which are based on entire music tracks. The implications of our findings are discussed. Finally, we make the dataset publicly available with lyrics, annotations and Spotify IDs.