GeeSanBhava: Sentiment Tagged Sinhala Music Video Comment Data Set
PositiveArtificial Intelligence
- The study introduces GeeSanBhava, a comprehensive dataset of Sinhala song comments sourced from YouTube, which has been meticulously tagged using Russell's Valence-Arousal model by three independent annotators, achieving a high inter-annotator agreement of 84.96%. This dataset highlights the emotional profiles associated with different songs, emphasizing the significance of comment-based emotion mapping.
- The development of the GeeSanBhava dataset is crucial for advancing sentiment analysis in Sinhala Natural Language Processing, as it provides a rich resource for training machine learning and deep learning models. The optimized Multi-Layer Perceptron model achieved a notable ROC-AUC score of 0.887, showcasing the potential for improved emotional understanding in user-generated content.
- This initiative reflects a broader trend in sentiment analysis where deep learning techniques are increasingly employed to decipher complex emotional nuances in textual data. Despite advancements, challenges remain in accurately interpreting emotional cues, indicating a need for ongoing research and refinement in the field.
— via World Pulse Now AI Editorial System
