Klasifikasi Emosi Lirik Lagu Dengan Long Short Term Memory dan Word2Vec

Abstrak

This research focuses on the classification of emotions in song lyrics using LSTM (Long ShortTerm Memory) and Word2Vec embedding. Emotion classification in lyrics plays a crucial role in music recommendation systems, sentiment analysis, and understanding the affective aspects of music. The study explores the effectiveness of LSTM, a type of recurrent neural network (RNN), in capturing the sequential dependencies and patterns in lyrics, combined with Word2Vec embedding to represent the semantic meaning of words.The dataset consists of a collection of song lyrics labeled with 2 emotions. The lyrics are preprocessed and converted into word vectors using the Word2Vec model. The LSTM model is then trained on the preprocessed lyrics data, aiming to predict the corresponding emotion category for a given set of lyrics. Experimental results demonstrate that the proposed approach achieves a maximum accuracy of 72.8% in classifying emotions in song lyrics. The LSTM model leverages the sequential information in the lyrics to capture the emotional context effectively. The Word2Vec embedding enhances the representation of words, allowing the model to understand the semantic relationships between words and better discriminate between different emotional categories.