Text Emotion Multi-Label Classification with Vectoring and Deep Learning

An important problem in natural language processing is text emotion multi-label classification, which seeks to predict various emotions connected to a given text. This research suggests a unique method for increasing the precision of text emotion classification that combines vectorization methods an...

Full description

Saved in:
Bibliographic Details
Published in2024 International Conference on Inventive Computation Technologies (ICICT) pp. 371 - 376
Main Authors Radha, Dinesh Raja, Mary Gladence, L., M, Dhanush Raj
Format Conference Proceeding
LanguageEnglish
Published IEEE 24.04.2024
Subjects
CNN
Data preprocessing
Deep learning
Emotion recognition
multi-label classification
NLP
RNN
Semantics
Sentiment analysis
text emotion
Text recognition
vectorization
Vectors
Online AccessGet full text

Cover

More Information
Summary:An important problem in natural language processing is text emotion multi-label classification, which seeks to predict various emotions connected to a given text. This research suggests a unique method for increasing the precision of text emotion classification that combines vectorization methods and deep learning models. Then, using methods like TF-IDF or word embeddings, the text input is preprocessed and converted into numerical vectors. Then, a deep learning architecture with numerous layers, like CNNs or RNNs, is used to input vectorized data. Accurate emotion classification is made possible by the deep learning model, which efficiently learns the many correlations and patterns found in the text data. The effectiveness of the suggested strategy in achieving high classification accuracy for numerous emotions is demonstrated by experimental findings on a benchmark dataset.
ISSN:2767-7788
DOI:10.1109/ICICT60155.2024.10544461