Text Sentiment Analysis for JD.com Based on Machine Learning

Hanyu Wang

2024

Abstract

One of the most important uses of Natural Language Processing (NLP) is text sentiment analysis. It is the process of processing and classifying textual content that has been infused with subjective attitudes. The final result is the identification of public sentiment patterns toward specific topics or products. To elevate both accuracy and efficiency in sentiment analysis, the research simultaneously assesses the effectiveness of several models, promoting a detailed understanding of their individual benefits and limitations. Notably, the investigation showed that the Long Short-Term Memory (LSTM) model was a strong competitor. The LSTM model demonstrated its effectiveness in sentiment analysis tasks by achieving an excellent accuracy rate of 87.29% during rigorous training and testing with tens of thousands of datasets. This work then uses this model to analyze user reviews for certain digital products on JD.com, providing an example of the usefulness of LSTM in practical settings. This paper highlights the promising potential of LSTM networks in addressing complex sentiment analysis problems and pushes the boundaries of sentiment analysis approaches.

Paper Citation

in Harvard Style

Wang H. (2024). Text Sentiment Analysis for JD.com Based on Machine Learning. In Proceedings of the 2nd International Conference on Data Analysis and Machine Learning - Volume 1: DAML; ISBN 978-989-758-754-2, SciTePress, pages 257-260. DOI: 10.5220/0013515400004619

in Bibtex Style

@conference{daml24,
author={Hanyu Wang},
title={Text Sentiment Analysis for JD.com Based on Machine Learning},
booktitle={Proceedings of the 2nd International Conference on Data Analysis and Machine Learning - Volume 1: DAML},
year={2024},
pages={257-260},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013515400004619},
isbn={978-989-758-754-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 2nd International Conference on Data Analysis and Machine Learning - Volume 1: DAML
TI - Text Sentiment Analysis for JD.com Based on Machine Learning
SN - 978-989-758-754-2
AU - Wang H.
PY - 2024
SP - 257
EP - 260
DO - 10.5220/0013515400004619
PB - SciTePress