Research Progress of Sentiment Analysis Based on Deep Learning

Jiameng Li

doi:10.62051/2qgbqm02

Authors

Jiameng Li

DOI:

https://doi.org/10.62051/2qgbqm02

Keywords:

Sentiment Analysis, Deep learning, Natural language processing, LSTM, Transformer.

Abstract

Sentiment analysis technology is widely used in film and television media, social media, entertainment industry, medical and other fields, and has great commercial use value. In the early stages of research, sentiment analysis methods based on traditional machine learning are not effective, which greatly limits its application in the commercial field. In recent years, with the development of artificial intelligence, deep learning-based sentiment analysis have made great advances. However, the large variation in performance results and characteristics for different algorithms heightened the difficulty in practical application. According to the technical progress of sentiment analysis, this paper summarizes from two aspects: data set and algorithm, introducing the commonly used data sets, evaluation indicators and sentiment analysis methods based on deep learning. In addition, this paper also provided a comparison among different algorithms widely used for sentiment analysis. Finally, this paper analyzes the existing technical adjustment, and discusses the future research direction.

Downloads

Download data is not yet available.

References

Jinpei Yan, Yong Qi, Qifan Rao.Detecting Malware with an Ensemble Method Based on Deep Neural Network, IEEE International Conference On Big Data Science And Enginerring,2018, 1170-1179.

Rehab Duwairi and Mahmoud El-Orfali. A Study of the Effects of Preprocessing Strategies on Sentiment Analysis for Arabic Text, Journal of Information Science, 2014, 40(4):501-513

Cházaro-Ruiz LF, Kellenberger A, Dunsch L. Dunsch. In situ ESR/UV-vis-NIR and ATR-FTIR spectroelectrochemical studies on the p-doping of copolymers of 3-methylthiophene and 3-hexylthiophene, Journal of Physical Chemistry, 2009, 113(8): 2310-2316.

Mathias Kraus, Stefan Feuerriegel. Sentiment analysis based on rhetorical structure theory: Learning deep neural networks from discourse trees, Expert Systems with Applications,2019, 65-79.

Joeky T Senders, Omar Arnaout, Aditya V Karhade, et. al. Natural and Artificial Intelligence in Neurosurgery: A Systematic Review, Neurosurgery, 2018, 83(2):181-192.

Author Picture Rathany Chan Sam, Author Picture Huong Thanh Le, Author Picture Thuy Thanh Nguyen, et. al. Combining proper name-coreference with conditional random fields for semi-supervised named entity recognition in Vietnamese text, Proceedings of the 15th Pacific-Asia conference on Advances in knowledge discovery and data mining - Volume Part I, 2011, 512–524.

Resch, Bernd, Usländer, Florian, Havas, Clemens. Combining machine-learning topic models and spatiotemporal analysis of social media data for disaster footprint and damage assessment, Cartography and Geographic Information Science, 2018, 362-376.

Vineet John, Olga Vechtomova. Sentiment Analysis on Financial News Headlines using Training Dataset Augmentation. Proceedings of the 11th International Workshop on Semantic Evaluation, 2017.

Ali Sharif Razavian, Hossein Azizpour, Josephine Sullivan. CNN Features off-the-shelf: an Astounding Baseline for Recognition, 2014 IEEE conference on computer vision and pattern recognition workshops,2014, 512-519.

WANG Yingjie, ZHU Jiuqi, WANG Zumin1, BAI Fengbo, GONG Jian. Review of applications of natural language processing in text sentiment analysis, Frontiers in Business Economics and Management, 2023, 10(1):58-64.

Adji B. Dieng, Chong Wang, Jianfeng Gao, John Paisley. TopicRNN: a recurrent neural network with long-range semantic dependency, Cornell University, 2016.

He Yanxiang, Sun Songtao, Niu Feifei. A Deep learning model of emotion semantic Enhancement for Weibo sentiment Analysis. Journal of computers, 2017, 40 (4): 18.

Yequan Wang, Minlie Huang, Xiaoyan Zhu, and Li Zhao, Attention-based LSTM for Aspect-level Sentiment Classification, Association for Computational Linguistics,2016, 606–615.

Usman Naseem, Imran Razzak, Katarzyna Musial, Muhammad Imran. Transformer based Deep Intelligent Contextual Embedding for Twitter sentiment analysis. Future Generation Computer Systems, 2020, 58-69.