News-based business sentiment and its properties as an economic index

Seki, Kazuhiko; Ikuta, Yusuke; Matsubayashi, Yoichi

doi:10.1016/j.ipm.2021.102795

Cited by 23 publications

(9 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Business sentiment can be effectively captured from news text based on newspaper articles ( Seki, Ikuta & Matsubayashi, 2022 ). Mehta, Pandya & Kotecha (2021) have proposed models for stock price prediction by integrating sentiment analysis and different machine learning techniques.…”

Section: Related Workmentioning

confidence: 99%

A cooperative deep learning model for stock market prediction using deep autoencoder and sentiment analysis

2022

PeerJ Computer Science

View full text Add to dashboard Cite

Stock market prediction is a challenging and complex problem that has received the attention of researchers due to the high returns resulting from an improved prediction. Even though machine learning models are popular in this domain dynamic and the volatile nature of the stock markets limits the accuracy of stock prediction. Studies show that incorporating news sentiment in stock market predictions enhances performance compared to models using stock features alone. There is a need to develop an architecture that facilitates noise removal from stock data, captures market sentiments, and ensures prediction to a reasonable degree of accuracy. The proposed cooperative deep-learning architecture comprises a deep autoencoder, lexicon-based software for sentiment analysis of news headlines, and LSTM/GRU layers for prediction. The autoencoder is used to denoise the historical stock data, and the denoised data is transferred into the deep learning model along with news sentiments. The stock data is concatenated with the sentiment score and is fed to the LSTM/GRU model for output prediction. The model’s performance is evaluated using the standard measures used in the literature. The results show that the combined model using deep autoencoder with news sentiments performs better than the standalone LSTM/GRU models. The performance of our model also compares favorably with state-of-the-art models in the literature.

show abstract

Section: Related Workmentioning

confidence: 99%

A cooperative deep learning model for stock market prediction using deep autoencoder and sentiment analysis

2022

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…In the case of the MF-CCI + , we also considered an expanded information set by including a proxy for media sentiment. Several authors showed that the role of media is crucial in orienting firm opinion, and the media sentiment itself can be used as a leading indicator in a forecasting strategy (e.g., Seki et al 2022).…”

Section: Concluding Remarks and Policy Implicationsmentioning

confidence: 99%

Mixed frequency composite indicators for measuring public sentiment in the EU

et al. 2022

View full text Add to dashboard Cite

Monitoring the state of the economy in a short time is a crucial aspect for designing appropriate and timely policy responses in the presence of shocks and crises. Short-term confidence indicators can help policymakers in evaluating both the effect of policies and the economic activity condition. The indicator commonly used in the EU to evaluate the public opinion orientation is the Economic Sentiment Indicator (ESI). Nevertheless, the ESI shows some drawbacks, particularly in the adopted weighting scheme that is static and not country-specific. This paper proposes an approach to construct novel composite confidence indicators, focusing on both the weights and the information set to use. We evaluate these indicators by studying their response to the policies introduced to contain the COVID-19 pandemic in some selected EU countries. Furthermore, we carry out an experimental study where the proposed indicators are used to forecast economic activity.

show abstract

“…Seki, K., et al [22] have devised a method for measuring business mood based on newspaper article analysis. Using sentiment analysis, they compute the S-APIR index based on sentiment score.…”

Section: Review Of Deep Learning Techniques In User Opinion Analysismentioning

confidence: 99%

Classification of Twitter COVID Tweets Using Deep CNN-SLSTM Technique

2022

View full text Add to dashboard Cite

A wide range of industries, including company management, travel and tourism management, education management (E-Learning), the medical field, government agencies, telecommunications management, and private firms, can benefit from user opinion analysis. Many classifiers for deep learning and machine learning are being created to automate sentiment analysis. For sentiment analysis, real-time tweets are initially gathered from various social media platforms like Twitter and Facebook as well as numerous review websites like Amazon and Flip-kart. In this research, a real-time dataset is created using the Twitter API and is used to gather tweets about COVIDbased keywords between

show abstract

News-based business sentiment and its properties as an economic index

Cited by 23 publications

References 37 publications

A cooperative deep learning model for stock market prediction using deep autoencoder and sentiment analysis

A cooperative deep learning model for stock market prediction using deep autoencoder and sentiment analysis

Mixed frequency composite indicators for measuring public sentiment in the EU

Classification of Twitter COVID Tweets Using Deep CNN-SLSTM Technique

Contact Info

Product

Resources

About