Enhanced news sentiment analysis using deep learning methods

被引：0

作者：

Wataru Souma

Irena Vodenska

Hideaki Aoyama

机构：

[1] Nihon University,College of Science and Technology

[2] Boston University,Metropolitan College

[3] Boston University,Center for Polymer Studies

[4] Kyoto University,Graduate School of Science

[5] Trade and Industry,Research Institute of Economy

来源：

Journal of Computational Social Science | 2019年 / 2卷

关键词：

Sentiment analysis; Deep learning; Forecasting;

D O I：

暂无

中图分类号：

学科分类号：

摘要：

We explore the predictive power of historical news sentiments based on financial market performance to forecast financial news sentiments. We define news sentiments based on stock price returns averaged over one minute right after a news article has been released. If the stock price exhibits positive (negative) return, we classify the news article released just prior to the observed stock return as positive (negative). We use Wikipedia and Gigaword five corpus articles from 2014 and we apply the global vectors for word representation method to this corpus to create word vectors to use as inputs into the deep learning TensorFlow network. We analyze high-frequency (intraday) Thompson Reuters News Archive as well as the high-frequency price tick history of the Dow Jones Industrial Average (DJIA 30) Index individual stocks for the period between 1/1/2003 and 12/30/2013. We apply a combination of deep learning methodologies of recurrent neural network with long short-term memory units to train the Thompson Reuters News Archive Data from 2003 to 2012, and we test the forecasting power of our method on 2013 News Archive data. We find that the forecasting accuracy of our methodology improves when we switch from random selection of positive and negative news to selecting the news with highest positive scores as positive news and news with highest negative scores as negative news to create our training data set.

引用

页码：33 / 46

页数：13

共 50 条

[1] Enhanced news sentiment analysis using deep learning methods
Souma, Wataru
Vodenska, Irena
Aoyama, Hideaki
[J]. JOURNAL OF COMPUTATIONAL SOCIAL SCIENCE, 2019, 2 (01): : 33 - 46
[2] Sentiment Analysis of Sindhi News Articles using Deep Learning
Barakzai, Fahama
Bhatti, Sania
Saddar, Salahuddin
[J]. 2022 IEEE 17TH INTERNATIONAL CONFERENCE ON COMPUTER SCIENCES AND INFORMATION TECHNOLOGIES (CSIT), 2022, : 26 - 31
[3] Twitter Sentiment Analysis using Deep Learning Methods
Ramadhani, Adyan Marendra
Goo, Hong Soon
[J]. 2017 7TH INTERNATIONAL ANNUAL ENGINEERING SEMINAR (INAES), 2017, : 100 - 103
[4] Sentiment Analysis of Lithuanian Texts Using Deep Learning Methods
Kapociute-Dzikiene, Jurgita
Damasevicius, Robertas
Wozniak, Marcin
[J]. INFORMATION AND SOFTWARE TECHNOLOGIES, ICIST 2018, 2018, 920 : 521 - 532
[5] Arabic Sentiment Analysis Using Deep Learning and Ensemble Methods
Amal Alharbi
Manal Kalkatawi
Mounira Taileb
[J]. Arabian Journal for Science and Engineering, 2021, 46 : 8913 - 8923
[6] Arabic Sentiment Analysis Using Deep Learning and Ensemble Methods
Alharbi, Amal
Kalkatawi, Manal
Taileb, Mounira
[J]. ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING, 2021, 46 (09) : 8913 - 8923
[7] Urdu Sentiment Analysis With Deep Learning Methods
Khan, Lal
Amjad, Ammar
Ashraf, Noman
Chang, Hsien-Tsung
Gelbukh, Alexander
[J]. IEEE ACCESS, 2021, 9 : 97803 - 97812
[8] ENHANCED DEEP LEARNING-BASED MODEL FOR SENTIMENT ANALYSIS TO IDENTIFY SARCASM APPEARED IN THE NEWS
Gupta, Isha
Chatterjee, Indranath
Gupta, Neha
[J]. COMPUTING AND INFORMATICS, 2023, 42 (05) : 1091 - 1113
[9] UTSA: Urdu Text Sentiment Analysis Using Deep Learning Methods
Naqvi, Uzma
Majid, Abdul
Abbas, Syed Ali
[J]. IEEE ACCESS, 2021, 9 : 114085 - 114094
[10] UTSA: Urdu Text Sentiment Analysis Using Deep Learning Methods
Naqvi, Uzma
Majid, Abdul
Abbas, Syed Ali
[J]. IEEE Access, 2021, 9 : 114085 - 114094

← 1 2 3 4 5 →