Advanced search
1 file | 962.04 KB Add to list

Questioning the news about economic growth : sparse forecasting using thousands of news-based sentiment values

Author
Organization
Abstract
The modern calculation of textual sentiment involves a myriad of choices as to the actual calibration. We introduce a general sentiment engineering framework that optimizes the design for forecasting purposes. It includes the use of the elastic net for sparse data-driven selection and the weighting of thousands of sentiment values. These values are obtained by pooling the textual sentiment values across publication venues, article topics, sentiment construction methods, and time. We apply the framework to the investigation of the value added by textual analysis-based sentiment indices for forecasting economic growth in the US. We find that the additional use of optimized news-based sentiment values yields significant accuracy gains for forecasting the nine-month and annual growth rates of the US industrial production, compared to the use of high-dimensional forecasting techniques based on only economic and financial indicators. (C) 2018 The Author(s). Published by Elsevier B.V. on behalf of International Institute of Forecasters.
Keywords
Business and International Management, Elastic net, Sentiment analysis, Time series aggregation, Topic-sentiment, US industrial production, Sentometrics, VARIABLE SELECTION, NUMBER, REGRESSION, HETEROSKEDASTICITY, REGULARIZATION, CONFIDENCE, SHRINKAGE, FREEDOM, MODELS

Downloads

  • ArdiaBoudtBluteau.pdf
    • full text (Published version)
    • |
    • open access
    • |
    • PDF
    • |
    • 962.04 KB

Citation

Please use this url to cite or link to this publication:

MLA
Ardia, David, et al. “Questioning the News about Economic Growth : Sparse Forecasting Using Thousands of News-Based Sentiment Values.” INTERNATIONAL JOURNAL OF FORECASTING, vol. 35, no. 4, 2019, pp. 1370–86.
APA
Ardia, D., Bluteau, K., & Boudt, K. (2019). Questioning the news about economic growth : sparse forecasting using thousands of news-based sentiment values. INTERNATIONAL JOURNAL OF FORECASTING, 35(4), 1370–1386.
Chicago author-date
Ardia, David, Keven Bluteau, and Kris Boudt. 2019. “Questioning the News about Economic Growth : Sparse Forecasting Using Thousands of News-Based Sentiment Values.” INTERNATIONAL JOURNAL OF FORECASTING 35 (4): 1370–86.
Chicago author-date (all authors)
Ardia, David, Keven Bluteau, and Kris Boudt. 2019. “Questioning the News about Economic Growth : Sparse Forecasting Using Thousands of News-Based Sentiment Values.” INTERNATIONAL JOURNAL OF FORECASTING 35 (4): 1370–1386.
Vancouver
1.
Ardia D, Bluteau K, Boudt K. Questioning the news about economic growth : sparse forecasting using thousands of news-based sentiment values. INTERNATIONAL JOURNAL OF FORECASTING. 2019;35(4):1370–86.
IEEE
[1]
D. Ardia, K. Bluteau, and K. Boudt, “Questioning the news about economic growth : sparse forecasting using thousands of news-based sentiment values,” INTERNATIONAL JOURNAL OF FORECASTING, vol. 35, no. 4, pp. 1370–1386, 2019.
@article{8600237,
  abstract     = {The modern calculation of textual sentiment involves a myriad of choices as to the actual calibration. We introduce a general sentiment engineering framework that optimizes the design for forecasting purposes. It includes the use of the elastic net for sparse data-driven selection and the weighting of thousands of sentiment values. These values are obtained by pooling the textual sentiment values across publication venues, article topics, sentiment construction methods, and time. We apply the framework to the investigation of the value added by textual analysis-based sentiment indices for forecasting economic growth in the US. We find that the additional use of optimized news-based sentiment values yields significant accuracy gains for forecasting the nine-month and annual growth rates of the US industrial production, compared to the use of high-dimensional forecasting techniques based on only economic and financial indicators. (C) 2018 The Author(s). Published by Elsevier B.V. on behalf of International Institute of Forecasters.},
  author       = {Ardia, David and Bluteau, Keven and Boudt, Kris},
  issn         = {0169-2070},
  journal      = {INTERNATIONAL JOURNAL OF FORECASTING},
  keywords     = {Business and International Management,Elastic net,Sentiment analysis,Time series aggregation,Topic-sentiment,US industrial production,Sentometrics,VARIABLE SELECTION,NUMBER,REGRESSION,HETEROSKEDASTICITY,REGULARIZATION,CONFIDENCE,SHRINKAGE,FREEDOM,MODELS},
  language     = {eng},
  number       = {4},
  pages        = {1370--1386},
  title        = {Questioning the news about economic growth : sparse forecasting using thousands of news-based sentiment values},
  url          = {http://dx.doi.org/10.1016/j.ijforecast.2018.10.010},
  volume       = {35},
  year         = {2019},
}

Altmetric
View in Altmetric
Web of Science
Times cited: