EconBase
← All papers

Identifying Different Definitions of Future in the Assessment of Future Economic Conditions: Application of PU Learning and Text Mining

Masahiro Kato

arXiv 7 Sep 2019 · Econometrics · 1 citations (OpenAlex)

arXiv:1909.03348 · PDF · DOI · OpenAlex · Extracted main text

Abstract

The Economy Watcher Survey, which is a market survey published by the Japanese government, contains assessments of current and future economic conditions by people from various fields. Although this survey provides insights regarding economic policy for policymakers, a clear definition of the word "future" in future economic conditions is not provided. Hence, the assessments respondents provide in the survey are simply based on their interpretations of the meaning of "future." This motivated us to reveal the different interpretations of the future in their judgments of future economic conditions by applying weakly supervised learning and text mining. In our research, we separate the assessments of future economic conditions into economic conditions of the near and distant future using learning from positive and unlabeled data (PU learning). Because the dataset includes data from several periods, we devised new architecture to enable neural networks to conduct PU learning based on the idea of multi-task learning to efficiently learn a classifier. Our empirical analysis confirmed that the proposed method could separate the future economic conditions, and we interpreted the classification results to obtain intuitions for policymaking.

Citation extraction

18
references
25
in-text mentions
18
distinct cited
2
self-citations
4,327
main-text words

appendix boundary found by appendix_command · 94% of the source is main text. Read the extracted text to check this.

Most heavily cited references

The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.

ReferenceIntensityMentionsSectionsMain text
1Charles Elkan and Keith Noto (2008) Learning classifiers from only positive and unlabeled data0.73732100%
2Marthinus Christoffel du Plessis, Gang. Niu, and Masashi Sugiyama (2015) Convex formulation for learning from positive and unlabeled data0.64422100%
3Ryuichi Kiryo, Gang Niu, Marthinus Christoffel du Plessis, and Masas… (2017) Positive-unlabeled learning with non-negative risk estimator0.58531100%
4Masahiro Kato, Takeshi Teshima, and Junya Honda (2019) Learning from positive and unlabeled data with a selection bias self0.58531100%
5Masahiro Kato, Liyuan Xu, Gang Niu, and Masashi Sugiyama (2018) Alternate estimation of a classifier and the class-prior from positive and unlabeled data self0.40511100%
6Rich Caruana (1997) Multitask learning0.40511100%
7Marthinus Christoffel du Plessis and Masashi Sugiyama (2014) Class prior estimation from positive and unlabeled data0.40511100%
8Christopher D. Manning and Hinrich Schütze (1999) Foundations of Statistical Natural Language Processing0.40511100%
9Vinod Nair and Geoffrey E. Hinton (2010) Rectified linear units improve restricted boltzmann machines0.40511100%
10Paul C. Tetlock, Maytal Saar‐tsechansky, and Sofus Macskassy (2008) More than words: Quantifying language to measure firms' fundamentals0.40511100%

Showing the top 10 of 18 scored citations.