Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Framing in the Presence of Supporting Data: A Case Study in U.S. Economic News

Alexandria Leto, Elliot Pickens, Coen D. Needell, David Rothschild, Maria Leonor Pacheco

TL;DR

It is argued that there are newsworthy topics where objective measures exist in the form of supporting data and a computational framework to analyze editorial choices in this setup is proposed and proposed.

Abstract

The mainstream media has much leeway in what it chooses to cover and how it covers it. These choices have real-world consequences on what people know and their subsequent behaviors. However, the lack of objective measures to evaluate editorial choices makes research in this area particularly difficult. In this paper, we argue that there are newsworthy topics where objective measures exist in the form of supporting data and propose a computational framework to analyze editorial choices in this setup. We focus on the economy because the reporting of economic indicators presents us with a relatively easy way to determine both the selection and framing of various publications. Their values provide a ground truth of how the economy is doing relative to how the publications choose to cover it. To do this, we define frame prediction as a set of interdependent tasks. At the article level, we learn to identify the reported stance towards the general state of the economy. Then, for every numerical quantity reported in the article, we learn to identify whether it corresponds to an economic indicator and whether it is being reported in a positive or negative way. To perform our analysis, we track six American publishers and each article that appeared in the top 10 slots of their landing page between 2015 and 2023.

Framing in the Presence of Supporting Data: A Case Study in U.S. Economic News

TL;DR

It is argued that there are newsworthy topics where objective measures exist in the form of supporting data and a computational framework to analyze editorial choices in this setup is proposed and proposed.

Abstract

The mainstream media has much leeway in what it chooses to cover and how it covers it. These choices have real-world consequences on what people know and their subsequent behaviors. However, the lack of objective measures to evaluate editorial choices makes research in this area particularly difficult. In this paper, we argue that there are newsworthy topics where objective measures exist in the form of supporting data and propose a computational framework to analyze editorial choices in this setup. We focus on the economy because the reporting of economic indicators presents us with a relatively easy way to determine both the selection and framing of various publications. Their values provide a ground truth of how the economy is doing relative to how the publications choose to cover it. To do this, we define frame prediction as a set of interdependent tasks. At the article level, we learn to identify the reported stance towards the general state of the economy. Then, for every numerical quantity reported in the article, we learn to identify whether it corresponds to an economic indicator and whether it is being reported in a positive or negative way. To perform our analysis, we track six American publishers and each article that appeared in the top 10 slots of their landing page between 2015 and 2023.
Paper Structure (45 sections, 21 figures, 12 tables)

This paper contains 45 sections, 21 figures, 12 tables.

Table of Contents

  1. Introduction
  2. Background and Related Work
  3. Selection and Framing
  4. Economic Indicators
  5. Framing of Economic News
  6. Computational Framing Analysis
  7. Data
  8. Data Collection
  9. Data Annotation
  10. Model
  11. Exploiting inter-dependencies with SRL
  12. Enhancing PSL priors with pre-trained language models
  13. Experimental Evaluation
  14. Frame Prediction
  15. Experimental Settings
  16. ...and 30 more sections

Figures (21)

  • Figure 1: The Frame Prediction Framework
  • Figure 2: Distribution of article-level annotation labels
  • Figure 3: Distribution of quantity-level annotation labels
  • Figure 4: Framing of articles referencing job numbers from 2015 through 2023 in the New York Times. Spin was aggregated quarterly. Monthly payroll (employment) data can be seen in the dotted black line. The gray bars represent proportion of the overall coverage taken up by jobs reporting.
  • Figure 5: Selection of economic indicators referencing price (price & energy) numbers from 2015 through 2023 in the New York Times, Washington Post, and Wall Street Journal. Aggregated Quarterly. Monthly CPI data can be seen in the dotted blue line.
  • ...and 16 more figures