Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Evaluating the Ability of Computationally Extracted Narrative Maps to Encode Media Framing

Sebastián Concha Macías, Brian Keith Norambuena

TL;DR

The study evaluates whether computationally extracted narrative maps can encode media framing in news data. By applying the narrative maps method to a reduced three-frame version of the Gun Violence Frame Corpus and using $K=6$ with a linear-programming coherence objective, the authors demonstrate that the maps closely reproduce the data's framing distribution, evidenced by a mean Jensen–Shannon divergence of $0.0218$. However, qualitative analyses reveal framing inconsistencies within individual maps, indicating that the extraction process currently emphasizes content similarity over consistent framing trajectories. These findings suggest that narrative maps can yield high-level framing insights but highlight the need for framing-aware extraction methods to ensure coherent framing across narrative chains, with significant implications for researchers and practitioners in computational journalism and sensemaking.

Abstract

Narratives serve as fundamental frameworks in our understanding of the world and play a crucial role in collaborative sensemaking, providing a versatile foundation for sensemaking. Framing is a subtle yet potent mechanism that influences public perception through specific word choices, shaping interpretations of reported news events. Despite the recognized importance of narratives and framing, a significant gap exists in the literature with regard to the explicit consideration of framing within the context of computational extraction and representation. This article explores the capabilities of a specific narrative extraction and representation approach -- narrative maps -- to capture framing information from news data. The research addresses two key questions: (1) Does the narrative extraction method capture the framing distribution of the data set? (2) Does it produce a representation with consistent framing? Our results indicate that while the algorithm captures framing distributions, achieving consistent framing across various starting and ending events poses challenges. Our results highlight the potential of narrative maps to provide users with insights into the intricate framing dynamics within news narratives. However, we note that directly leveraging framing information in the computational narrative extraction process remains an open challenge.

Evaluating the Ability of Computationally Extracted Narrative Maps to Encode Media Framing

TL;DR

The study evaluates whether computationally extracted narrative maps can encode media framing in news data. By applying the narrative maps method to a reduced three-frame version of the Gun Violence Frame Corpus and using with a linear-programming coherence objective, the authors demonstrate that the maps closely reproduce the data's framing distribution, evidenced by a mean Jensen–Shannon divergence of . However, qualitative analyses reveal framing inconsistencies within individual maps, indicating that the extraction process currently emphasizes content similarity over consistent framing trajectories. These findings suggest that narrative maps can yield high-level framing insights but highlight the need for framing-aware extraction methods to ensure coherent framing across narrative chains, with significant implications for researchers and practitioners in computational journalism and sensemaking.

Abstract

Narratives serve as fundamental frameworks in our understanding of the world and play a crucial role in collaborative sensemaking, providing a versatile foundation for sensemaking. Framing is a subtle yet potent mechanism that influences public perception through specific word choices, shaping interpretations of reported news events. Despite the recognized importance of narratives and framing, a significant gap exists in the literature with regard to the explicit consideration of framing within the context of computational extraction and representation. This article explores the capabilities of a specific narrative extraction and representation approach -- narrative maps -- to capture framing information from news data. The research addresses two key questions: (1) Does the narrative extraction method capture the framing distribution of the data set? (2) Does it produce a representation with consistent framing? Our results indicate that while the algorithm captures framing distributions, achieving consistent framing across various starting and ending events poses challenges. Our results highlight the potential of narrative maps to provide users with insights into the intricate framing dynamics within news narratives. However, we note that directly leveraging framing information in the computational narrative extraction process remains an open challenge.
Paper Structure (14 sections, 3 figures, 3 tables)

This paper contains 14 sections, 3 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Background and Related Work
  3. Narrative Maps and Extraction
  4. Computational Frame Modeling
  5. Materials and Methods
  6. Data Set Description
  7. Narrative Extraction Method
  8. Evaluation Metrics
  9. Results and Discussion
  10. Resulting Maps
  11. Quantitative Results
  12. Qualitative Example
  13. Implications
  14. Conclusions

Figures (3)

  • Figure 1: Technical methodological diagram illustrating the key steps in the narrative extraction and analysis process, starting with the preprocessed final data set and ending with the quantitative and qualitative evaluation of the resulting narrative maps.
  • Figure 2: Linear programming formulation of the extraction method of Keith and Mitra keith2020maps.
  • Figure 3: Sample narrative map extracted from news events spanning January to June 2018. Events are represented as nodes labeled with headlines and frames. Connections indicate narrative relationships between events. Inconsistencies in framing across the map highlight challenges in producing coherent framing narratives through the extraction process.