Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Using Natural Language Processing and Networks to Automate Structured Literature Reviews: An Application to Farmers Climate Change Adaptation

Sofia Gil-Clavel, Tatiana Filatova

TL;DR

The paper addresses the challenge of keeping up with rapidly growing literature and opaque black-box summarization by proposing an NLP-supported, network-based framework for descriptive literature reviews. It develops a pipeline that extracts and contextualizes findings from articles, encodes variable relationships with a verb-sign dictionary, and visualizes results as interpretable networks, specifically applied to farmers' climate-change adaptation. The approach is benchmarked against traditional text-summarization methods using Dang et al. (2019) as a gold standard and is further evaluated by human experts, showing superior readability and closer alignment with established findings. The methodology offers a fast, theory-grounded tool for synthesis in interdisciplinary, climate-focused domains, while acknowledging limitations in subjectivity and the descriptive nature of the results.

Abstract

The fast-growing number of research articles makes it problematic for scholars to keep track of the new findings related to their areas of expertise. Furthermore, linking knowledge across disciplines in rapidly developing fields becomes challenging for complex topics like climate change that demand interdisciplinary solutions. At the same time, the rise of Black Box types of text summarization makes it difficult to understand how text relationships are built, let alone relate to existing theories conceptualizing cause-effect relationships and permitting hypothesizing. This work aims to sensibly use Natural Language Processing by extracting variables relations and synthesizing their findings using networks while relating to key concepts dominant in relevant disciplines. As an example, we apply our methodology to the analysis of farmers' adaptation to climate change. For this, we perform a Natural Language Processing analysis of publications returned by Scopus in August 2022. Results show that the use of Natural Language Processing together with networks in a descriptive manner offers a fast and interpretable way to synthesize literature review findings as long as researchers back up results with theory.

Using Natural Language Processing and Networks to Automate Structured Literature Reviews: An Application to Farmers Climate Change Adaptation

TL;DR

The paper addresses the challenge of keeping up with rapidly growing literature and opaque black-box summarization by proposing an NLP-supported, network-based framework for descriptive literature reviews. It develops a pipeline that extracts and contextualizes findings from articles, encodes variable relationships with a verb-sign dictionary, and visualizes results as interpretable networks, specifically applied to farmers' climate-change adaptation. The approach is benchmarked against traditional text-summarization methods using Dang et al. (2019) as a gold standard and is further evaluated by human experts, showing superior readability and closer alignment with established findings. The methodology offers a fast, theory-grounded tool for synthesis in interdisciplinary, climate-focused domains, while acknowledging limitations in subjectivity and the descriptive nature of the results.

Abstract

The fast-growing number of research articles makes it problematic for scholars to keep track of the new findings related to their areas of expertise. Furthermore, linking knowledge across disciplines in rapidly developing fields becomes challenging for complex topics like climate change that demand interdisciplinary solutions. At the same time, the rise of Black Box types of text summarization makes it difficult to understand how text relationships are built, let alone relate to existing theories conceptualizing cause-effect relationships and permitting hypothesizing. This work aims to sensibly use Natural Language Processing by extracting variables relations and synthesizing their findings using networks while relating to key concepts dominant in relevant disciplines. As an example, we apply our methodology to the analysis of farmers' adaptation to climate change. For this, we perform a Natural Language Processing analysis of publications returned by Scopus in August 2022. Results show that the use of Natural Language Processing together with networks in a descriptive manner offers a fast and interpretable way to synthesize literature review findings as long as researchers back up results with theory.
Paper Structure (12 sections, 3 equations, 5 figures, 3 tables)

This paper contains 12 sections, 3 equations, 5 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Methodology
  3. General Overview of the Algorithm
  4. Aesthetics of the Network Visualization
  5. Network Visualization of NLP-supported Findings vs. Text Summarization Systems
  6. Network Visualization of NLP-supported Findings
  7. Text Summarization Systems
  8. Human Comparison of Both Methodologies
  9. Conclusions
  10. Limitations and Future Work
  11. Articles used to build the database
  12. Verbs Findings Dictionary

Figures (5)

  • Figure 1: Flow chart diagram presenting our algorithm based on Bui et al. bui_extractive_2016. Boxes with bold text signal the novel steps added in the framework presented here.
  • Figure 2: Workflow chart diagram
  • Figure 3: Example of a sentence transformation into directed network.
  • Figure 4: Clustered networks of nodes that target nodes containing the word "adaptation".
  • Figure 5: The complete network of all terms associated with farmers' climate change adaptation in the processed literature.