Abstract
Complex interactions among multiple abiotic and biotic drivers result in rapid changes in ecosystems worldwide. Predicting how specific interactions can cause ripple effects potentially resulting in abrupt shifts in ecosystems is of high relevance to policymakers, but difficult to quantify using data from singular cases. We present causalizeR (https://github.com/fjmurguzur/causalizeR), a text-processing algorithm that extracts causal relations from literature based on simple grammatical rules that can be used to synthesize evidence in unstructured texts in a structured manner. The algorithm extracts causal links using the relative position of nouns relative to the keyword of choice to extract the cause and effects of interest. The resulting database can be combined with network analysis tools to estimate the direct and indirect effects of multiple drivers at the network level, which is useful for synthesizing available knowledge and for hypothesis creation and testing. We illustrate the use of the algorithm by detecting causal relationships in scientific literature relating to the tundra ecosystem.
Highlights
One of the major challenges for ecosystem scientists is to unravel the complex interactions among drivers that can explain how ecosystems are responding to global warming and human impacts (LaDeau et al, 2017; Peters & Okin, 2017)
A manual word cleanup is needed after the algorithm has processed the texts to remove clearly nonsensical relationships that arise due to word placement, e.g., ‘‘our results show an increase in productivity’’ will return the causal relationship of results-increaseproductivity, which does not provide us with useful information due to lack of context
Our algorithm extracts causal links reported in published literature by means of simple grammatical rules that offer high flexibility to process unstructured texts and identifies the interactions between the components of ecosystem change
Summary
One of the major challenges for ecosystem scientists is to unravel the complex interactions among drivers that can explain how ecosystems are responding to global warming and human impacts (LaDeau et al, 2017; Peters & Okin, 2017). Synthesizing evidence from literature is a necessary step to identify potential drivers and interactions that could influence changes in ecosystems as a result of climate change (Hassani, Huang & Silva, 2019). Due to the large amount of work necessary to extract the relevant information from each published article, most evidence syntheses narrow down the focus to a limited set of interactions in ecosystems that will change as a result of the accelerating global changes. Natural language processing tools offer the opportunity to classify literature into topics based on the words that are contained in the text (Blei, Ng & Jordan, 2003; Syed & Weber, 2018).
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
