Biodiversity Observations Miner: A web application to unlock primary biodiversity data from published literature

Abstract

BackgroundA considerable portion of primary biodiversity data is digitally locked inside published literature which is often stored as pdf files. Large-scale approaches to biodiversity science could benefit from retrieving this information and making it digitally accessible and machine-readable. Nonetheless, the amount and diversity of digitally published literature pose many challenges for knowledge discovery and retrieval. Text mining has been extensively used for data discovery tasks in large quantities of documents. However, text mining approaches for knowledge discovery and retrieval have been limited in biodiversity science compared to other disciplines.New informationHere, we present a novel, open source text mining tool, the Biodiversity Observations Miner (BOM). This web application, written in R, allows the semi-automated discovery of punctual biodiversity observations (e.g. biotic interactions, functional or behavioural traits and natural history descriptions) associated with the scientific names present inside a corpus of scientific literature. Furthermore, BOM enable users the rapid screening of large quantities of literature based on word co-occurrences that match custom biodiversity dictionaries. This tool aims to increase the digital mobilisation of primary biodiversity data and is freely accessible via GitHub or through a web server.

Past and future uses of text mining in ecology and evolution

“…With dictionaries containing terms of interest (e.g. species names, traits, keywords describing an ecological interaction), the frequency of term co-occurrences can be used to discover associations [49]. For example, by quantifying the co-occurrence frequencies of ant species names and terms describing ant-plant mutualisms, Kaur et al [50] were able to identify ant species associated with mutualistic behaviours, and used the compiled dataset to study the evolution of plant mutualisms.…”

Past and future uses of text mining in ecology & evolution

“…Applying NLP approaches, unstructured texts can be transformed into structured data commonly analyzed in ecological and evolutionary studies. With dictionaries containing terms of interest (e.g., species names, traits, keywords describing an ecological interaction), the frequency of term co-occurrences can be used to discover associations [44]. For example, by quantifying the co-occurrence frequencies of ant species names and terms describing ant-plant mutualisms, [45] were able to identify ant species associated with mutualistic behaviours, and used the compiled dataset to study the evolution of plant mutualisms.…”

TaxoNERD: Deep neural models for the recognition of taxonomic entities in the ecological and evolutionary literature

“…While these toolkits often provide deep models for biomedical NLP, there is so far no such models for ecological applications. As new use cases emerge, including the need to extract factual statements from the ecological literature to augment biodiversity databases with up‐to‐date information, ecological information extraction sees a resurgence of interest from the community (Chaix et al., 2019; Compson et al., 2018; Muñoz et al., 2019; Nguyen et al., 2019; Tamaddoni‐Nezhad et al., 2013; Thessen & Parr, 2014). However, ecologists still lack the tools to build biodiversity information extraction pipelines with state‐of‐the‐art performance.…”

“…This network of interconnected entities forms what is commonly known as a knowledge graph (Ji et al, 2021). Knowledge graphs are a cornerstone of modern artificial intelligence applications factual statements from the ecological literature to augment biodiversity databases with up-to-date information, ecological information extraction sees a resurgence of interest from the community (Chaix et al, 2019;Compson et al, 2018;Muñoz et al, 2019;Nguyen et al, 2019;Tamaddoni-Nezhad et al, 2013;Thessen & Parr, 2014).…”