Data-driven classification of the certainty of scholarly assertions

Abstract

The grammatical structures scholars use to express their assertions are intended to convey various degrees of certainty or speculation. Prior studies have suggested a variety of categorization systems for scholarly certainty; however, these have not been objectively tested for their validity, particularly with respect to representing the interpretation by the reader, rather than the intention of the author. In this study, we use a series of questionnaires to determine how researchers classify various scholarly assertions, using three distinct certainty classification systems. We find that there are three distinct categories of certainty along a spectrum from high to low. We show that these categories can be detected in an automated manner, using a machine learning model, with a cross-validation accuracy of 89.2% relative to an author-annotated corpus, and 82.2% accuracy against a publicly-annotated corpus. This finding provides an opportunity for contextual metadata related to certainty to be captured as a part of text-mining pipelines, which currently miss these subtle linguistic cues. We provide an exemplar machine-accessible representation—a Nanopublication—where certainty category is embedded as metadata in a formal, ontology-based manner within text-mined scholarly assertions.

Anatomy Knowledge Graphs: Toward FAIR morphological data

“…For each statement unit, users can specify the level of the statement's certainty or confidence. This is a statement about a statement, linking the node of the target Statement Unit to a resource indicating the certainty of the assertioninformation that can be useful for identifying citation distortions, in which mere possible claims become well-established facts through a chain of citations [29].…”

2nd Workshop on Digital Infrastructures for Scholarly Content Objects (DISCO'22)

“…Further, context-specific information inside a paper may not be immediately reusable when extracted by automated processes, leading to apparent contradictions [15]. Current mitigating approaches use the underlying reasoning for information retrieval [1,13], develop new infrastructures analyzing the reasoning [5,11,21] or certainty [14] of statements, or use visualization to highlight possible discrepancies [8,11]. Moreover, new retrieval models based on narrative intelligence try to foster coherence and plausibility of scientific argumentation [9,12,18].…”