No abstract

No abstract

The COVID-19 pandemic highlighted the importance of validated and updated scientific information to help policy makers, healthcare professionals, and the public. The speed in disseminating reliable information and the subsequent guidelines and policy implementation are also essential to save as many lives as possible. Trustworthy guidelines should be based on a systematic evidence review which uses reproducible analytical methods to collect secondary data and analyse them. However, the guidelines’ drafting process is time consuming and requires a great deal of resources. This paper aims to highlight the importance of accelerating and streamlining the extraction and synthesis of scientific evidence, specifically within the systematic review process. To do so, this paper describes the COKE (COVID-19 Knowledge Extraction framework for next generation discovery science) Project, which involves the use of machine reading and deep learning to design and implement a semi-automated system that supports and enhances the systematic literature review and guideline drafting processes. Specifically, we propose a framework for aiding in the literature selection and navigation process that employs natural language processing and clustering techniques for selecting and organizing the literature for human consultation, according to PICO (Population/Problem, Intervention, Comparison, and Outcome) elements. We show some preliminary results of the automatic classification of sentences on a dataset of abstracts related to COVID-19.

Moral Foundations Theory is a socio-cognitive psychological theory that constitutes a general framework aimed at explaining the origin and evolution of human moral reasoning. Due to its dyadic structure of values and their violations, it can be used as a theoretical background for discerning moral values from natural language text as it captures a user's perspective on a specific topic. In this paper, we focus on the automatic detection of moral content in sentences or short paragraphs by means of machine learning techniques. We leverage on a corpus of tweets previously labeled as containing values or violations, according to the Moral Foundations Theory. We double evaluate the result of our work: (i) we compare the results of our model with the state of the art and (ii) we assess the proposed model in detecting the moral values with their polarity. The final outcome shows both an overall improvement in detecting moral content compared to the state of the art and adequate performances in detecting moral values with their sentiment polarity.