English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

An increasing number of people now rely on online platforms to meet theirhealth information needs. Thus identifying inconsistent or conflicting textualhealth information has become a safety-critical task. Health advice data posesa unique challenge where information that is accurate in the context of onediagnosis can be conflicting in the context of another. For example, peoplesuffering from diabetes and hypertension often receive conflicting healthadvice on diet. This motivates the need for technologies which can providecontextualized, user-specific health advice. A crucial step towardscontextualized advice is the ability to compare health advice statements anddetect if and how they are conflicting. This is the task of health conflictdetection (HCD). Given two pieces of health advice, the goal of HCD is todetect and categorize the type of conflict. It is a challenging task, as (i)automatically identifying and categorizing conflicts requires a deeperunderstanding of the semantics of the text, and (ii) the amount of availabledata is quite limited.  In this study, we are the first to explore HCD in the context of pre-trainedlanguage models. We find that DeBERTa-v3 performs best with a mean F1 score of0.68 across all experiments. We additionally investigate the challenges posedby different conflict types and how synthetic data improves a model'sunderstanding of conflict-specific semantics. Finally, we highlight thedifficulty in collecting real health conflicts and propose a human-in-the-loopsynthetic data augmentation approach to expand existing HCD datasets. Our HCDtraining dataset is over 2x bigger than the existing HCD dataset and is madepublicly available on Github.

Scope of Pre-trained Language Models for Detecting Conflicting Health Information