One size fits all: Enhanced zero-shot text classification for patient listening on social media

TL;DR

This paper introduces an AI framework to analyze social media for patient insights in drug development with minimal manual effort.

Contribution

A novel zero-shot text classification framework for patient listening with minimal annotation effort.

Findings

The framework identifies interest groups, challenges, and treatment insights from social media data.

Minimal annotation effort is achieved by leveraging ontologies and zero-shot classification.

Initial meaningful insights are extracted for patient-focused drug development topics.

Abstract

Patient-focused drug development (PFDD) represents a transformative approach that is reshaping the pharmaceutical landscape by centering on patients throughout the drug development process. Recent advancements in Artificial Intelligence (AI), especially in Natural Language Processing (NLP), have enabled the analysis of vast social media datasets, also called Social Media Listening (SML), providing insights not only into patient perspectives but also into those of other interest groups such as caregivers. In this method study, we propose an NLP framework that—given a particular disease—is designed to extract pertinent information related to three primary research topics: identification of interest groups, understanding of challenges, and assessing treatments and support systems. Leveraging external resources like ontologies and employing various NLP techniques, particularly zero-shot text classification, the presented framework yields initial meaningful insights into these research topics with minimal annotation effort.

Figures