# RecSOI: recommending research directions using statements of ignorance

**Authors:** Adrien Bibal, Nourah M. Salem, Rémi Cardon, Elizabeth K. White, Daniel E. Acuna, Robin Burke, Lawrence E. Hunter

PMC · DOI: 10.1186/s13326-024-00304-3 · 2024-04-22

## TL;DR

RecSOI is a system that recommends research directions by analyzing statements of ignorance in scientific literature.

## Contribution

Introduces RecSOI, a novel recommender system for personalized research direction suggestions based on statements of ignorance.

## Key findings

- RecSOI generates personalized research recommendations by analyzing textual elements in scientific literature.
- The system provides contextual information to help researchers assess the relevance of suggested directions.
- Evaluation shows RecSOI effectively guides researchers through a vast landscape of potential research avenues.

## Abstract

The more science advances, the more questions are asked. This compounding growth can make it difficult to keep up with current research directions. Furthermore, this difficulty is exacerbated for junior researchers who enter fields with already large bases of potentially fruitful research avenues. In this paper, we propose a novel task and a recommender system for research directions, RecSOI, that draws from statements of ignorance (SOIs) found in the research literature. By building researchers’ profiles based on textual elements, RecSOI generates personalized recommendations of potential research directions tailored to their interests. In addition, RecSOI provides context for the recommended SOIs, so that users can quickly evaluate how relevant the research direction is for them. In this paper, we provide an overview of RecSOI’s functioning, implementation, and evaluation, demonstrating its effectiveness in guiding researchers through the vast landscape of potential research directions.

## Full-text entities

- **Diseases:** PMID (MESH:C537985), LLMs (MESH:D007806), prenatal nutrition (MESH:D044342), abnormalities (MESH:D000014), apnea (MESH:D001049), COVID-19 (MESH:D000086382), structural abnormalities (MESH:C566527)
- **Chemicals:** GPT-3.5 (-), PS (MESH:D010758), fatty acid (MESH:D005227)
- **Species:** Homo sapiens (human, species) [taxon 9606]

## Figures

2 figures with captions in the complete paper: https://tomesphere.com/paper/PMC11034121/full.md

---
Source: https://tomesphere.com/paper/PMC11034121