chzuo/adma2023_tweet_IR

Cross-genre Retrieval for Information Integrity: A COVID-19 Case Study

Accepted at ADMA 2023

This repository contains the accompanying data and code for the paper, where we present an ad hoc information retrieval (IR) task for identifying support for claims made in tweets about COVID-19 from reputable news outlets.

Dataset

The dataset for the IR Task can be accessed here.

Instructions on Usage.

Our approach consists of two steps:

1. Selecting the most relevant candidates from a collection of 57k news articles, and
2. Re-rankingthis the candidates list.

• For code related to step 1, see Phase1
• For code related to step 2, see Phase2

Citation

If you use this work please cite our research paper: