LAMBRETTA: Learning to Rank for Twitter Soft Moderation

TL;DR

LAMBRETTA is an automated system that uses Learning To Rank to effectively identify tweets containing false information, significantly aiding moderation efforts on Twitter with high accuracy and coverage.

Contribution

The paper introduces LAMBRETTA, a novel Learning To Rank-based approach for detecting false claims on Twitter, outperforming existing keyword and semantic search methods.

Findings

Flags over 20 times more tweets than Twitter's current moderation.

Achieves 3.93% false positives and 18.81% false negatives.

Outperforms state-of-the-art keyword and semantic search methods.

Abstract

To curb the problem of false information, social media platforms like Twitter started adding warning labels to content discussing debunked narratives, with the goal of providing more context to their audiences. Unfortunately, these labels are not applied uniformly and leave large amounts of false content unmoderated. This paper presents LAMBRETTA, a system that automatically identifies tweets that are candidates for soft moderation using Learning To Rank (LTR). We run LAMBRETTA on Twitter data to moderate false claims related to the 2020 US Election and find that it flags over 20 times more tweets than Twitter, with only 3.93% false positives and 18.81% false negatives, outperforming alternative state-of-the-art methods based on keyword extraction and semantic search. Overall, LAMBRETTA assists human moderators in identifying and flagging false information on social media.