ACTI at EVALITA 2023: Overview of the Conspiracy Theory Identification Task

TL;DR

The ACTI challenge at EVALITA 2023 introduced a new shared task focused on identifying and categorizing conspiracy theories in Telegram comments, highlighting the effectiveness of large language models in this domain.

Contribution

This paper presents the first shared task on conspiracy theory identification, providing a benchmark dataset and evaluating approaches based on large language models.

Findings

Large language models achieved top performance in conspiracy content classification.

The shared task attracted 15 teams with 81 submissions.

Utilization of language models can aid in counteracting misinformation online.

Abstract

Conspiracy Theory Identication task is a new shared task proposed for the first time at the Evalita 2023. The ACTI challenge, based exclusively on comments published on conspiratorial channels of telegram, is divided into two subtasks: (i) Conspiratorial Content Classification: identifying conspiratorial content and (ii) Conspiratorial Category Classification about specific conspiracy theory classification. A total of fifteen teams participated in the task for a total of 81 submissions. We illustrate the best performing approaches were based on the utilization of large language models. We finally draw conclusions about the utilization of these models for counteracting the spreading of misinformation in online platforms.