UPB @ ACTI: Detecting Conspiracies using fine tuned Sentence Transformers

Andrei Paraschiv, Mihai Dascalu
9/28/2023
cs.CLcs.AI

No confident code implementation found for this paper.

Abstract

Conspiracy theories have become a prominent and concerning aspect of online discourse, posing challenges to information integrity and societal trust. As such, we address conspiracy theory detection as proposed by the ACTI @ EVALITA 2023 shared task. The combination of pre-trained sentence Transformer models and data augmentation techniques enabled us to secure first place in the final leaderboard of both sub-tasks. Our methodology attained F1 scores of 85.71% in the binary classification and 91.23% for the fine-grained conspiracy topic classification, surpassing other competing systems.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

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

86% match2023

The Anatomy of Conspirators: Unveiling Traits using a Comprehensive Twitter Dataset

84% match2023

Classifying Conspiratorial Narratives At Scale: False Alarms and Erroneous Connections

83% match1 repo2024

ConspEmoLLM: Conspiracy Theory Detection Using an Emotion-Based Large Language Model

83% match1 repo132024

Who's Behind It? Annotating and Extracting Conspiratorial Actors from German Telegram Posts

82% match2026

Nexus at ArAIEval Shared Task: Fine-Tuning Arabic Language Models for Propaganda and Disinformation Detection

82% match2023

Cite this paper

@article{paraschiv2023acti,
  title  = {UPB @ ACTI: Detecting Conspiracies using fine tuned Sentence Transformers},
  author = {Andrei Paraschiv and Mihai Dascalu},
  year   = {2023},
  eprint = {2309.16275},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2309.16275v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2309.16275.svg)](https://codeofpaper.com/paper/2309.16275)

Discussion