# CLEARumor at SemEval-2019 Task 7: ConvoLving ELMo Against Rumors

## TL;DR

This paper presents a neural network approach using ELMo embeddings for classifying rumor interactions and veracity in social media, achieving competitive results in SemEval-2019 Task 7.

## Contribution

It introduces a CNN and MLP-based system leveraging ELMo embeddings for rumor classification and veracity prediction, with detailed analysis and ablation studies.

## Key findings

- Achieved 44.6% F1-score in classifying rumor interactions.
- Achieved 30.1% F1-score in predicting rumor veracity.
- Second place in the SemEval-2019 Task 7 competition.

## Abstract

This paper describes our submission to SemEval-2019 Task 7: RumourEval: Determining Rumor Veracity and Support for Rumors. We participated in both subtasks. The goal of subtask A is to classify the type of interaction between a rumorous social media post and a reply post as support, query, deny, or comment. The goal of subtask B is to predict the veracity of a given rumor. For subtask A, we implement a CNN-based neural architecture using ELMo embeddings of post text combined with auxiliary features and achieve a F1-score of 44.6%. For subtask B, we employ a MLP neural network leveraging our estimates for subtask A and achieve a F1-score of 30.1% (second place in the competition). We provide results and analysis of our system performance and present ablation experiments.