# SemEval-2019 Task 8: Fact Checking in Community Question Answering Forums

## TL;DR

This paper introduces SemEval-2019 Task 8, focusing on fact checking in community question answering forums through two subtasks: classifying question types and verifying answer correctness, with system evaluations and baseline comparisons.

## Contribution

It presents a new benchmark dataset and evaluation framework for fact checking in community QA forums, along with analysis of system performances.

## Key findings

- All systems improved over the baseline in Subtask A.
- All systems underperformed in Subtask B but some approached the baseline.
- The dataset and leaderboard are publicly available for future research.

## Abstract

We present SemEval-2019 Task 8 on Fact Checking in Community Question Answering Forums, which features two subtasks. Subtask A is about deciding whether a question asks for factual information vs. an opinion/advice vs. just socializing. Subtask B asks to predict whether an answer to a factual question is true, false or not a proper answer. We received 17 official submissions for subtask A and 11 official submissions for Subtask B. For subtask A, all systems improved over the majority class baseline. For Subtask B, all systems were below a majority class baseline, but several systems were very close to it. The leaderboard and the data from the competition can be found at http://competitions.codalab.org/competitions/20022