ControversialQA: Exploring Controversy in Question Answering
This addresses the problem of improving controversy detection for researchers and practitioners in NLP, but it is incremental as it builds on prior work by shifting from sentiment-based to user-perception-based definitions.
The paper tackled the problem of defining and detecting controversy in online content by introducing ControversialQA, the first question-answering dataset that defines controversy based on user perception via votes, containing nearly 10K questions with best and controversial answers. The result showed that controversy detection in question answering is essential and challenging, with no strong correlation to sentiment tasks.
Controversy is widespread online. Previous studies mainly define controversy based on vague assumptions of its relation to sentiment such as hate speech and offensive words. This paper introduces the first question-answering dataset that defines content controversy by user perception, i.e., votes from plenty of users. It contains nearly 10K questions, and each question has a best answer and a most controversial answer. Experimental results reveal that controversy detection in question answering is essential and challenging, and there is no strong correlation between controversy and sentiment tasks.