Why Should This Article Be Deleted? Transparent Stance Detection in Multilingual Wikipedia Editor Discussions

TL;DR

A novel multilingual dataset of Wikipedia editor discussions along with their reasoning in three languages is constructed and it is demonstrated that stance and corresponding reason can be predicted jointly with a high degree of accuracy, adding transparency to the decision-making process.

Abstract

The moderation of content on online platforms is usually non-transparent. On Wikipedia, however, this discussion is carried out publicly and the editors are encouraged to use the content moderation policies as explanations for making moderation decisions. Currently, only a few comments explicitly mention those policies -- 20% of the English ones, but as few as 2% of the German and Turkish comments. To aid in this process of understanding how content is moderated, we construct a novel multilingual dataset of Wikipedia editor discussions along with their reasoning in three languages. The dataset contains the stances of the editors (keep, delete, merge, comment), along with the stated reason, and a content moderation policy, for each edit decision. We demonstrate that stance and corresponding reason (policy) can be predicted jointly with a high degree of accuracy, adding transparency to the decision-making process. We release both our joint prediction models and the multilingual content moderation dataset for further research on automated transparent content moderation.

Figures (4)

• Figure 1: Example comment from the dataset
• Figure 2: Overview of the approach for policy prediction and stance detection
• Figure 3: The 15 most frequently used policies across comments for (a) English, (b) German, and (c) Turkish.
• Figure 4: Most salient bi-grams for each label in the training set