# Wikipedia is Not a Dictionary, Delete! Text Classification as a Proxy for Analysing Wiki Deletion Discussions

arXiv: https://arxiv.org/abs/2503.10294 · HTML: https://mlsanity.com/paper/2503.10294/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 30 references that are in the map.
- First posted on arXiv 13 Mar 2025.

## Builds on (most cited first, 13 of 13)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classification](https://mlsanity.com/paper/2010.12421/) (2020)
- [Efficient Few-Shot Learning Without Prompts](https://mlsanity.com/paper/2209.11055/) (2022)
- [TimeLMs: Diachronic Language Models from Twitter](https://mlsanity.com/paper/2202.03829/) (2022)
- [The Rise of AI-Generated Content in Wikipedia](https://mlsanity.com/paper/2410.08044/) (2024)
- [Why the World Reads Wikipedia: Beyond English Speakers](https://mlsanity.com/paper/1812.00474/) (2018)
- [Automated Content Moderation Increases Adherence to Community Guidelines](https://mlsanity.com/paper/2210.10454/) (2022)
- [Why We Read Wikipedia](https://mlsanity.com/paper/1702.05379/) (2017)
- [Why Should This Article Be Deleted? Transparent Stance Detection in Multilingual Wikipedia Editor Discussions](https://mlsanity.com/paper/2310.05779/) (2023)
- [WiDe-analysis: Enabling One-click Content Moderation Analysis on Wikipedia's Articles for Deletion](https://mlsanity.com/paper/2408.05655/) (2024)

## Abstract (arXiv)

Automated content moderation for collaborative knowledge hubs like Wikipedia or Wikidata is an important yet challenging task due to multiple factors. In this paper, we construct a database of discussions happening around articles marked for deletion in several Wikis and in three languages, which we then use to evaluate a range of LMs on different tasks (from predicting the outcome of the discussion to identifying the implicit policy an individual comment might be pointing to). Our results reveal, among others, that discussions leading to deletion are easier to predict, and that, surprisingly, self-produced tags (keep, delete or redirect) don't always help guiding the classifiers, presumably because of users' hesitation or deliberation within comments.