# Personalized Prediction of Offensive News Comments by Considering the Characteristics of Commenters

arXiv: https://arxiv.org/abs/2212.13205 · HTML: https://mlsanity.com/paper/2212.13205/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 15 references that are in the map.
- First posted on arXiv 26 Dec 2022.

## Builds on (most cited first, 7 of 7)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detection](https://mlsanity.com/paper/2111.07997/) (2021)
- [Designing Toxic Content Classification for a Diversity of Perspectives](https://mlsanity.com/paper/2106.04511/) (2021)
- [Convolutional Neural Networks for Toxic Comment Classification](https://mlsanity.com/paper/1802.09957/) (2018)
- [The Structure of Toxic Conversations on Twitter](https://mlsanity.com/paper/2105.11596/) (2021)
- [Something's Brewing! Early Prediction of Controversy-causing Posts from Discussion Features](https://mlsanity.com/paper/1904.07372/) (2019)

## Abstract (arXiv)

When reading news articles on social networking services and news sites, readers can view comments marked by other people on these articles. By reading these comments, a reader can understand the public opinion about the news, and it is often helpful to grasp the overall picture of the news. However, these comments often contain offensive language that readers do not prefer to read. This study aims to predict such offensive comments to improve the quality of the experience of the reader while reading comments. By considering the diversity of the readers' values, the proposed method predicts offensive news comments for each reader based on the feedback from a small number of news comments that the reader rated as "offensive" in the past. In addition, we used a machine learning model that considers the characteristics of the commenters to make predictions, independent of the words and topics in news comments. The experimental results of the proposed method show that prediction can be personalized even when the amount of readers' feedback data used in the prediction is limited. In particular, the proposed method, which considers the commenters' characteristics, has a low probability of false detection of offensive comments.