paper-with-me

홈 › Papers

Toxicity Detection: Does Context Really Matter?

2020-06-01 · ACL 2020 6 · John Pavlopoulos, Jeffrey Sorensen, Lucas Dixon, Nithum Thain, Ion Androutsopoulos

Moderation is crucial to promoting healthy on-line discussions. Although several `toxicity' detection datasets and models have been published, most of them ignore the context of the posts, implicitly assuming that comments maybe judged independently. We investigate this assumption by focusing on two questions: (a) does context affect the human judgement, and (b) does conditioning on context improve performance of toxicity detection systems? We experiment with Wikipedia conversations, limiting the notion of context to the previous post in the thread and the discussion title. We find that context can both amplify or mitigate the perceived toxicity of posts. Moreover, a small but significant subset of manually labeled posts (5% in one of our experiments) end up having the opposite toxicity labels if the annotators are not provided with context. Surprisingly, we also find no evidence that context actually improves the performance of toxicity classifiers, having tried a range of classifiers and mechanisms to make them context aware. This points to the need for larger datasets of comments annotated in context. We make our code and data publicly available.

📄 PDF Abstract BibTeX arXiv:2006.00998

Code (1)

ipavlopoulos/context_toxicity 공식 구현 tf

Similar Papers 제목 키워드 기반

Toxicity Detection can be Sensitive to the Conversational Context

2021-11-19 · Alexandros Xenos, John Pavlopoulos, Ion Androutsopoulos, Lucas Dixon 외

User posts whose perceived toxicity depends on the conversational context are rare in current toxicity detection datasets. Hence, toxicity detectors trained on existing datasets will also tend to disregard context, makin…

Data AugmentationKnowledge Distillation

Capturing the Flow of Art History

2022-12-07 · Chenxi Ji

Do we really understand how machine classifies art styles? Historically, art is perceived and interpreted by human eyes and there are always controversial discussions over how people identify and understand art. Historia…

Does Thermal Really Always Matter for RGB-T Salient Object Detection?

2022-10-09 · Runmin Cong, Kepu Zhang, Chen Zhang, Feng Zheng 외

In recent years, RGB-T salient object detection (SOD) has attracted continuous attention, which makes it possible to identify salient objects in environments such as low light by introducing thermal image. However, most …

object-detectionObject DetectionObject LocalizationRGB-T Salient Object Detection+1

Context Sensitivity Estimation in Toxicity Detection

2021-08-01 · ACL (WOAH) 2021 8 · Alexandros Xenos, John Pavlopoulos, Ion Androutsopoulos

User posts whose perceived toxicity depends on the conversational context are rare in current toxicity detection datasets. Hence, toxicity detectors trained on current datasets will also disregard context, making the det…

Sensitivity

Revisiting Contextual Toxicity Detection in Conversations

2021-11-24 · Atijit Anuchitanukul, Julia Ive, Lucia Specia

Understanding toxicity in user conversations is undoubtedly an important problem. Addressing "covert" or implicit cases of toxicity is particularly hard and requires context. Very few previous studies have analysed the i…

Data AugmentationToxic Comment Classification