Countering hate on social media: Large scale classification of hate and counter speech

• URL: http://arxiv.org/abs/2006.01974v3
• Date: Fri, 5 Jun 2020 20:38:27 GMT
• Title: Countering hate on social media: Large scale classification of hate and counter speech
• Authors: Joshua Garland and Keyan Ghazi-Zahedi and Jean-Gabriel Young and Laurent H\'ebert-Dufresne and Mirta Galesic
• Abstract summary: Hateful rhetoric is plaguing online discourse, fostering extreme societal movements and possibly giving rise to real-world violence. A potential solution is citizen-generated counter speech where citizens actively engage in hate-filled conversations to attempt to restore civil non-polarized discourse. Here we made use of a unique situation in Germany where self-labeling groups engaged in organized online hate and counter speech. We used an ensemble learning algorithm which pairs a variety of paragraph embeddings with regularized logistic regression functions to classify both hate and counter speech in a corpus of millions of relevant tweets from these two groups.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Hateful rhetoric is plaguing online discourse, fostering extreme societal movements and possibly giving rise to real-world violence. A potential solution to this growing global problem is citizen-generated counter speech where citizens actively engage in hate-filled conversations to attempt to restore civil non-polarized discourse. However, its actual effectiveness in curbing the spread of hatred is unknown and hard to quantify. One major obstacle to researching this question is a lack of large labeled data sets for training automated classifiers to identify counter speech. Here we made use of a unique situation in Germany where self-labeling groups engaged in organized online hate and counter speech. We used an ensemble learning algorithm which pairs a variety of paragraph embeddings with regularized logistic regression functions to classify both hate and counter speech in a corpus of millions of relevant tweets from these two groups. Our pipeline achieved macro F1 scores on out of sample balanced test sets ranging from 0.76 to 0.97---accuracy in line and even exceeding the state of the art. On thousands of tweets, we used crowdsourcing to verify that the judgments made by the classifier are in close alignment with human judgment. We then used the classifier to discover hate and counter speech in more than 135,000 fully-resolved Twitter conversations occurring from 2013 to 2018 and study their frequency and interaction. Altogether, our results highlight the potential of automated methods to evaluate the impact of coordinated counter speech in stabilizing conversations on social media.

Related papers

• When the Majority is Wrong: Modeling Annotator Disagreement for Subjective Tasks [45.14664901245331]
  A crucial problem in hate speech detection is determining whether a statement is offensive to a demographic group. We construct a model that predicts individual annotator ratings on potentially offensive text. We find that annotator ratings can be predicted using their demographic information and opinions on online content.
  arXiv  Detail & Related papers  (2023-05-11T07:55:20Z)
• CoSyn: Detecting Implicit Hate Speech in Online Conversations Using a Context Synergized Hyperbolic Network [52.85130555886915]
  CoSyn is a context-synergized neural network that explicitly incorporates user- and conversational context for detecting implicit hate speech in online conversations. We show that CoSyn outperforms all our baselines in detecting implicit hate speech with absolute improvements in the range of 1.24% - 57.8%.
  arXiv  Detail & Related papers  (2023-03-02T17:30:43Z)
• Collective moderation of hate, toxicity, and extremity in online discussions [1.114199733551736]
  We analyze a large corpus of more than 130,000 discussions on Twitter over four years. We identify different dimensions of discourse that might be related to the probability of hate speech in subsequent tweets. We find that expressing simple opinions, not necessarily supported by facts, relates to the least hate in subsequent discussions.
  arXiv  Detail & Related papers  (2023-03-01T09:35:26Z)
• Parsimonious Argument Annotations for Hate Speech Counter-narratives [4.825848785596437]
  We present an enrichment of the Hateval corpus of hate speech tweets (Basile et. al.) aimed to facilitate automated counter-narrative generation. We have also annotated tweets with argumentative information based on Wagemanns, that we believe can help in building convincing and effective counter-narratives for hate speech against particular groups. Preliminary results show that automatic annotators perform close to human annotators to detect some aspects of argumentation, while others only reach low or moderate level of inter-annotator agreement.
  arXiv  Detail & Related papers  (2022-08-01T18:58:32Z)
• AlexU-AIC at Arabic Hate Speech 2022: Contrast to Classify [2.9220076568786326]
  We present our submission to the Arabic Hate Speech 2022 Shared Task Workshop (OSACT5 2022) using the associated Arabic Twitter dataset. For offensive Tweets, sub-task B focuses on detecting whether the tweet is hate speech or not. For hate speech Tweets, sub-task C focuses on detecting the fine-grained type of hate speech among six different classes.
  arXiv  Detail & Related papers  (2022-07-18T12:33:51Z)
• Addressing the Challenges of Cross-Lingual Hate Speech Detection [115.1352779982269]
  In this paper we focus on cross-lingual transfer learning to support hate speech detection in low-resource languages. We leverage cross-lingual word embeddings to train our neural network systems on the source language and apply it to the target language. We investigate the issue of label imbalance of hate speech datasets, since the high ratio of non-hate examples compared to hate examples often leads to low model performance.
  arXiv  Detail & Related papers  (2022-01-15T20:48:14Z)
• Leveraging Transformers for Hate Speech Detection in Conversational Code-Mixed Tweets [36.29939722039909]
  This paper describes the system proposed by team MIDAS-IIITD for HASOC 2021 subtask 2. It is one of the first shared tasks focusing on detecting hate speech from Hindi-English code-mixed conversations on Twitter. Our best performing system, a hard voting ensemble of Indic-BERT, XLM-RoBERTa, and Multilingual BERT, achieved a macro F1 score of 0.7253.
  arXiv  Detail & Related papers  (2021-12-18T19:27:33Z)
• Unsupervised Domain Adaptation for Hate Speech Detection Using a Data Augmentation Approach [6.497816402045099]
  We propose an unsupervised domain adaptation approach to augment labeled data for hate speech detection. We show our approach improves Area under the Precision/Recall curve by as much as 42% and recall by as much as 278%.
  arXiv  Detail & Related papers  (2021-07-27T15:01:22Z)
• Impact and dynamics of hate and counter speech online [0.0]
  Citizen-generated counter speech is a promising way to fight hate speech and promote peaceful, non-polarized discourse. We analyze 180,000 political conversations that took place on German Twitter over four years.
  arXiv  Detail & Related papers  (2020-09-16T01:43:28Z)
• Racism is a Virus: Anti-Asian Hate and Counterspeech in Social Media during the COVID-19 Crisis [51.39895377836919]
  COVID-19 has sparked racism and hate on social media targeted towards Asian communities. We study the evolution and spread of anti-Asian hate speech through the lens of Twitter. We create COVID-HATE, the largest dataset of anti-Asian hate and counterspeech spanning 14 months.
  arXiv  Detail & Related papers  (2020-05-25T21:58:09Z)
• Echo Chambers on Social Media: A comparative analysis [64.2256216637683]
  We introduce an operational definition of echo chambers and perform a massive comparative analysis on 1B pieces of contents produced by 1M users on four social media platforms. We infer the leaning of users about controversial topics and reconstruct their interaction networks by analyzing different features. We find support for the hypothesis that platforms implementing news feed algorithms like Facebook may elicit the emergence of echo-chambers.
  arXiv  Detail & Related papers  (2020-04-20T20:00:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.