When Large Language Models Do Not Work: Online Incivility Prediction through Graph Neural Networks

• URL: http://arxiv.org/abs/2512.07684v1
• Date: Mon, 08 Dec 2025 16:22:40 GMT
• Title: When Large Language Models Do Not Work: Online Incivility Prediction through Graph Neural Networks
• Authors: Zihan Chen, Lanyu Yu,
• Abstract summary: We propose a Graph Neural Network framework for detecting three types of uncivil behavior within the English Wikipedia community.<n>Our model represents each user comment as a node, with textual similarity between comments defining the edges.<n>We also introduce a dynamically adjusted attention mechanism that adaptively balances nodal and topological features during information aggregation.
• Score: 3.353377687171614
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Online incivility has emerged as a widespread and persistent problem in digital communities, imposing substantial social and psychological burdens on users. Although many platforms attempt to curb incivility through moderation and automated detection, the performance of existing approaches often remains limited in both accuracy and efficiency. To address this challenge, we propose a Graph Neural Network (GNN) framework for detecting three types of uncivil behavior (i.e., toxicity, aggression, and personal attacks) within the English Wikipedia community. Our model represents each user comment as a node, with textual similarity between comments defining the edges, allowing the network to jointly learn from both linguistic content and relational structures among comments. We also introduce a dynamically adjusted attention mechanism that adaptively balances nodal and topological features during information aggregation. Empirical evaluations demonstrate that our proposed architecture outperforms 12 state-of-the-art Large Language Models (LLMs) across multiple metrics while requiring significantly lower inference cost. These findings highlight the crucial role of structural context in detecting online incivility and address the limitations of text-only LLM paradigms in behavioral prediction. All datasets and comparative outputs will be publicly available in our repository to support further research and reproducibility.

Related papers

• Interpretable Debiasing of Vision-Language Models for Social Fairness [55.85977929985967]
  We introduce an interpretable, model-agnostic bias mitigation framework, DeBiasLens, that localizes social attribute neurons in Vision-Language models.<n>We train SAEs on facial image or caption datasets without corresponding social attribute labels to uncover neurons highly responsive to specific demographics.<n>Our research lays the groundwork for future auditing tools, prioritizing social fairness in emerging real-world AI systems.
  arXiv  Detail & Related papers  (2026-02-27T13:37:11Z)
• Graphically Speaking: Unmasking Abuse in Social Media with Conversation Insights [10.188075925271471]
  Abusive language in social media conversations depends on the conversational context, characterized by the content and topology of preceding comments.<n>Traditional Abusive Language Detection models often overlook this context, which can lead to unreliable performance metrics.<n>Recent Natural Language Processing (NLP) methods that integrate conversational context often depend on limited and simplified representations, and report inconsistent results.<n>We propose a novel approach that utilize graph neural networks (GNNs) to model social media conversations as graphs, where nodes represent comments, and edges capture reply structures.
  arXiv  Detail & Related papers  (2025-04-02T17:03:37Z)
• Transcending the Attention Paradigm: Representation Learning from Geospatial Social Media Data [1.8311821879979955]
  This study challenges the paradigm of performance benchmarking by investigating social media data as a source of distributed patterns. To properly represent these abstract relationships, this research dissects empirical social media corpora into their elemental components, analyzing over two billion tweets across population-dense locations.
  arXiv  Detail & Related papers  (2023-10-09T03:27:05Z)
• Foundational Models Defining a New Era in Vision: A Survey and Outlook [151.49434496615427]
  Vision systems to see and reason about the compositional nature of visual scenes are fundamental to understanding our world. The models learned to bridge the gap between such modalities coupled with large-scale training data facilitate contextual reasoning, generalization, and prompt capabilities at test time. The output of such models can be modified through human-provided prompts without retraining, e.g., segmenting a particular object by providing a bounding box, having interactive dialogues by asking questions about an image or video scene or manipulating the robot's behavior through language instructions.
  arXiv  Detail & Related papers  (2023-07-25T17:59:18Z)
• Graph Neural Networks for Multi-Robot Active Information Acquisition [15.900385823366117]
  A team of mobile robots, communicating through an underlying graph, estimates a hidden state expressing a phenomenon of interest. Existing approaches are either not scalable, unable to handle dynamic phenomena or not robust to changes in the communication graph. We propose an Information-aware Graph Block Network (I-GBNet) that aggregates information over the graph representation and provides sequential-decision making in a distributed manner.
  arXiv  Detail & Related papers  (2022-09-24T21:45:06Z)
• Interpretable part-whole hierarchies and conceptual-semantic relationships in neural networks [4.153804257347222]
  We present Agglomerator, a framework capable of providing a representation of part-whole hierarchies from visual cues. We evaluate our method on common datasets, such as SmallNORB, MNIST, FashionMNIST, CIFAR-10, and CIFAR-100.
  arXiv  Detail & Related papers  (2022-03-07T10:56:13Z)
• Detecting Offensive Language on Social Networks: An End-to-end Detection Method based on Graph Attention Networks [7.723697303436006]
  We propose an end-to-end method based on community structure and text features for offensive language detection (CT-OLD) We add user opinion to the community structure for representing user features. The user opinion is represented by user historical behavior information, which outperforms that represented by text information.
  arXiv  Detail & Related papers  (2022-03-04T03:57:18Z)
• Spatial-Temporal Sequential Hypergraph Network for Crime Prediction [56.41899180029119]
  We propose Spatial-Temporal Sequential Hypergraph Network (ST-SHN) to collectively encode complex crime spatial-temporal patterns. In particular, to handle spatial-temporal dynamics under the long-range and global context, we design a graph-structured message passing architecture. We conduct extensive experiments on two real-world datasets, showing that our proposed ST-SHN framework can significantly improve the prediction performance.
  arXiv  Detail & Related papers  (2022-01-07T12:46:50Z)
• Improving Classifier Training Efficiency for Automatic Cyberbullying Detection with Feature Density [58.64907136562178]
  We study the effectiveness of Feature Density (FD) using different linguistically-backed feature preprocessing methods. We hypothesise that estimating dataset complexity allows for the reduction of the number of required experiments. The difference in linguistic complexity of datasets allows us to additionally discuss the efficacy of linguistically-backed word preprocessing.
  arXiv  Detail & Related papers  (2021-11-02T15:48:28Z)
• Explainable Adversarial Attacks in Deep Neural Networks Using Activation Profiles [69.9674326582747]
  This paper presents a visual framework to investigate neural network models subjected to adversarial examples. We show how observing these elements can quickly pinpoint exploited areas in a model.
  arXiv  Detail & Related papers  (2021-03-18T13:04:21Z)
• Generative Counterfactuals for Neural Networks via Attribute-Informed Perturbation [51.29486247405601]
  We design a framework to generate counterfactuals for raw data instances with the proposed Attribute-Informed Perturbation (AIP) By utilizing generative models conditioned with different attributes, counterfactuals with desired labels can be obtained effectively and efficiently. Experimental results on real-world texts and images demonstrate the effectiveness, sample quality as well as efficiency of our designed framework.
  arXiv  Detail & Related papers  (2021-01-18T08:37:13Z)

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.