Controversy Detection: a Text and Graph Neural Network Based Approach - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Web Information Systems Engineering – WISE 2021 Année : 2021

Controversy Detection: a Text and Graph Neural Network Based Approach

Détection de sujets controversés: une approche combinant informations textuelles et les réseaux de neurones graphiques

Résumé

Controversial content refers to any content that attracts both positive and negative feedback. Its automatic identification, especially on social media, is a challenging task as it should be done on a large number of continuously evolving posts, covering a large variety of topics. Most of the existing approaches rely on the graph structure of a topic-discussion and/or the content of messages. This paper proposes a controversy detection approach based on both graph structure of a discussion and text features. Our proposed approach relies on Graph Neural Network (gnn) to encode the graph representation (including its texts) in an embedding vector before performing a graph classification task. The latter will classify the post as controversial or not. Two controversy detection strategies are proposed. The first one is based on a hierarchical graph representation learning. Graph user nodes are embedded hierarchically and iteratively to compute the whole graph embedding vector. The second one is based on the attention mechanism, which allows each user node to give more or less importance to its neighbors when computing node embeddings. We conduct experiments to evaluate our approach using different real-world datasets. Conducted experiments show the positive impact of combining textual features and structural information in terms of performance.
Fichier principal
Vignette du fichier
Controversy_Detection__a_Text_and_Graph_Neural_Network_Based_Approach.pdf (422.47 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03464243 , version 1 (03-12-2021)

Identifiants

Citer

Samy Benslimane, Jérôme Azé, Sandra Bringay, Maximilien Servajean, Caroline Mollevi. Controversy Detection: a Text and Graph Neural Network Based Approach. WISE 2021 - 22nd International Conference on Web Information Systems Engineering, Oct 2021, Melbourne, Australia. pp.339-354, ⟨10.1007/978-3-030-90888-1_26⟩. ⟨hal-03464243⟩
127 Consultations
278 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More