GENE: Graph generation conditioned on named entities for polarity and controversy detection in social media
作者：
Highlights：
• We introduce GENE, a new representation of social networks conditioned on named entities.
• We study controversy in scenarios where there are positive, negative, and neutral poles.
• We show that GENE has predictive capabilities, favoring the early forecast of the polarization of a social network.
• Our experiments show that users’ comments on news that involve a specific group of entities are predictable.
• We release a dataset that includes news and conversational threads from which this study was conducted.
摘要
•We introduce GENE, a new representation of social networks conditioned on named entities.•We study controversy in scenarios where there are positive, negative, and neutral poles.•We show that GENE has predictive capabilities, favoring the early forecast of the polarization of a social network.•Our experiments show that users’ comments on news that involve a specific group of entities are predictable.•We release a dataset that includes news and conversational threads from which this study was conducted.
论文关键词：Graph-based representations,Controversy detection,Polarity dynamics
论文评审过程：Received 29 January 2020, Revised 19 May 2020, Accepted 29 July 2020, Available online 18 August 2020, Version of Record 20 October 2020.
论文官网地址：https://doi.org/10.1016/j.ipm.2020.102366
