用文本和特征空间双重增强提升社交事件检测效果
Explicit and Implicit Data Augmentation for Social Event Detection
- 结合大模型生成与特征空间扰动，实现双路数据增强
- 在Twitter2012和Twitter2018上平均F1提升超15%
- 无需改动主模型，可直接嵌入现有系统使用
社交事件检测需依赖标注数据，但人工标注成本高。为此，我们提出SED-Aug——一种即插即用的双重增强框架，融合显式文本增强与隐式特征空间增强，提升数据多样性与模型鲁棒性。显式增强利用大语言模型，通过五种不同策略生成文本信息；隐式增强设计五种新型扰动技术，在结构融合嵌入的特征空间中操作，保持语义与关系特性的同时增加多样性。实验表明，SED-Aug在Twitter2012数据集上较最优基线平均F1提升约17.67%，在Twitter2018数据集上提升约15.57%。代码已开源：https://github.com/congboma/SED-Aug。
原文摘要 · Abstract (English)
Social event detection involves identifying and categorizing important events from social media, which relies on labeled data, but annotation is costly and labor-intensive. To address this problem, we propose Augmentation framework for Social Event Detection (SED-Aug), a plug-and-play dual augmentation framework, which combines explicit text-based and implicit feature-space augmentation to enhance data diversity and model robustness. The explicit augmentation utilizes large language models to enhance textual information through five diverse generation strategies. For implicit augmentation, we design five novel perturbation techniques that operate in the feature space on structural fused embeddings. These perturbations are crafted to keep the semantic and relational properties of the embeddings and make them more diverse. Specifically, SED-Aug outperforms the best baseline model by approximately 17.67% on the Twitter2012 dataset and by about 15.57% on the Twitter2018 dataset in terms of the average F1 score. The code is available at GitHub: https://github.com/congboma/SED-Aug.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。