Towards Effective, Efficient and Unsupervised Social Event Detection in the Hyperbolic Space
Authors: Xiaoyan Yu, Yifan Wei, Shuaishuai Zhou, Zhiwei Yang, Li Sun, Hao Peng, Liehuang Zhu, Philip S. Yu
AAAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments on public datasets demonstrate Hyper SED s competitive performance, along with a substantial improvement in efficiency compared to the current state-of-the-art unsupervised paradigm. We conduct experiments and analyses to evaluate the effectiveness and efficiency of the proposed framework. Additionally, we present ablation studies and parameter analyses to demonstrate the advancement of the proposed framework. |
| Researcher Affiliation | Academia | 1School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China 2Beihang University, Beijing, China 3Kunming University of Science and Technology, Kunming, China 4Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China 5North China Electric Power University, Beijing, China 6University of Illinois at Chicago, Chicago, USA EMAIL, EMAIL, EMAIL |
| Pseudocode | No | The paper describes the methodology in narrative text and uses Figure 1 for an overall framework visualization, but does not include any explicitly labeled pseudocode or algorithm blocks. |
| Open Source Code | Yes | Implements github.com/Xiaoyan Work/Hyper SED |
| Open Datasets | Yes | We conduct experiments on two publicly available datasets: the English Twitter dataset (Mc Minn, Moshfeghi, and Jose 2013) and the French Twitter dataset (Mazoyer et al. 2020). |
| Dataset Splits | Yes | Data splitting for offline and online evaluation consistent with prior studiy (Cao et al. 2024). Specifically, for offline evaluation, the data is divided into training, validation, and test sets with a ratio of 7:1:2; for online evaluation, the data is segmented into message blocks based on time intervals: the first block encompassed messages from the first seven days (weekly), followed by daily blocks. |
| Hardware Specification | No | The paper does not provide specific hardware details such as GPU/CPU models, processor types, or memory used for running the experiments. |
| Software Dependencies | No | The paper mentions tools like SBERT and GNNs, and provides a GitHub link for implementation, but does not specify version numbers for any software dependencies or libraries used. |
| Experiment Setup | Yes | We set the hyperparameter n to 200 to mitigate occasional deadlock issues. All baselines, except Event X and HISEvent, require predefined event numbers. For implementation details, please refer to the Appendix. |