|
|
|
| Information Tracing Model Based on Node Feature Enhancement |
| HUO Xuanrong, XIAO Yuzhi, HAN Jiaxina, HUANG Tao, HU Zeyu
|
| a. School of Computer; b. Qinghai Provincial Key Laboratory of Tibetan Information Processing and Machine Translation; c. Key Laboratory of Tibetan Information Processing Ministry of Education, Qinghai Normal University, Xining 810008 |
|
|
|
|
Abstract Aiming at the difficulty of tracing Internet rumors, a Node Feature-Enhanced Traceability Model (NFETM) is proposed based on information carrier model and in-depth mining of user characteristics. This paper aims to use deep learning method to obtain high-order multi-scale features of information nodes (high-order neighbors, neighbor states, different state connection structures), and combine SEIR propagation mechanism to learn node states into information sources (I states) and non-information sources (S, E, R states). Firstly, multiple node centrality indexes are used to expand and enrich node characteristics. Secondly, an anti-noise enhancement module is used to reconstruct the expanded node features, and dynamically learn the features of the node itself and its first-order neighbors. Thirdly, the metric learning method is used to adjust the node feature space, so that the distance between nodes in the same state is reduced, so as to distinguish the categories and characteristics of nodes. Finally, the multi-dimensional features of nodes are fused and classified to determine the information source. The experimental results show that the proposed model achieves relatively good results in both the simulated generation network and the real network.
|
|
Received: 11 August 2023
Published: 09 October 2025
|
|
|
|
|
|
|
|
|
