Xiaodong Feng

Purpose: Collecting online opinions, particularly suggestive opinions on pre-release policies, is crucial for the government's informed policy-making. Grounded in social cognition theories, this study explores how public social attributes, cognitive experience and environmental factors influence the expression of suggestive opinions on such pre-release policies. Design/methodology/approach: We collected a dataset with 37,087 online comments on 12 selected pre-release policies and 1,059,019 microblogs by commenting users on Sina Weibo in China. Using text mining techniques, we extracted relevant features and applied a two-stage regression analysis alongside explainable machine learning to identify factors influencing suggestive opinion expression. Findings: Females, individuals possessing more extensive social experience, and users who frequently convey negative sentiments exhibit a higher propensity to post suggestive opinions. Environmental factors, particularly existing suggestive opinions, exert a significant promoting effect on the subsequent expression of suggestions. Moreover, there exists a time decay effect in the expression of suggestive opinions, and these effects are more prominent among females compared to males. Originality/value: While prior research has explored determinants of general online information behaviors and examined sentiment analysis, this study seeks to uniquely investigate the factors driving suggestive opinion expression, as opposed to other opinion types.

It is critical to accurately predict the future popularity of information cascades for many related applications, such as online opinion warning or academic influence evaluation. Despite many efforts devoted to developing effective prediction approaches, especially the recent presence of deep learning-based model, the structural information of the cascade network is ignored. Thus, to make use of the structural information in cascade prediction task, we propose a structural-topic aware deep neural networks (STDNN), which firstly learns the structure topic distribution of each node in the cascade, feeds it to a sequential neural network, and finally predicts the future popularity of the cascades. It can inherit the high interpretability of Hawkes process and possesses the high predictive power of deep learning methods, bridging the gap between prediction and understanding of information cascades by capturing indicative graph structures. We evaluate our model through quantitative experiments, where our model exhibits promising performance, efficiency higher than the baselines.

Anomalous links such as noisy links or adversarial edges widely exist in real-world networks, which may undermine the credibility of the network study, e.g., community detection in social networks. Therefore, anomalous links need to be removed from the polluted network by a detector. Due to the co-existence of normal links and anomalous links, how to identify anomalous links in a polluted network is a challenging issue. By designing a robust graph structure embedding framework, also called RGSE, the link-level feature representations that are generated from both global embedding view and local stable view can be used for anomalous link detection on contaminated graphs. Comparison experiments on a variety of datasets demonstrate that the new model and its variants achieve up to an average 5.2% improvement with respect to the accuracy of anomalous link detection against the traditional graph representation models. Further analyses also provide interpretable evidence to support the model's superiority.