Online public opinion has become a critical component of web-based social systems, where large-scale user interactions generate complex propagation behaviors and evolving topic structures. With the rapid growth of social networking platforms, public opinion exhibits network-driven diffusion, temporal volatility, and fragmented topic evolution, posing challenges for web platform monitoring and governance. Existing studies typically rely on either epidemic propagation models or standalone topic modeling methods, limiting their ability to jointly capture diffusion mechanisms and content evolution. To address this issue, this study proposes an integrated web analytics framework that combines epidemic-based propagation modeling with topic mining. Using real data from the Weibo platform, an improved epidemic dynamics model is developed to simulate opinion diffusion over complex networks, with parameters calibrated from observed user interactions. In parallel, latent Dirichlet allocation (LDA) is applied to large-scale textual data to extract latent topics and analyze their temporal evolution. The results show that the network positions of initial propagators and key topological characteristics significantly influence propagation dynamics. Topic mining further reveals six stable thematic clusters with distinct evolutionary patterns across time windows. The proposed framework provides an interpretable system-level approach for analyzing online public opinion, offering practical support for real-time monitoring, moderation workflows, and decision-support systems in web governance.

A shared goal of several machine learning communities like continual learning, meta-learning and transfer learning, is to design algorithms and models that efficiently and robustly adapt to unseen tasks. An even more ambitious goal is to build models that never stop adapting, and that become increasingly more efficient through time by suitably transferring the accrued knowledge. Beyond the study of the actual learning algorithm and model architecture, there are several hurdles towards our quest to build such models, such as the choice of learning protocol, metric of success and data needed to validate research hypotheses. In this work, we introduce the Never-Ending VIsual-classification Stream (NEVIS'22), a benchmark consisting of a stream of over 100 visual classification tasks, sorted chronologically and extracted from papers sampled uniformly from computer vision proceedings spanning the last three decades. The resulting stream reflects what the research community thought was meaningful at any point in time, and it serves as an ideal test bed to assess how well models can adapt to new tasks, and do so better and more efficiently as time goes by. Despite being limited to classification, the resulting stream has a rich diversity of tasks from OCR, to texture analysis, scene recognition, and so forth. The diversity is also reflected in the wide range of dataset sizes, spanning over four orders of magnitude. Overall, NEVIS'22 poses an unprecedented challenge for current sequential learning approaches due to the scale and diversity of tasks, yet with a low entry barrier as it is limited to a single modality and well understood supervised learning problems. Moreover, we provide a reference implementation including strong baselines and an evaluation protocol to compare methods in terms of their trade-off between accuracy and compute. We hope that NEVIS'22 can be useful to researchers working on continual learning, meta-learning, AutoML and more generally sequential learning, and help these communities join forces towards more robust models that efficiently adapt to a never ending stream of data.

Sequential Bayesian inference over predictive functions is a natural framework for continual learning from streams of data. However, applying it to neural networks has proved challenging in practice. Addressing the drawbacks of existing techniques, we propose an optimization objective derived by formulating continual learning as sequential function-space variational inference. In contrast to existing methods that regularize neural network parameters directly, this objective allows parameters to vary widely during training, enabling better adaptation to new tasks. Compared to objectives that directly regularize neural network predictions, the proposed objective allows for more flexible variational distributions and more effective regularization. We demonstrate that, across a range of task sequences, neural networks trained via sequential function-space variational inference achieve better predictive accuracy than networks trained with related methods while depending less on maintaining a set of representative points from previous tasks.