The aim of English personalized learning is to create a learning process tailored to each learner’s needs for better efficiency and better engaged. Designing an adaptive learning path that adapts to the learner as he learns is a complex problem. The current solutions are based on a rule-based model or on a fixed sequence, offering no way of capturing the variability, engagement, or skill deficit of the learner at any given moment. To solve those problems, we suggest a Reinforcement Learning-Driven Dynamic Path Optimization (RL-DPO) framework, which can realize the generation of personalized English learning paths following the principles of dynamic programming and AI. The model is continuously updated based on the learners’ performance data, allowing the system to dynamically suggest the next module, which is the best fit based on the anticipated learning gain, and the time spent. DPO’s superior performance, achieving Learning Accuracy 96.8
Information dissemination in Online Social Networks (OSNs) is shaped both by the structural foundation of the network and by the interest-based relationships among its users. Identifying the seed users of information diffusion in OSNs remains a challenge. Traditional seed detection methods apply centrality measures globally to uncover seed nodes and overlook seed detection based on interest groups. As a result, the selected seed nodes are often concentrated in the same locality, and efficient information diffusion remains a challenge. In this paper, we propose an interest group-based seed node detection framework for information dissemination in OSNs. The proposed approach first finds the interest groups using the Leiden community detection method; once all interest groups are detected, the seed nodes within each group are identified using Netdegree Centrality (NDC), a variant of degree centrality. Selecting influential seed nodes from every interest group ensures diversified and efficient information diffusion over the network. Experimental evaluation on eight benchmark datasets using the Independent Cascade (IC) model of information diffusion shows that the seeds selected across the different interest groups achieve good diffusion coverage of the whole network. The results show that the proposed approach combines community-aware analysis with local influence metrics for seed detection in varied and scalable OSNs.
High-quality feedback can support writing development, yet producing it consistently at classroom scale remains difficult. Large language models generate fluent comments quickly, but their feedback can over-emphasise surface grammar, drift from the target rubric, assert errors not present in the essay, or disclose complete rewrites. We propose RUMAR, a retrieval-augmented framework for English-as-a-Foreign-Language writing feedback. RUMAR combines error detection and rubric-aware retrieval with a bounded Generation–Evaluation–Refinement loop comprising two language-model agents—a Generator and a Critic—and a deterministic refinement controller. The Critic evaluates candidate feedback against five explicitly anchored 1–5 criteria, and an aggregator organises accepted comments across Hattie’s feed-up, feed-back, and feed-forward layers. On the reported ASAP-AES and ELLIPSE evaluation, RUMAR has the highest observed point estimate in each automatic-metric column relative to the six implemented baselines. Descriptive expert ratings and a four-week trial with 80 B1–B2 learners at one institution also favour RUMAR among the automated systems compared. These findings are limited to the reported datasets, argumentative tasks, and automated comparators. The trial contains neither a human-teacher nor a no-feedback control, and the one-week delayed post-test cannot establish durable transfer. We therefore interpret the results as evidence of feasibility and pedagogical alignment within the evaluated setting, not as proof of superiority over teacher feedback or broad classroom readiness.
The rapid growth of digitalization has transformed how news is produced and consumed, but it has also accelerated the spread of multimodal fake news, in which misleading text is deliberately combined with manipulated or out-of-context images to deceive audiences. Because unimodal, text-only methods cannot capture cross-modal inconsistencies, deep-learning-based multimodal detection has become a critical research frontier. This systematic literature review, conducted in accordance with the PRISMA 2020 guidelines, synthesizes methods for multimodal fake news detection that combine textual and visual data using deep learning. A structured Boolean search of Scopus and Web of Science retrieved 1,123 records; after duplicate removal, title/abstract screening, and full-text eligibility assessment, 81 studies published between 2020 and 2026 (a partial year) were included. The review spans five analytical dimensions: deep-learning architecture, modality and feature representations, fusion strategies, benchmark datasets, and evaluation metrics. The findings reveal a clear paradigm shift from recurrent and convolutional networks toward pre-trained transformer encoders (BERT, RoBERTa, and Vision Transformers) and graph-based models, and from naive feature concatenation toward attention-driven joint and hybrid fusion. Text-plus-image is the dominant modality combination, while the Weibo and MediaEval Twitter corpora remain the most-used benchmarks, and accuracy and F1-score are the most frequently reported metrics. Rather than presenting this shift as the current frontier, the review positions these findings as a consolidated, reproducible baseline of the text-image deep-learning literature at its transition toward foundation-model-based detection - a record that broad or LVLM-centred surveys presuppose but do not themselves establish. The review further identifies persistent gaps, including modality dominance, over-reliance on internal text–image consistency, limited external verification and explainability, weak generalization under domain shift, dataset and linguistic bias, and high computational cost. Collectively, these findings provide a consolidated foundation and roadmap for future research.
Amidst the fast-paced advancements in mobile robot technologies, route optimization, which forms the crux of autonomous navigation, must strike a balance between obstacle avoidance safety, travel distance, and movement efficiency. This study proposes a dual-layer hybrid route optimization model that combines an improved Beetle Antennae Search and an improved Sine Cosine Algorithm. The model uses Opposition-Based Learning to optimize the initial population. It applies an improved Sine Cosine Algorithm with nonlinear decay and adaptive inertia weight to enhance global exploration ability. It also integrates an improved Beetle Antennae Search mechanism with dynamic step size and multi-beetle parallel search to strengthen local refinement. Simulation results show that under standard benchmark functions, the model achieves higher convergence accuracy and better stability than comparison methods. In a simple grid environment, the optimized robot route length is 29.22 m, which is reduced by 16.73
