geolocation extraction

This work addresses the challenges of fragile entity and event extraction from unstructured data, heavy reliance on costly ontology engineering in knowledge graph construction, and limited cross-domain generalization. To overcome these limitations, the authors propose an end-to-end multidimensional information extraction framework that leverages spatiotemporal context as a universal anchor. The approach employs large language models (e.g., GPT-4o-mini, Qwen3-8B) for context-aware entity and event extraction, enhanced by document-level memory, geocoding correction, and quality validation mechanisms. It further supports user-defined analytical dimensions and interactive exploration, including clustering, burst detection, and entity network analysis. Evaluated on a public health benchmark, the method achieves F1 score improvements of 4.37% and 3.60% for spatial and temporal entity extraction, respectively. The code and an online demo platform are publicly released.

Existing event extraction datasets commonly suffer from limited event type coverage, domain closure, and a lack of large-scale human validation. To address these limitations, this work introduces EVENT5Ws—a large-scale, human-annotated, and statistically validated open-domain event extraction dataset. Through a systematic annotation pipeline and rigorous quality control mechanisms, EVENT5Ws achieves, for the first time, broad cross-regional coverage of diverse event types. The study also establishes strong baselines leveraging pretrained large language models. Experimental results demonstrate that EVENT5Ws substantially enhances model generalization across varied geographical contexts, offering a reliable resource and practical guidance for advancing open-domain event extraction research.

In the context of information overload, automated detection of news bias—specifically commission, omission, and source selection (COSS)—remains a critical yet unsolved challenge. This paper proposes the first unified framework for jointly modeling all three COSS bias types, departing from conventional single-task paradigms by introducing an end-to-end multi-task learning architecture. Methodologically, the approach integrates text reuse analysis, multi-granularity feature extraction, and pattern recognition within a pipeline-based design to enable fine-grained bias detection. Additionally, we introduce an interpretable visualization module that explicitly highlights bias type, location, and intensity. Experimental results demonstrate that our framework significantly outperforms baseline methods in both bias classification accuracy and interpretability. By offering a systematic, deployable solution, this work advances practical news neutrality assessment and provides a foundation for transparent, large-scale media bias analysis.

Existing document chunking methods rely solely on semantic similarity while ignoring spatial layout, leading to suboptimal segmentation in complex documents (e.g., multi-column or image-text interleaved layouts) and poor controllability of chunk length for LLM input constraints. To address this, we propose a structure-aware adaptive chunking method: it jointly models textual bounding boxes, semantic embeddings (BERT/MPNet), and spatial relationships to construct a weighted heterogeneous graph, then applies spectral clustering for semantic-structural co-optimization; additionally, a dynamic length truncation strategy enforces strict token limits. This is the first document chunking framework that explicitly integrates spatial structure modeling with semantic coherence. Experiments demonstrate a 12.7% F1-score improvement on multi-layout benchmarks, 98.3% intra-chunk semantic consistency, and 100% compliance with prescribed token constraints.

To address the challenge of analyzing sentiment and thematic dynamics in large-scale Twitter streams during geopolitical conflicts, this paper proposes a sentiment–metadata joint-partitioning topic modeling framework. Our method integrates ensemble sentiment labeling from multiple pretrained models and metadata-aware LDA modeling—grouped along temporal, geographic, and sentiment dimensions—and implements an interactive spatiotemporal visualization system powered by D3.js. The key innovation lies in explicitly incorporating predicted sentiment labels into the prior structure of topic modeling, thereby strengthening interpretable associations between sentiment and topics. Evaluated on real-world conflict-related Twitter data, our approach achieves sentiment classification F1-scores ≥ 0.89, successfully identifies temporally evolving topic clusters, and enables cross-regional analysis of sentiment–topic co-dynamics. This significantly enhances both the depth and interpretability of social舆情 understanding under dynamic contextual conditions.

Existing approaches struggle to effectively capture and convey the spatial relationships and semantic associations among regions in document layouts, limiting users’ understanding of structural organization. This work proposes CAPE, a novel framework that integrates spatial context into explanation generation by identifying salient spatial patterns—such as clusters, subgroups, and outliers—to construct multi-granular contextual representations. These representations are then leveraged in conjunction with large language models to produce hierarchical, semantically grounded natural language explanations. User studies on news and academic documents demonstrate that CAPE’s spatially aware explanations significantly enhance users’ comprehension of layout structures and improve their efficiency in document exploration, outperforming baseline methods that rely solely on keywords or content features.

This work proposes a context-aware bias detection framework that identifies subtle linguistic biases in large language model outputs toward diverse social groups without relying on predefined lists of sensitive terms. The approach generates structured synthetic minimal-pair texts—narratively consistent except for the substitution of target group markers—and employs linguistic form abstraction combined with an enhanced variant of pointwise mutual information (PMI) for comparative analysis. Integrating quantitative statistics with qualitative evaluation, the framework is adaptable across multiple text genres and effectively quantifies asymmetric associations between social groups and levels of linguistic abstraction. It precisely localizes textual segments with high concentrations of bias signals, enabling domain experts to identify potentially harmful expressions within their contextual settings.

This study addresses the limited interactivity and domain adaptability of existing clustering methods for digital humanities scholars working with large-scale unstructured documents. To bridge this gap, the authors propose an analysis-perspective-driven interactive document clustering framework. This framework enables users to define initial semantic lenses through prompt rewriting and instruction embedding, and integrates interactive visualization, on-the-fly cluster adjustment, and online fine-tuning of embedding models into a closed-loop human-in-the-loop feedback process. The approach supports an interpretable, intervenable, and iterative clustering experience, empowering researchers to efficiently uncover latent semantic structures—such as thematic patterns or sentiment signals—and thereby generate high-quality structured data to support in-depth humanities inquiry.

This work addresses the challenge of modeling the dynamic and highly abstract evolution of information narratives during crisis events, a task where existing approaches are largely confined to static snapshots. We propose the first framework that integrates situated cognition theory with unsupervised temporal modeling, enabling adaptive representation of narrative entity trajectories within a shared semantic space. By combining semantic embeddings, density-based clustering, and rolling time-window linkage, our method requires no predefined labels and captures fine-grained narrative lifecycles, revealing heterogeneous evolution patterns characterized by coexisting transient fragments and stable anchors. Experiments on real-world crisis data demonstrate high clustering consistency and the ability to effectively identify diverse narrative evolution pathways, offering interpretable temporal representations for dynamic information monitoring and decision-making.

Existing text analysis methods, such as perplexity, overlook the influence of context on the shape of the next-token probability distribution, limiting their ability to accurately capture the statistical characteristics of language model–generated text. This work proposes DMAP, a novel approach that introduces, for the first time, a mathematically rigorous distribution mapping mechanism to transform text into a set of samples within the unit interval via a language model. By jointly encoding token rank and probability information, DMAP enables efficient, model-agnostic statistical analysis. The method provides a unified representation of both probabilistic and ranking structures in text, demonstrating its effectiveness across three case studies: accurately inferring generation parameters, revealing the critical role of probability curvature in machine-generated text detection, and successfully tracing statistically detectable signatures of synthetic data in downstream models.