Geospatial AI, Dataverse Metadata, and the Study of Place-Based Government

• URL: http://arxiv.org/abs/2609.11674v1
• Date: Thu, 10 Sep 2026 15:08:58 GMT
• Title: Geospatial AI, Dataverse Metadata, and the Study of Place-Based Government
• Abstract summary: We construct a knowledge graph from the repository's public data and metadata.<n>Of 102,650 datasets, 43,991 (42.9 percent) carry at least one geospatial field.<n>A conservative keyword search identifies 7,654 geospatially tagged datasets as directly policy-relevant.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Harvard Dataverse hosts over 150,000 research datasets, but the geographic information those datasets carry is entered as free text by depositors and has never been assembled into a searchable structure. We construct a knowledge graph from the repository's public data and metadata, organizing 102,650 datasets within a 215,985-node network of 528,003 edges linking datasets to keywords, publications, subjects, journals, and locations. Of those datasets, 43,991 (42.9 percent) carry at least one geospatial field, geographic coverage, geographic unit, or a bounding box and 96.9 percent of all nodes sit in a single connected component, so datasets remain reachable from one another even when their geospatial metadata share nothing in common. A conservative keyword search identifies 7,654 geospatially tagged datasets (17.4 percent) as directly policy-relevant, with elections and legislatures the largest cluster, followed by government administration, health policy, transportation, and education. Five datasets illustrate how this metadata behaves across policy domains and spatial scales, and an extended use case shows how community language models, stance detection with geographic aggregation, and partisan language bridging tools can attach discourse to place. The central obstacle is place resolution: the same location appears as many disconnected nodes. We argue that the graph provides a concrete setting for developing AI-driven metadata enrichment and entity resolution, and we document its coverage skew toward American, city-level data.

Related papers

• Geospatial Metadata Improves Discoverability by Connecting Datasets Across Scientific Disciplines [0.0]
  We train and fine-tune a small language model using datasets from Harvard Dataverse.<n>We find that datasets with more missing metadata receive fewer downstream citations and have fewer resolvable connections to other datasets.
  arXiv  Detail & Related papers  (2026-09-15T01:40:36Z)
• World-POI: Global Point-of-Interest Data Enriched from Foursquare and OpenStreetMap as Tabular and Graph Data [1.2107297090229685]
  Recently, Foursquare released a global dataset with more than 100 million points of interest (POIs)<n>In contrast, OpenStreetMap (OSM) offers a rich, user-contributed POI dataset with detailed and frequently updated metadata.<n>We present a methodology that integrates the strengths of both datasets.
  arXiv  Detail & Related papers  (2025-10-24T11:12:41Z)
• Geolocation with Real Human Gameplay Data: A Large-Scale Dataset and Human-Like Reasoning Framework [59.42946541163632]
  We introduce a comprehensive geolocation framework with three key components.<n>GeoComp, a large-scale dataset; GeoCoT, a novel reasoning method; and GeoEval, an evaluation metric.<n>We demonstrate that GeoCoT significantly boosts geolocation accuracy by up to 25% while enhancing interpretability.
  arXiv  Detail & Related papers  (2025-02-19T14:21:25Z)
• EarthView: A Large Scale Remote Sensing Dataset for Self-Supervision [72.84868704100595]
  This paper presents a dataset specifically designed for self-supervision on remote sensing data, intended to enhance deep learning applications on Earth monitoring tasks.<n>The dataset spans 15 tera pixels of global remote-sensing data, combining imagery from a diverse range of sources, including NEON, Sentinel, and a novel release of 1m spatial resolution data from Satellogic.<n>Accompanying the dataset is EarthMAE, a tailored Masked Autoencoder developed to tackle the distinct challenges of remote sensing data.
  arXiv  Detail & Related papers  (2025-01-14T13:42:22Z)
• Quantifying Geospatial in the Common Crawl Corpus [0.07499722271664144]
  This paper investigates the prevalence of geospatial data in recent Common Crawl releases using Gemini 1.5, a powerful language model. We estimate that 18.7% of web documents in CC contain geospatial information such as coordinates and addresses.
  arXiv  Detail & Related papers  (2024-06-07T14:16:37Z)
• Where on Earth Do Users Say They Are?: Geo-Entity Linking for Noisy Multilingual User Input [2.516307239032451]
  We present a method which represents real-world locations as averaged embeddings from labeled user-input location names. We show that our approach improves geo-entity linking on a global and multilingual social media dataset.
  arXiv  Detail & Related papers  (2024-04-29T15:18:33Z)
• Discovering Geo-dependent Stories by Combining Density-based Clustering and Thread-based Aggregation techniques [0.0]
  This paper introduces a global analysis of the geo-tagged posts in social media. It supports (i) the detection of unexpected behavior in the city and (ii) the analysis of the posts to infer what is happening. We have applied our methodology to a dataset obtained from Instagram activity in New York City for seven months.
  arXiv  Detail & Related papers  (2023-12-18T10:17:12Z)
• GeoGLUE: A GeoGraphic Language Understanding Evaluation Benchmark [56.08664336835741]
  We propose a GeoGraphic Language Understanding Evaluation benchmark, named GeoGLUE. We collect data from open-released geographic resources and introduce six natural language understanding tasks. We pro vide evaluation experiments and analysis of general baselines, indicating the effectiveness and significance of the GeoGLUE benchmark.
  arXiv  Detail & Related papers  (2023-05-11T03:21:56Z)
• UKnow: A Unified Knowledge Protocol with Multimodal Knowledge Graph Datasets for Reasoning and Vision-Language Pre-Training [48.184673241046134]
  This work presents a unified knowledge protocol, called UKnow, which facilitates knowledge-based studies from the perspective of data. We categorize data knowledge into five unit types, namely, in-image, in-text, cross-image, cross-text, and image-text. Following UKnow protocol, we collect, from public international news, a large-scale multimodal knowledge graph dataset.
  arXiv  Detail & Related papers  (2023-02-14T08:27:42Z)
• GeoDE: a Geographically Diverse Evaluation Dataset for Object Recognition [31.345584733507547]
  GeoDE is a geographically diverse dataset with 61,940 images from 40 classes and 6 world regions.<n>We release the full dataset and code at https://geodiverse-data-collection.cs.princeton.edu.
  arXiv  Detail & Related papers  (2023-01-05T18:21:50Z)
• Robust Self-Tuning Data Association for Geo-Referencing Using Lane Markings [44.4879068879732]
  This paper presents a complete pipeline for resolving ambiguities during the data association. Its core is a robust self-tuning data association that adapts the search area depending on the entropy of the measurements. We evaluate our method on real data from urban and rural scenarios around the city of Karlsruhe in Germany.
  arXiv  Detail & Related papers  (2022-07-28T12:29:39Z)
• Sketch and Scale: Geo-distributed tSNE and UMAP [75.44887265789056]
  Running machine learning analytics over geographically distributed datasets is a rapidly arising problem. We introduce a novel framework: Sketch and Scale (SnS) It leverages a Count Sketch data structure to compress the data on the edge nodes, aggregates the reduced size sketches on the master node, and runs vanilla tSNE or UMAP on the summary. We show this technique to be fully parallel, scale linearly in time, logarithmically in memory, and communication, making it possible to analyze datasets with many millions, potentially billions of data points, spread across several data centers around the globe.
  arXiv  Detail & Related papers  (2020-11-11T22:32:21Z)
• Open Graph Benchmark: Datasets for Machine Learning on Graphs [86.96887552203479]
  We present the Open Graph Benchmark (OGB) to facilitate scalable, robust, and reproducible graph machine learning (ML) research. OGB datasets are large-scale, encompass multiple important graph ML tasks, and cover a diverse range of domains. For each dataset, we provide a unified evaluation protocol using meaningful application-specific data splits and evaluation metrics.
  arXiv  Detail & Related papers  (2020-05-02T03:09:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.