{"id":20478662,"url":"https://github.com/do-me/semantic-hexbins","last_synced_at":"2025-08-01T23:35:50.478Z","repository":{"id":207947708,"uuid":"720481329","full_name":"do-me/semantic-hexbins","owner":"do-me","description":"A light-weight demo app for geospatial semantic search. Designed for text data with geospatial references.","archived":false,"fork":false,"pushed_at":"2025-04-13T08:15:54.000Z","size":202175,"stargazers_count":2,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-13T13:16:12.417Z","etag":null,"topics":["hexbins","leaflet","semanticsearch","transformers"],"latest_commit_sha":null,"homepage":"https://do-me.github.io/semantic-hexbins/","language":"JavaScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/do-me.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2023-11-18T16:10:38.000Z","updated_at":"2025-04-13T08:15:57.000Z","dependencies_parsed_at":"2025-04-13T13:26:16.801Z","dependency_job_id":null,"html_url":"https://github.com/do-me/semantic-hexbins","commit_stats":null,"previous_names":["do-me/semantic-hexbins"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/do-me/semantic-hexbins","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/do-me%2Fsemantic-hexbins","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/do-me%2Fsemantic-hexbins/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/do-me%2Fsemantic-hexbins/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/do-me%2Fsemantic-hexbins/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/do-me","download_url":"https://codeload.github.com/do-me/semantic-hexbins/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/do-me%2Fsemantic-hexbins/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":261391270,"owners_count":23151662,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["hexbins","leaflet","semanticsearch","transformers"],"created_at":"2024-11-15T15:38:38.050Z","updated_at":"2025-08-01T23:35:50.462Z","avatar_url":"https://github.com/do-me.png","language":"JavaScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Semantic Hexbins\n\nA light-weight demo app and processing scripts for geospatial semantic search. Designed for any kind of textual data with geospatial references.\nRepository for the paper: XXX (still to submit)\n\n![](screenshot_overview.png)\n\n## Idea \n\nThe paper describes an approach to use semantic similarity for geospatial purposes, like georeferenced social media data.\n\n## Data samples\n\nRanging from 8 - 32 Mb for individual posts or 0.8 - 5.1 Mb for aggreagted posts, see data folder.\n\n## Script for Data Processing \u0026 Reproduction\n\nScripts for data processing can be found here:\n- Data Mining: https://github.com/do-me/fast-instagram-scraper\n- Data Processing \u0026 Text Inferencing: https://gist.github.com/do-me/d60ea47d0dc97ba40c9d727bf26f7a77\n- Index creating for loading in JavaScript Frontend: https://gist.github.com/do-me/dc8877049c2c074df3c7d8e707adf138\n\n## Example Queries \n\nSee the screenshots folder for query comparisons between the location-averaged and individual embedding indice.\n\n## Performance \n### File size\nSee the data directory for comparison: https://github.com/do-me/semantic-hexbins/tree/main/data\n\n### Speed\nTested devices: \n- Windows laptop with Intel i7-8550 CPU\n- Ubuntu laptop with AMD Ryzen 7 PRO 6850U\n- Android phone Samsung S9 with Exynos 9810\n- Apple iPhone 15 Pro with A17 Pro\n\nRun times for a full layer update are significantly below 200ms with ~60ms inferencing time. Iphone 15 Pro averages around 54ms (33ms for inferencing) for 100 runs.\n\nFor comparison to a simple full-text search (GFTS) in JS see this app: https://do-me.github.io/semantic-hexbins/full_text_search_benchmark/. It benchmarks dummy data in social media style with 4 columns: lat, lon, location ID and text.\n\n![image](https://github.com/user-attachments/assets/9364866c-a1de-453c-a4b4-18f93fa6c549)\n\nScreenshot results run on an M3 Max.\n\n## Previous research\n- [An Application-Oriented Implementation of Hexagonal On-the-fly Binning Metrics for City-Scale Georeferenced Social Media Data](https://isprs-archives.copernicus.org/articles/XLVIII-4-W7-2023/253/2023/)\n- [Developing a Privacy-Aware Map-Based Cross-Platform Social Media Dashboard for Municipal Decision-Making](https://isprs-archives.copernicus.org/articles/XLVIII-4-W1-2022/545/2022/)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdo-me%2Fsemantic-hexbins","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdo-me%2Fsemantic-hexbins","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdo-me%2Fsemantic-hexbins/lists"}