{"adoption": {"forks": 181, "observed_at": "2026-08-28T04:03:58.145534+00:00", "stars": 1201}, "canonical_url": "https://ross.abutalabs.com/products/tidytext", "card": {"archived": false, "artifact_type": "library", "description": "Text mining using tidy tools :sparkles::page_facing_up::sparkles:", "domain": ["data-science"], "enriched": true, "function": ["nlp", "parser", "data-science"], "health_score": 91, "homepage": "https://juliasilge.github.io/tidytext/", "language": "R", "license": "NOASSERTION", "license_family": "other", "maturity": "stable", "member_repos": ["juliasilge/tidytext"], "name": "juliasilge/tidytext", "platform": ["python"], "pushed_at": "2026-08-02T19:37:32+00:00", "repo": "juliasilge/tidytext", "stars": 1201, "tags": ["r", "tidyverse", "text-mining", "tokenization", "sentiment-analysis", "tf-idf", "cran", "natural-language-processing"], "topics": ["text-mining", "r", "tidyverse", "tidy-data", "natural-language-processing"], "urls": [], "use_cases": ["tokenize text into tidy data frames in R", "compute tf-idf for term frequencies across documents", "do sentiment analysis on text corpora with tidy tools", "convert between tidy text format and document-term matrices", "analyze n-grams and word frequencies in R", "tidy topic modeling outputs for ggplot2 visualization"], "what_it_is": "tidytext is an R package that applies tidy data principles to text mining, providing functions like unnest_tokens to convert text to and from tidy data frames. It integrates with dplyr, tidyr, broom, and ggplot2, and bridges to existing text mining packages and formats like document-term matrices.", "when_to_avoid": ["you need deep learning or transformer-based NLP", "you work outside R or prefer spaCy/NLTK pipelines", "you need production-scale streaming text processing"], "when_to_choose": ["you work in R with tidyverse tools and need text mining", "you want text analysis results as tidy data frames for dplyr/ggplot2 workflows", "you need to interoperate with tm or quanteda-style corpus and DTM objects"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/tidytext", "repo": "juliasilge/tidytext", "role": "main", "score": 66}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.145534+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:20:42.207585+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e855844ee0454a6d09b24fa30c42533075c3928d6cc958b9f16b01ba11257617", "fetched_at": "2026-08-28T04:03:58.145534+00:00", "kind": "readme", "missing": false, "url": "https://github.com/juliasilge/tidytext"}, {"content_hash": "ba573f6f3ce432aaf838c6f1a4fe73c4e49517e478b5b9f439e609014f66224e", "fetched_at": "2026-08-29T12:27:49.165181+00:00", "kind": "homepage", "missing": false, "url": "https://juliasilge.github.io/tidytext/"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.145534+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:20:42.207585+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e855844ee0454a6d09b24fa30c42533075c3928d6cc958b9f16b01ba11257617", "fetched_at": "2026-08-28T04:03:58.145534+00:00", "kind": "readme", "missing": false, "url": "https://github.com/juliasilge/tidytext"}, {"content_hash": "ba573f6f3ce432aaf838c6f1a4fe73c4e49517e478b5b9f439e609014f66224e", "fetched_at": "2026-08-29T12:27:49.165181+00:00", "kind": "homepage", "missing": false, "url": "https://juliasilge.github.io/tidytext/"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:20:42.207585+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e855844ee0454a6d09b24fa30c42533075c3928d6cc958b9f16b01ba11257617", "fetched_at": "2026-08-28T04:03:58.145534+00:00", "kind": "readme", "missing": false, "url": "https://github.com/juliasilge/tidytext"}, {"content_hash": "ba573f6f3ce432aaf838c6f1a4fe73c4e49517e478b5b9f439e609014f66224e", "fetched_at": "2026-08-29T12:27:49.165181+00:00", "kind": "homepage", "missing": false, "url": "https://juliasilge.github.io/tidytext/"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.145534+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.145534+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.145534+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:20:42.207585+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e855844ee0454a6d09b24fa30c42533075c3928d6cc958b9f16b01ba11257617", "fetched_at": "2026-08-28T04:03:58.145534+00:00", "kind": "readme", "missing": false, "url": "https://github.com/juliasilge/tidytext"}, {"content_hash": "ba573f6f3ce432aaf838c6f1a4fe73c4e49517e478b5b9f439e609014f66224e", "fetched_at": "2026-08-29T12:27:49.165181+00:00", "kind": "homepage", "missing": false, "url": "https://juliasilge.github.io/tidytext/"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.145534+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.145534+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:20:42.207585+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e855844ee0454a6d09b24fa30c42533075c3928d6cc958b9f16b01ba11257617", "fetched_at": "2026-08-28T04:03:58.145534+00:00", "kind": "readme", "missing": false, "url": "https://github.com/juliasilge/tidytext"}, {"content_hash": "ba573f6f3ce432aaf838c6f1a4fe73c4e49517e478b5b9f439e609014f66224e", "fetched_at": "2026-08-29T12:27:49.165181+00:00", "kind": "homepage", "missing": false, "url": "https://juliasilge.github.io/tidytext/"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.145534+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.145534+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.145534+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:20:42.207585+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e855844ee0454a6d09b24fa30c42533075c3928d6cc958b9f16b01ba11257617", "fetched_at": "2026-08-28T04:03:58.145534+00:00", "kind": "readme", "missing": false, "url": "https://github.com/juliasilge/tidytext"}, {"content_hash": "ba573f6f3ce432aaf838c6f1a4fe73c4e49517e478b5b9f439e609014f66224e", "fetched_at": "2026-08-29T12:27:49.165181+00:00", "kind": "homepage", "missing": false, "url": "https://juliasilge.github.io/tidytext/"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.145534+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.145534+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:20:42.207585+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e855844ee0454a6d09b24fa30c42533075c3928d6cc958b9f16b01ba11257617", "fetched_at": "2026-08-28T04:03:58.145534+00:00", "kind": "readme", "missing": false, "url": "https://github.com/juliasilge/tidytext"}, {"content_hash": "ba573f6f3ce432aaf838c6f1a4fe73c4e49517e478b5b9f439e609014f66224e", "fetched_at": "2026-08-29T12:27:49.165181+00:00", "kind": "homepage", "missing": false, "url": "https://juliasilge.github.io/tidytext/"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:20:42.207585+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e855844ee0454a6d09b24fa30c42533075c3928d6cc958b9f16b01ba11257617", "fetched_at": "2026-08-28T04:03:58.145534+00:00", "kind": "readme", "missing": false, "url": "https://github.com/juliasilge/tidytext"}, {"content_hash": "ba573f6f3ce432aaf838c6f1a4fe73c4e49517e478b5b9f439e609014f66224e", "fetched_at": "2026-08-29T12:27:49.165181+00:00", "kind": "homepage", "missing": false, "url": "https://juliasilge.github.io/tidytext/"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:20:42.207585+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e855844ee0454a6d09b24fa30c42533075c3928d6cc958b9f16b01ba11257617", "fetched_at": "2026-08-28T04:03:58.145534+00:00", "kind": "readme", "missing": false, "url": "https://github.com/juliasilge/tidytext"}, {"content_hash": "ba573f6f3ce432aaf838c6f1a4fe73c4e49517e478b5b9f439e609014f66224e", "fetched_at": "2026-08-29T12:27:49.165181+00:00", "kind": "homepage", "missing": false, "url": "https://juliasilge.github.io/tidytext/"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:20:42.207585+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e855844ee0454a6d09b24fa30c42533075c3928d6cc958b9f16b01ba11257617", "fetched_at": "2026-08-28T04:03:58.145534+00:00", "kind": "readme", "missing": false, "url": "https://github.com/juliasilge/tidytext"}, {"content_hash": "ba573f6f3ce432aaf838c6f1a4fe73c4e49517e478b5b9f439e609014f66224e", "fetched_at": "2026-08-29T12:27:49.165181+00:00", "kind": "homepage", "missing": false, "url": "https://juliasilge.github.io/tidytext/"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 95, "longevity": 100, "rhythm": 8}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 3807, "days_push": 31, "days_rel": 404, "gap_med": null, "n_releases_24m": 1}, "score": 66, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}