{"adoption": {"forks": 343, "observed_at": "2026-08-28T04:05:07.429757+00:00", "stars": 1584}, "canonical_url": "https://ross.abutalabs.com/products/similarity", "card": {"archived": false, "artifact_type": "library", "description": "similarity: Text similarity calculation Toolkit for Java. 文本相似度计算工具包，java编写，可用于文本相似度计算、情感分析等任务，开箱即用。", "domain": [], "enriched": true, "function": ["nlp", "machine-learning"], "health_score": 76, "homepage": "https://shibing624.github.io/similarity/", "language": "Java", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["shibing624/similarity"], "name": "shibing624/similarity", "platform": ["jvm"], "pushed_at": "2026-07-16T12:10:21+00:00", "repo": "shibing624/similarity", "stars": 1584, "tags": ["text-similarity", "sentiment-analysis", "word2vec", "edit-distance", "cosine-similarity", "chinese-nlp", "natural-language-processing", "text-processing"], "topics": ["nlp", "similarity", "sentiment", "semantic", "java", "sim-scores"], "urls": [], "use_cases": ["compute similarity between two Chinese words or sentences in Java", "find duplicate or near-duplicate paragraphs with SimHash or cosine similarity", "score the sentiment polarity of Chinese words", "compare strings with edit distance or Jaro-Winkler in a JVM app", "find semantically similar words using a Chinese thesaurus", "build a deduplication or matching feature for Chinese text"], "what_it_is": "A Java toolkit for computing text similarity at word, phrase, sentence, and paragraph levels, offering algorithms like Cilin-based similarity, edit distance, cosine similarity, Jaccard, SimHash, and more. It also includes Chinese sentiment analysis, lexicon-based word tendency scoring, and word2vec-based near-word lookup.", "when_to_avoid": ["you need neural embedding-based similarity (e.g., BERT/sentence transformers) rather than lexical/semantic-dictionary methods", "your primary language is not Chinese and you need multilingual semantic similarity", "you work in Python or another non-JVM stack"], "when_to_choose": ["you need text similarity computation in a Java/JVM project", "you work with Chinese text and want thesaurus- or Hownet-based semantic similarity", "you want multiple similarity algorithms behind one simple API", "you need lightweight, dictionary-based sentiment tendency scoring"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/similarity", "repo": "shibing624/similarity", "role": "main", "score": 64}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:07.429757+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:55:58.934142+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "734a3b9960bfe8645f2899ea1e3491005b28cb785ec3102bb9d9f2358984520f", "fetched_at": "2026-08-28T04:05:07.429757+00:00", "kind": "readme", "missing": false, "url": "https://github.com/shibing624/similarity"}, {"content_hash": "32bb9f774aa277ab4f978c79905394f0c129a38aa53ac37cbd52c6ab55cc8066", "fetched_at": "2026-08-29T11:26:23.852401+00:00", "kind": "homepage", "missing": false, "url": "https://shibing624.github.io/similarity/"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:07.429757+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:55:58.934142+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "734a3b9960bfe8645f2899ea1e3491005b28cb785ec3102bb9d9f2358984520f", "fetched_at": "2026-08-28T04:05:07.429757+00:00", "kind": "readme", "missing": false, "url": "https://github.com/shibing624/similarity"}, {"content_hash": "32bb9f774aa277ab4f978c79905394f0c129a38aa53ac37cbd52c6ab55cc8066", "fetched_at": "2026-08-29T11:26:23.852401+00:00", "kind": "homepage", "missing": false, "url": "https://shibing624.github.io/similarity/"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:55:58.934142+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "734a3b9960bfe8645f2899ea1e3491005b28cb785ec3102bb9d9f2358984520f", "fetched_at": "2026-08-28T04:05:07.429757+00:00", "kind": "readme", "missing": false, "url": "https://github.com/shibing624/similarity"}, {"content_hash": "32bb9f774aa277ab4f978c79905394f0c129a38aa53ac37cbd52c6ab55cc8066", "fetched_at": "2026-08-29T11:26:23.852401+00:00", "kind": "homepage", "missing": false, "url": "https://shibing624.github.io/similarity/"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:07.429757+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:07.429757+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:07.429757+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:55:58.934142+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "734a3b9960bfe8645f2899ea1e3491005b28cb785ec3102bb9d9f2358984520f", "fetched_at": "2026-08-28T04:05:07.429757+00:00", "kind": "readme", "missing": false, "url": "https://github.com/shibing624/similarity"}, {"content_hash": "32bb9f774aa277ab4f978c79905394f0c129a38aa53ac37cbd52c6ab55cc8066", "fetched_at": "2026-08-29T11:26:23.852401+00:00", "kind": "homepage", "missing": false, "url": "https://shibing624.github.io/similarity/"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:07.429757+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:07.429757+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:55:58.934142+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "734a3b9960bfe8645f2899ea1e3491005b28cb785ec3102bb9d9f2358984520f", "fetched_at": "2026-08-28T04:05:07.429757+00:00", "kind": "readme", "missing": false, "url": "https://github.com/shibing624/similarity"}, {"content_hash": "32bb9f774aa277ab4f978c79905394f0c129a38aa53ac37cbd52c6ab55cc8066", "fetched_at": "2026-08-29T11:26:23.852401+00:00", "kind": "homepage", "missing": false, "url": "https://shibing624.github.io/similarity/"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:07.429757+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:07.429757+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:07.429757+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:55:58.934142+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "734a3b9960bfe8645f2899ea1e3491005b28cb785ec3102bb9d9f2358984520f", "fetched_at": "2026-08-28T04:05:07.429757+00:00", "kind": "readme", "missing": false, "url": "https://github.com/shibing624/similarity"}, {"content_hash": "32bb9f774aa277ab4f978c79905394f0c129a38aa53ac37cbd52c6ab55cc8066", "fetched_at": "2026-08-29T11:26:23.852401+00:00", "kind": "homepage", "missing": false, "url": "https://shibing624.github.io/similarity/"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:07.429757+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:07.429757+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:55:58.934142+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "734a3b9960bfe8645f2899ea1e3491005b28cb785ec3102bb9d9f2358984520f", "fetched_at": "2026-08-28T04:05:07.429757+00:00", "kind": "readme", "missing": false, "url": "https://github.com/shibing624/similarity"}, {"content_hash": "32bb9f774aa277ab4f978c79905394f0c129a38aa53ac37cbd52c6ab55cc8066", "fetched_at": "2026-08-29T11:26:23.852401+00:00", "kind": "homepage", "missing": false, "url": "https://shibing624.github.io/similarity/"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:55:58.934142+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "734a3b9960bfe8645f2899ea1e3491005b28cb785ec3102bb9d9f2358984520f", "fetched_at": "2026-08-28T04:05:07.429757+00:00", "kind": "readme", "missing": false, "url": "https://github.com/shibing624/similarity"}, {"content_hash": "32bb9f774aa277ab4f978c79905394f0c129a38aa53ac37cbd52c6ab55cc8066", "fetched_at": "2026-08-29T11:26:23.852401+00:00", "kind": "homepage", "missing": false, "url": "https://shibing624.github.io/similarity/"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:55:58.934142+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "734a3b9960bfe8645f2899ea1e3491005b28cb785ec3102bb9d9f2358984520f", "fetched_at": "2026-08-28T04:05:07.429757+00:00", "kind": "readme", "missing": false, "url": "https://github.com/shibing624/similarity"}, {"content_hash": "32bb9f774aa277ab4f978c79905394f0c129a38aa53ac37cbd52c6ab55cc8066", "fetched_at": "2026-08-29T11:26:23.852401+00:00", "kind": "homepage", "missing": false, "url": "https://shibing624.github.io/similarity/"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:55:58.934142+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "734a3b9960bfe8645f2899ea1e3491005b28cb785ec3102bb9d9f2358984520f", "fetched_at": "2026-08-28T04:05:07.429757+00:00", "kind": "readme", "missing": false, "url": "https://github.com/shibing624/similarity"}, {"content_hash": "32bb9f774aa277ab4f978c79905394f0c129a38aa53ac37cbd52c6ab55cc8066", "fetched_at": "2026-08-29T11:26:23.852401+00:00", "kind": "homepage", "missing": false, "url": "https://shibing624.github.io/similarity/"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 92, "longevity": 100, "rhythm": 8}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 3585, "days_push": 48, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 64, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}