corpus-analysis 开源项目推荐（69 个）

BLKSerene /Wordless

一个集成语料库工具，支持多语言学习语言、文学和翻译

tanloong /neosca

L2SCA & LCA fork: cross-platform, GUI, without Java dependency

mshakirDr /MFTE

MFTE (Multi Feature Tagger of English) Python is the Python version based on Le Foll's MFTE written in Perl. It is extended to include semantic tags from Biber (2006) and Biber et al. (1999), including other specific tags.

katreparitosh /Discourse-Analytics-of-Political-Speech-Transcripts

Political Discourse Analysis (PDA) of Political Speech Transcripts using Natural Language Processing (NLP)

IngTian /witness

Turns any text stream into a dated history of how its subject changed. Point it at your Claude Code, OpenCode or Codex sessions to track how you think and work, or at market news, research, or any corpus to track how it changed — raw records to observations to bi-temporal facets to narrative, with provenance, served over MCP. Single pure-Go binary.

dhfbk /variationist

Variationist: Exploring Multifaceted Variation and Bias in Written Language Data (ACL 2024 demo track)

elenlefoll /MultiFeatureTaggerEnglish

A Multi-Feature Tagger of English originally designed for multi-feature/multi-dimensional analysis (MDA) (Biber 1988; 1995) of situational variation in standard written and spoken English

yongzhuo /Text-Analysis

文本数据分析, Text-Analysis

thecsw /katya-dev

Katya or The Liberated Corpus a text corpus that allows you to request and scrape any web resource!

FlapPearLabs /zhihu-grabber-toolkit

ZhiHu CLI PRO — Cross-question deep research for Zhihu & AI Agents. Search, capture, verify, analyze large corpora, preserve evidence lineage, and synthesize across questions.

beenhow /ESW

高中英语真题词汇分析工具：课标词五级分类、跨年份词频统计、高频词 docx/xlsx 导出｜Windows + Android 双端离线运行

Sonnet0524 /wechat-corpus-toolkit

微信语料本地分析工具链 — wechat-decrypt 完整下游扩展：提key/解密/导出/建库/27个分析脚本。语料数据全程不出本机，LLM判读层可选云端API或本地模型（可完全离线）。MIT双署名。

LucasHofmann /DistlerCorpus

Hugo Distler: Der Jahrkreis op. 5 (1933)

AliceLJY /digital-clone-skill

Build corpus-driven digital clones with pre-write privacy filtering, readiness checks, and human verification

sakamoto6000-png /linear-a-structural-analysis

Structural and quantitative analysis of Linear A inscriptions using non-phonetic methodology based on GORILA corpus.

instituutnederlandsetaal /woordpeiler

Corpus-based temporal word frequencies and trend analysis.

denisecase /nlp-03-text-exploration

Exploratory analysis of text corpora using tokenization, frequency, co-occurrence, and bigrams to reveal structure in text.

199-biotechnologies /douglas-adamiser

Claude Code skill: transform any text into Douglas Adams' style, calibrated against 528,808 words

sp1227 /sejong-corpus-toolkit

A Python toolkit for processing and analyzing the 21st Century Sejong Corpus (National Institute of Korean Language) | 21세기 세종계획 말뭉치 분석 도구

phueb /CorrelationLength

Research code for computing correlation length of words in corpus