GitHub topics: context-extraction
hammadaslam1/reviews-classifier
This is my final year project "customer reviews classification and analysis system using data mining and nlp". It analyzes and then classifies the customer reviews on the basis of their fakeness, sentiments, contexts and topics discussed. The reviews are taken from various e-commerce platforms like daraz and amazon.
Language: Jupyter Notebook - Size: 78 MB - Last synced at: 8 days ago - Pushed at: 8 days ago - Stars: 0 - Forks: 0
ranjanakarsh/Swift-API-Extractor
Extracts a structured summary (including doc comments) of all classes, structs, protocols, enums, typealiases, variables, and functions from all .swift files in a directory (recursively). Optimized for LLM ingestion and codebase documentation.
Language: Python - Size: 4.88 KB - Last synced at: 3 days ago - Pushed at: 19 days ago - Stars: 0 - Forks: 0
vipul-sharma20/sharingan
Tool to extract news articles from newspaper and give the context about the news
Language: Python - Size: 26.4 KB - Last synced at: 5 days ago - Pushed at: almost 8 years ago - Stars: 211 - Forks: 26
joe-stifler/crawler
Crawler is a Python package that crawls web pages and converts their content into Markdown format, making it easy to create documentation, notes, or other text-based representations. It features domain restrictions, flexible output options, and graph visualization.
Language: Python - Size: 283 KB - Last synced at: about 2 months ago - Pushed at: about 1 year ago - Stars: 7 - Forks: 1
chrissmartin/dataset-miner
Generates standardised datasets from given docs for use in LLM training.
Language: Python - Size: 20.5 KB - Last synced at: 14 days ago - Pushed at: 8 months ago - Stars: 2 - Forks: 0
ParasGarg/Context-Extraction
The main aim of the project is to scrap reviews from a website for American cuisine restaurants in NYC. Then from the scrapped reviews, it would extract the context and calculate the accuracy for each context. (Contexts considered are: Whom, When, Where, and Occasion) - 'Whom' denotes, with whom the user went to the restaurant (example: friends, family, etc.) - 'When' denotes, for which part of the day the user dined in (example: lunch, dinner, etc.) - 'Where' denotes, whether the user is local or tourist - 'Occasion' denotes, for which particular occasion the user visited (example: birthday, wedding anniversary, etc.)
Language: Python - Size: 356 KB - Last synced at: 3 months ago - Pushed at: over 7 years ago - Stars: 1 - Forks: 2
