An open API service indexing awesome lists of open source software.

https://github.com/ritvik19/text-insights


https://github.com/ritvik19/text-insights

Last synced: about 1 year ago
JSON representation

Awesome Lists containing this project

README

          

# Text Insights

Exracting Insights from text

* KeyWords CSV : Extract Keywords from csv data
* KeyWords Text : Extract Keywords from string data
* Knowledge Graph: Live Tweets
* POS Based Keywords: Extract keywords from csv data taking into account their POS
* Review Insights 1: Get Insights about the customer focus areas based on their reviews
* Review Insights 2: Get Insights about the customer focus areas based on their reviews (less complex)
* Spell Checker: Implementation of Peter Norvig's spell checker using Word2Vec
* Text Clustering 1: TFIDF+KMeans+Hierarchical
* Text Clustering 2: Word Clustering (Word2Vec+KMeans+Hierarchical)
* Text Clustering 3: Doc Clusetering (TFIDF weighted avg. Word2Vec +Kmeans + Hierarchical)
* Text Similarities: Various Text Similarity Metrics
* Text Summarizer 1: Text Summarizer based on word counts
* Text Summarizer 2: Text Summarizer based on word counts and invesrse document frequency
* Text Summarizer 3: Text Summarizer based on Text Rank Algorithm

Text Classification Models:

* [Toxic-Comment-Classification](https://github.com/Ritvik19/Toxic-Comment-Classification): A multi-headed model that’s capable of detecting different types of of toxicity like threats, obscenity, insults, and identity-based hate
* [Spam-Filter](https://github.com/Ritvik19/Spam-Filter): Model to classify texts as spam or ham
* [Clickbait-Detection](https://github.com/Ritvik19/Clickbait-Detection): Model that detects text based Clickbaits
* [News-Classifier](https://github.com/Ritvik19/News-Classifier): Various models to classify News Articles
* [Quora-Question-Pairs](https://github.com/Ritvik19/Quora-Question-Pairs): Model that can indentify similar texts
* [StackOverflow-Tag-Predictor](https://github.com/Ritvik19/StackOverflow-Tag-Predictor):A model to suggest the tags based on the content that was there in the question posted on Stackoverflow.