You are on page 1of 5

TEXT ANALYTICS

MD ARHAM ANALYTICS
TEXT ANALYSTICS

TEXT MINING
Text mining is a process to extracting interesting and significant patterns to
explore knowledge from textual data source.
Unstructured Data examples
 Emails
 Insurance claims
 News article
 Web pages
 Patent portfolios
 Customer complaint letter
 Contracts
 Transcripts of phone calls with customers
 Technical documents

Text mining applications


 Customer profile analysis
 Trend analysis
 Information filtering
 Event tracks
 News stories classification
 Web search
 Sentiment analysis
Text mining process
Gain subject matter expertise and define text mining
Problem definition

Blogs Survey
Reviews
Unorganized state
Emails Articles
Social
media

Organization

Feature extraction

Analysis

Organized state Insight, recommendation or analytical output

Text mining process


 Text summarization
 Information extraction from text
 Information visualization
 Unsupervised learning methods - cluster
 Supervised learning methods - regression
Packages used in python
 Natural language toolkit(NLTK)
 Tokenization
 POS tagging
 Named entity recognition
 Parsing
 Stemming
 Classification
 Text bob
 Text processing Phrase extraction
 Association mining
 Sentiment analysis
 Genism
 Topic modelling
 Similarity analysis
 Pattern
 Crawling
 Pos tagging
 nGrams, sentiment analysis, WordNet
 Vector space models, clustering, classification
 Vocabulary
 Antonyms
 Part of speech
 Translation
 Pronunciation
 And hyphenation of a given word
 spaCy
 tokenization
 Pos tagging
 Parsing
 Named entity recognition
 Data Type
 List – [int, float, string] – it can change
 Tuple – it cannot change
 Set – values cannot be change it contain only unique values
 Dictionary it stores value with the key(name)

You might also like