Client Background

Client: A Leading Retail Firm in the USA

Industry Type: Retail

Services: Retail Business

Organization Size: 100+

The Problem

Create an API service that will parse text, include comments, analyse the remarks, assign a score based on sentiment or other criteria, etc. Feed it comments, and it should analyse the syntax and sentiment of the comments as well as extract key terms to add to the extended meta data of that model. In order for us to know a user’s behaviour, personal information, and more meta data about their interests

Our Solution

Created a flask API, that will take comments as input and will textual analysis as follows:

1. Spell and Grammar Check: We have used language tool python for this , LanguageTool is an open-source grammar tool, also known as the spellchecker for OpenOffice. This library allows you to detect grammar errors and spelling mistakes through a Python script or through a command-line interface. 
2. Sentimental Analysis: For Sentimental Analysis we used FLAIR, Flair is a pre-trained embedding-based model. This means that each word is represented inside a vector space. Words with vector representations most similar to another word are often used in the same context. This allows us, to, therefore, determine the sentiment of any given vector, and therefore, any given sentence. 
3. Keywords Extraction: For keywords extraction we used SPACY which is newer than NLTK or Scikit-Learn, is aimed at making deep learning for text data analysis as simple as possible. The following are the procedures involved in extracting keywords from a text using spacy.

• Split the input text content by tokens
• Extract the hot words from the token list.
  • Set the hot words as the words with pos tag “PROPN“, “ADJ“, or “NOUN“. (POS tag list is customizable)
• Find the most common T number of hot words from the list

Solution Architecture

Deliverables

CommentScoringAPI that will take comments/reviews as input, and do the textual analysis on the given comment and will return the Comment Score based on counts of spell and grammar errors, sentiments, hot keywords.

Tools used

Numpy, pandas, flask, NLTK, Spacy (Keyword Extraction), language tool python (spell and grammar check), flair (Sentimental Analysis)

Language/techniques used

Python 

Business Impact

Client have a user schema that contain all the information of users that have visited there platform, and he/she want to build a Script that will take all the reviews of a certain User as input and than will do textual analysis on all the comments of the user , by textual analysis we mean Spell and Grammar Check, Sentimental Analysis, and Keywords extraction. Based on these factors our Script scored each user and helped Client to understand his/her users well.