Search
Generic filters
Exact matches only
Search
Generic filters
Exact matches only

Review Inspector

Overview

In the world of internet, there is a lot of business information, but 80% of this information is unstructured i.e. unorganized, and it is expected to increase to 93% by 2020 due to constant use of social media, emails, documents, photos, videos, etc. This unstructured information gives a lot of information about your customers, your customer’s brand perceptions, your competitors, and much more. People share their positive and negative experiences regarding a product and provide feedback. This information in the form of online reviews, in turn, shapes the views of other people who proactively seek such information before purchasing a product. They give reviews about different products they have used. This impacts the views of other people regarding this product. First thing people see before buying a product or service is the online reviews.

We will see how the Review Inspector analyzes the sentiment of these reviews so that business owners can align their strategies with customer demand. Review Inspector does Sentiment Analysis as well as POS Tagging of reviews.

Sentiment Analysis:

  • Sentiment Analysis informs whether the sentiment of the review is positive, negative or neutral.

  • You can input a sentence of your choice and gauge the underlying sentiment.

POS Tagging:

  • POS Tagging (Part Of Speech Tagging) is the process of marking up a word in a text (corpus) as corresponding to a particular part of speech, based on both its definition and its context.

Our Approach

To solve the problem, we use DLTK.ai. Let’s see how DLTK works:

  • Firstly, the user will pass a sentence.
  • It goes to DLTK Language (a Natural Language Processing module in DLTK ).
  • It analyzes and gives the sentiment i.e. positive, negative or neutral, as well as, the part of speech of all words using POS Tagger.

Project Creation

First, we need to create a project in the DLTK Console.

In DLTK Console, we can build a model in two ways:

  • Using SDK (For Developer)
  • Using Interface (For Non-Developer)

Using SDKs

If you want to develop a model using SDK, just copy the API key from DLTK Console.

To install python SDK, use following command:

pip install dltk_ai

Connect to DLTK - Console

Description

You can access the services provided by enabling API for DLTK language. DLTK provides DltkAiClient where you have to pass your API KEY as an argument.

import dltk_ai
c = dltk_ai.DltkAiClient("YOUR API KEY")

Face Detection

Description

The Computer Vision’s face detection APIs identifies the faces and returns the image with detected faces.
Code: PYTHON 
import dltk_ai
c = dltk_ai.DltkAiClient("YOUR API KEY")
Response: 
import dltk_ai
c = dltk_ai.DltkAiClient("YOUR API KEY")

Sentiment Analytics

Description

The DLTK language’s Sentiment Analysis APIs identify the sentiments and return the JSON with Sentiment Analysis details. Code: PYTHON 
sentence = client.sentiment_analysis("The rooftop cafeteria of hotel was great.")
Response : 
response
{
 'x': 230,
 'y': 290,
  'width': 90,
  'height': 90,
  'ratio': 0
}

Sentiment Analytics

Description

The DLTK language’s Sentiment Analysis APIs identify the sentiments and return the JSON with Sentiment Analysis details. Code: PYTHON 
sentence = client.sentiment_analysis("The rooftop cafeteria of hotel was great.")
Response : 
{
   'text': "The rooftop cafeteria of hotel was great.",
    'polarity': 3,
    'emotion': 'POSITIVE',
    'msg': None
}

POS Tagger

Description

You can find Part Of Speech (POS) of each word in a sentence using DLTK language.
Code: PYTHON 
sentence = client.pos_tagger("The stay was great")
Response : 
{
  {
    'text': 'The stay was great',
    'result': {'The': 'DT', 'was': 'VBD', 'great': 'JJ', 'stay': 'NN'},
    'msg': None
  }
}

Summary

Review Inspector is just a small application of Dltk Language. We can extend the use case such as:

  • Analyzing the sentiment of comments for our social media posts.

  • We can also use it for faster customer support by filtering negative sentiments in forums by keeping them as a high priority.

Login

Register