Scribd
Upload
16 views15 pages

Sentiment Analysis

Uploaded by

Akash Singhania
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
16 views15 pages

Sentiment Analysis

Uploaded by

Akash Singhania
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 15

Sentiment

Analysis
Sentiment
Sentiment = feelings

– Attitudes
– Emotions
– Opinions

• It is crucial for businesses to dig into the customer opinions/feelings shared on


digital space like Twitter, Amazon, etc. and get insights about their products or
services

• Such data exists in an overwhelming amount and hence cannot be gauged manually
but, at the same time, requires attention and analysis to bring out valuable insights
Sentiment Analysis
• Also known as opinion mining. It refers to the
interpretation and classification of emotions expressed in
the text. It is a method to extract, identify, or otherwise
characterize the sentiment content of a text unit

• 95% of purchase decisions are made emotionally – this


shows how much emotion and sentiment play into how
well your campaign is doing

• It uses NLP (Natural Language Processing) technique to


understand whether social conversations are positive or
negative and to measure the strength of those emotions

• Sentiment analysis is often performed on textual data


to help businesses monitor brand and product
sentiment in customer feedback and understand
customer needs
Importance of Sentiment Analysis
• As we all are aware that data is widespread everywhere on the Internet and approximately 80% of
the generated data are unstructured

• To be more precise, huge volumes of text data like emails, support tickets, chats, social media
conversations, and so on are getting added every single day

• Though there is so much data available, it becomes hard to analyze it, and it is also a time-
consuming and expensive work without the help of sentimental analysis

• Every organization would wish to cut down customer churn rate to keep up their
performance. When looking to cut down customer churn, it is important to analyze customer
feedback

• With the existence of sentimental analysis, it becomes easier to organize unstructured text by
automatically tagging it with related emotions
Gaining Insights Using Sentiment Analysis
Making Decisions with Sentiment Analysis

It has highly positive reviews by customers, which indicates the company can escalate its
prices given its popularity

Has a neutral outlook amongst the customer which means your company should not change its
pricing

Has an overall negative sentiment associated with it — thus, the company should consider offering
a discount on it to balance the scales
Questions Sentiment Analysis Might Ask

• Is this product review positive or negative?

• Is this customer email satisfied or dissatisfied?

• Based on a sample of tweets, how are people responding to this ad


campaign/product release/news item?

• Etc.
Use Cases
• Social Media Monitoring for Brand Management: Brands can use sentiment analysis
to gauge their Brand’s public outlook. For example, a company can gather all Tweets
with the company’s mention or tag and perform sentiment analysis to learn the
company’s public outlook

• Product/Service Analysis: Brands/Organizations can perform sentiment analysis on


customer reviews to see how well a product or service is doing in the market and make
future decisions accordingly

• Stock Price Prediction: Predicting whether the stocks of a company will go up or down
is crucial for investors. One can determine the same by performing sentiment analysis on
News Headlines of articles containing the company’s name. If the news headlines
pertaining to a particular organization happen to have a positive sentiment - its stock
prices should go up and vice-versa
Challenges in Sentiment Analysis

• People express opinions in complex ways

• The method may be subject to errors in cases such as sarcasm, irony, or ambiguity
Sentiment Analysis

• It is a text analysis method that detects the polarity of the given text. Polarity in
the sentimental analysis is a float number that lies in the range of [-1,1]
where 1 means a positive statement, and -1 means a negative statement

• Sentiment score is measured based on the frequency of positive and negative


words used by customers during their interactions

• If the sentiment score is below 50%, it indicates that the customer experience is
mostly negative, while a score above 80% implies a positive customer experience
Carrying out Sentiment Analysis
• Sentiment analysis mainly uses two methods:

(1) A machine-learning method with which the analytics learns to evaluate


sentiment through the acquisition and integration of knowledge gained
from a large number of sentiment examples, or
(2) A lexical-based method with which the analytics evaluates sentiment by
utilizing a large dictionary of prescored words and phrases

Sentiment analysis has been used successfully for businesses activities,


including predicting stock market movements, determining market trends,
analyzing product defects, and managing crises
Carrying out Sentiment Analysis
• Lexical-based methods use a predefined set of words that carry a specific
sentiment

• They include a simple word or phrase counts; the use of emoticons to detect
polarity (i.e., positive and negative emoticons used in a message); sentiment
lexicons (i.e., based on words in the lexicon that have received specific features
marking positive or negative terms in a message); and the use of psychometric
scales to identify mood-based sentiments

• Machine-learning methods often rely on the use of supervised and unsupervised


machine-learning techniques. One advantage of machine learning methods is
their ability to adapt and create trained models for specific purposes and contexts
Carrying out Sentiment Analysis
Case Analysis
• Amazon Reviews on Musical Instruments

Description of columns in the file:


1. Reviewer.ID - ID of the reviewer, e.g. A2SUAM1J3GNN3B
2. ASIN (Amazon Standard Identification Number) - ID of the
product, e.g. 0000013714
3. Reviewer.Name - Name of the reviewer
4. Helpful - Helpfulness rating of the review, e.g. 2/3
5. Reviews.Text - Text of the review
6. Overall - Rating of the product
7. Summary - Summary of the review
8. Unix.Review.Time - Time of the review (Unix time)
9. Review.Time - Time of the review (raw)
Case Analysis
• Chips

You might also like