Scribd
Upload
63 views19 pages

Opinion Mining: Abhishek Srivastava & Prashant Singh Thakur

The document discusses opinion mining and various techniques related to it. It defines opinion mining as an approach to natural language processing that identifies the emotional tone behind text using data mining, machine learning and artificial intelligence. It discusses types of opinions like direct opinions on objects and comparisons. It also describes different types of opinion mining like fine-grained sentiment analysis, emotion detection, intent-based analysis and aspect-based analysis. Finally, it outlines some applications and challenges of opinion analysis.

Uploaded by

simran yadav
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
63 views19 pages

Opinion Mining: Abhishek Srivastava & Prashant Singh Thakur

The document discusses opinion mining and various techniques related to it. It defines opinion mining as an approach to natural language processing that identifies the emotional tone behind text using data mining, machine learning and artificial intelligence. It discusses types of opinions like direct opinions on objects and comparisons. It also describes different types of opinion mining like fine-grained sentiment analysis, emotion detection, intent-based analysis and aspect-based analysis. Finally, it outlines some applications and challenges of opinion analysis.

Uploaded by

simran yadav
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/ 19

OPINION MINING

ABHISHEK SRIVASTAVA
&
PRASHANT SINGH THAKUR
WHAT IS OPINION MINING?
 Sentiment analysis, also referred to as opinion mining,
is an approach to natural language processing (NLP)
that identifies the emotional tone behind a body of text.
This is a popular way for organizations to determine and
categorize opinions about a product, service or idea. It
involves the use of (data mining), machine learning
(ML) and artificial intelligence (AI) to mine text for
sentiment and subjective information.

2
TYPES OF OPINIONS
I. Direct Opinions: sentiment expressions on objects. E.g.
policies, politicians, movies, products.
E.g." I find myself in support of the Senate Judiciary Committee, which
approved legislation that clears the way for millions of undocumented
workers to continue working in America and seek citizenship.”
II.Comparisons: relations expressing similarities or differences of
more than one object.
E.g. “I think Bush will beat Kerry in the presidential elections” or “The
lens quality of Camera A is better than Camera B”
3
TYPES OF OPINION MINING
1. FINE-GRAINED SENTIMENT
ANALYSIS.
2. EMOTION DETECTION
IDENTIFIES.
3. INTENT-BASED ANALYSIS.
4. ASPECT-BASED ANALYSIS.

4
1. FINE-GRAINED SENTIMENT ANALYSIS

Fine-grained sentiment analysis provides a more precise level


of polarity by breaking it down into further categories, usually
very positive to very negative. This can be considered the
opinion equivalent of ratings on a 5-star scale.

5
6
2. EMOTION DETECTION IDENTIFIES

Emotion detection identifies specific emotions rather than


positivity and negativity. Examples could include happiness,
frustration, shock, anger and sadness.

7
EMOTION DETECTION

8
3. INTENT-BASED ANALYSIS

 Intent-based analysis recognizes actions behind a text in


addition to opinion. For example, an online comment
expressing frustration about changing a battery could prompt
customer service to reach out to resolve that specific issue.

9
4. ASPECT-BASED ANALYSIS

 Aspect-based analysis gathers the specific component being


positively or negatively mentioned. For example, a customer
might leave a review on a product saying the battery life was
too short. Then, the system will return that the negative
sentiment is not about the product as a whole, but about the
battery life

10
11
12
13
APPLICATIONS OF OPINION
ANALYSIS
1.IDENTIFYING BRAND AWARENESS, REPUTATION AND POPULARITY AT A SPECIFIC
MOMENT OR OVER TIME.
2.TRACKING CONSUMER RECEPTION OF NEW PRODUCTS OR
FEATURES.
3.EVALUATING THE SUCCESS OF A MARKETING CAMPAIGN, PINPOINTING THE
TARGET AUDIENCE OR DEMOGRAPHICS.
4.COLLECTING CUSTOMER FEEDBACK FROM SOCIAL MEDIA,
WEBSITES OR ONLINE FORMS.
5.CONDUCTING MARKET RESEARCH.
6.CATEGORIZING CUSTOMER SERVICE REQUESTS.

14
CHALLENGES WITH SENTIMENT ANALYSIS
 Challenges associated with sentiment analysis typically revolve around inaccuracies in training models. Objectivity, or
comments with a neutral sentiment, tend to pose a problem for systems and are often misidentified. For example, if a
customer received the wrong color item and submitted a comment "The product was blue," this would be identified as
neutral when in fact it should be negative.

Join the Discussion


 Sentiment can also be challenging to identify when systems cannot understand the context or tone. Answers to polls or
survey questions like "nothing" or "everything" are hard to categorize when the context is not given, as they could be
labelled as positive or negative depending on the question. Similarly, irony and sarcasm often cannot be explicitly
trained and lead to falsely labelled sentiments.
 Computer programs also have trouble when encountering emojis and irrelevant information. Special attention needs to
be given to training models with emojis and neutral data so as to not improperly flag texts.
 Finally, people can be contradictory in their statements. Most reviews will have both positive and negative comments,
which is somewhat manageable by analyzing sentences one at a time. However, the more informal the medium
(Twitter or blog posts, for example), the more likely people are to combine different opinions in the same sentence and
the more difficult it will be for a computer to parse.

15
ASPECT BASED OPINION MINING ON
RESTAURANT REVIEWS
BY H.A. Caldera

There are three different levels of opinion mining; Document based, Sentence
based and Aspect based. Document and Sentence based opinion mining focus on
overall polarity of document and sentence respectively and do not describe the
important aspects of each opinions which is more accurate.
Aspect level opinion mining classifies customer reviews based on important
features. In aspect level opinion mining, there are two parts. The first part is the
opinion word identification. The second part is orientation detection.
For example, a restaurant review can be “Environment is bad, but foods are
delicious”. Here the review comments are on two aspects. One aspect is the
“environment” and the other is the “food”.
16
Formula used for differentiation is:-

Aggregate_Positive _polarity[j] = ΣiPositive_Poli, j


Aggregate_Negative _polarity[j] = ΣiNegative_Poli, j

In the above formula “i” represent a review. For sentiment analysis,


supervised machine learning approach is used

CONCLUSION:
Opinion mining is a combination of data mining and natural language processing. Using
opinion mining, a document can be analyzed and its overall idea can be extracted. Previous
studies have used document level, and sentence level opinion mining to resolve this issue.
However, in this research, the author has discussed about aspect based opinion mining

17
MINING OPINION FEATURES IN
CUSTOMER REVIEWS
BY MINQING HU & BING LIU

 Now we all know that for any popular products the reviews are in hundred & thousands.
 Makes difficult for a customer to read & make a decision on whether to buy product or not.
 In this paper, they proposed a no of technique like opinion summarization system based on NLP & Data mining.
 Large No of customer reviews comes under positive or negative sentiments.
 Easy for customer to read about a particular sentiments

18
OPINION MINING ON TOURISM
BY R.RAJKUMAR

 Online tourisms forms and social networks have become popular in sharing
tourism related data.
 This paper proposes a platform for extraction and summarizing of opinions
expressed by users.
 Platform is evaluated using a manually pre classification data sets of user
reviews. Proposed system retriever by the tweets in twitter.
 Existing system:-Reviews are not concise e.g. people who liked the hotel
location but didn’t like the ambience of the hotel.
 In this paper presented opinion mining platform for extracting and classifying
reviews posted in twitter .
 Classify and segregates reviews based on certain categories so that user
can easily extract useful and necessary information.
19

You might also like