2. BIG DATA
BIG DATA – is a general term used to describe the voluminous
amount of unstructured and semi-structured data.
Big data analytics is the process of examining large amounts of
data of a variety of types.
It can process up to 1 yottabytes of data (10008 bytes).
It is basically a concept not technology.
3. SENTIMENT ANALYSIS
Sentiment data is unstructured data that represents opinions,
emotions, and attributes contained in sources such as
- social media posts.
- blogs.
- online product reviews.
- customer support interactions.
Sentiment analysis aims to determine the attitude or the
emotional communication of the public with respect to some
topic.
4. SENTIMENT ANALYSIS IN BIG DATA
The ultimate dream of many Big Data users is to tame the
vast amount of unstructured data in social media,
harnessing how people are thinking, talking, and feeling
about a product.
Sentiment analysis scans tweets, pins, likes, and more for
evidence of good, bad, or even indifferent impressions.
5. SOFTWARES USED
Sentiment analysis is implemented using
Apache hadoop
– A software that is required to analyze
huge . amount of data.
Apache flume
– It is required to fetch the data from a
social . site to HDFS.
Rstudio
– It enables us to present the analyzed
data in a graphical manner.
7. HOW THE DATA IS OBTAINED..?
In this analysis sentiment data related to the product ‘Google
glass’ is obtained from a social site Twitter using Flume.
8. HOW DATA IS PROCESSED…?
The obtained data is analyzed using map/reduce technique in
hadoop environment.
9. ANALYZED DATA…
The sentiments obtained is represented in graph in hourly basis
using Rstudio.
10. BENEFITS OF PRODUCT SENTIMENT ANALYSIS
Companies come to know their online brand reputation in
market.
Gain Business Intelligence.
Improve Customer Service.
Guides the customers to choose a product.
11. RESEARCH WORKS
Noisy texts (those with spelling/grammatical mistakes,
missing/problematic punctuation and slang) are still a big
challenge to most sentiment analysis systems.
Many of the statements about entities are factual in nature
and yet they still carry sentiment. Current sentiment
analysis approaches determine the sentiment of subjective
statements and overlook such objective statements.