Site Loader


research on this review paper presents the complicated usage of prescribed
drugs which perform in the zone of data mining for organizing a high volume of
data and usage of complex function for performing more refined analysis using
cloud platform. The aim of this paper is to understand the extensive and
innovative frame that uses the social media to characterize drug abuse. The
rough idea of this survey is an analytical approach to analyze social media for
acquiring the emerging trends in drug abuse by applying powerful techniques
such as cloud computing and Map Reduce model. This paper describes how to
capture important data to evaluate from networks like Twitter, Facebook, and
Instagram. Big data techniques are used to mine the useful content for analysis.

We Will Write a Custom Essay Specifically
For You For Only $13.90/page!

order now


media is an internet-based application which can be used for sharing
information and creative ideas through a communication network channel.
Currently, social media is used for enumerating the information regarding
patients for understanding the symptoms of the patient. Social media allows
message sharing, collecting information and deliver to the healthcare space.
Healthcare space is the one that provides the data of a patient with their
permission. The proper way of accessing data and programs over the internet
known as the cloud. It models the social media such as facebook, twitter etc
using network-based analysis method. Currently, the scientific research often
requires a vast amount of estimation during simulation and data processing. The
scientific problem can be solved by automatic computational through collection
or array list which is emerged by a set of sensors. The main aim of this paper
is to use the social media as an informative source for analyzing the illicit
drug activities in the society. Data mining play an important role in all
stages during the development of the drug. The use of data mining techniques
during the drug development is mainly classified into two areas:

New Effect of Drug Identification: conflict reaction occurs mostly, but
sometimes new remedial effect occurs and effects in some population.

Suitableness in drug use.

crawler which basis in Map Reduce Model is performing the data mining task for
the distributed computation of data which is implemented in the framework of
Hadoop. Data processing consists of three stages, first and second stages are
collecting information from different media sources and filter it which results
in a small dataset with data corresponding to solve the task. On the last stage
the small dataset which is analyzed using refined models. The main advantage of
this paper is that to provide knowledge about the drug used for a group of
people which are observed who rarely use drugs or not addicted to drugs and
another aim is to collect the reviews of patients which cause side effects due
to the drug and can prescribe another drug through media.

Literature Survey

V. R. Nagarajan, et at1 social media provide information for the field of
health informatics which includes Bioinformatics, Image informatics, Clinical
informatics, Public health informatics etc. In this paper, they use the methods
called SOMS ( an analysis to check the interrelationship between user posts and
positive or negative comments on drug usage) and hierarchical clustering. This
paper provides a framework which evaluates the positive and negative symptoms
of the disease and also the side effects of treatment common cancers lung

Jun Huan, et al2 frequent subgraph mining is an active research topic in the
data mining community. They use the graph as a general model to represent the
data and can be used in several fields like bioinformatics, web indexing, etc.
The problem of frequent sub-graph mining is to find all frequent subgraphs from
a graph database. In this paper, they propose a new algorithm FFSM(Fast
Frequent Subgraph Mining) for the frequent sub-graph mining problem i.e., to
reduce the number of redundant candidates proposed.

Mathew Herland, et al3  a bulk amount
of data is produced within health informatics and analysis of this data is done
by big data techniques and big data allows potentially unlimited possibilities
for knowledge to be gained. This information can improve health care quality
offered to patients. Several problems will arise while managing this bulk
amount of data, especially how to analyze data in a reliable manner. This paper
presents big data tools and approaches for the analysis of health informatics
data gathered at multiple levels including the molecular, tissue, patient and
population levels.

Deepa Sharma, et al4 appearance of recent techniques for scientific knowledge
collection has resulted in the large-scale accumulation of information relating
various fields. Retrieval of data from huge knowledge base by typical query
ways is an inadequate form. Therefore, cluster analysis is used for analysis
and k means clustering algorithm is mostly used for data mining applications.
The analysis of the cancer dataset with the k means and then applying with the
Som. This paper proposes a technique for creating knowledge retrieval more
practical and efficient using SOM with K means clustering technique, So as to
get better clustering with reduced quality.

Hari Kumar and Dr. P. Uma Maheshwari 5, Big data is the term that
characterized by its increasing volume, velocity, variety,  and veracity. All these characteristics make
processing on this big data a complex task. So, for processing such data Author
need to do it differently like Map-Reduce Framework. When an organization
exchanges data for mining useful information from this Big Data then the
privacy of the data becomes an important problem in the previous years, several
privacy preserving models have been given. Anonymizing the dataset can be done
on many operations like generalization, suppression, and specialization. These
algorithms are all suitable for a dataset that does not have the
characteristics of the Big Data. To perpetuate the privacy of dataset an
algorithm was proposed recently. An author represents how the growth of big
Data characteristics, the Map-Reduce framework for privacy preserving in future
of our research.


review paper instant approach for mining and managing data from the social
chain which depends upon a combination of a large amount of data through social
networks which is based on infrastructure paradigms and the combination of big
data. Map Reduce model is a useful method to mine, store and process bulk data
from the social network. Mined data processing is performed by Hadoop which
simplifies development of new algorithms and provides high scalability and
flexibility. The Map-Reduce programming path has been successfully used by
Google for many different purposes. The author attributes this success for many
reasons. First, the model is used, even for a programmer without any experience
with parallel processing and distributed system, because it shields the details
of parallelization, fault tolerance, and load balancing. Second, a large
variety of problem is easily expressible as Map-Reduce computation. For
example, Map Reduce is used for the generalization of data for Google’s
production web search service for sorting, for data mining, for machine
learning and many other systems. This paper presents the development of an
implementation of a Map-Reduce that extend to bulk storage of machines
comprising thousands of machines. The utilization makes efficient use of these
machine resources is suitable for many large computational issues encountered
at Google.



Mr. V. R. Nagarajan, Monisha. P. M., “Extracting Knowledge from Social
Media to Improve Health Informatics”.

Jun  Huan,  Wei 
Wang,  Jan  Prins, 
“Efficient  Mining of  Frequent 
Subgraph in the Presence of Isomorphism”.

Matthew Herland, “A review of data mining using big data in health

Deepa Sharma, “Efficient Data Retrieval using Combine Approach of SOM and
K-Mean Clustering”,   International
Journal of Computer Applications.

Hari Kumar.R M.E (CSE), Dr. P. Uma Maheshwari, Ph.D. “Literature survey on
big data in the cloud,” International Journal of Technical Research and

Post Author: admin


I'm Erica!

Would you like to get a custom essay? How about receiving a customized one?

Check it out