Content uploaded by Prafulla E Ajmire
Author content
All content in this area was uploaded by Prafulla E Ajmire on Jan 14, 2019
Content may be subject to copyright.
An Analytical Study of Use of Data mining for Entertainment
Ms. Apeksha G. Sharma. A. A. Tayade P. S. Bodkhe P. E .Ajmire
apekshasharma882@gmail.com arvindtayade40@gmail.com psbodkhe@gmail.com peajmire@rediffmail.com
Department of Computer Science & Application,
G. S. Science, Arts & Commerce College, Khamgaon, 444303.
Maharashtra, India
Abstract:- In Entertainment domain TV shows are dominant. The various services providers are
continuously increasing various types of shows, but the customer’s choice varies according to the
locality and according to the season. The services providers of TV channel provide the package of
their own groups. The techniques of data mining can used to analyze and found the new groups or
packages or different channels selected by customer.
Keywords:- Data mining, techniques, Television shows, clustering.
INTRODUCTION: Television has played most important role in our daily life. In different
channels telecast many different shows related dancing comedy, singing ,and new reality shows
are increasing day by day. Viewer are more interested in television program and episodes. The
episodes discharge on the end of week. In today’s generation the television reality shows are
increasing [1]. There are many different ways to find out the TRP of these shows.TRP is television
rating point. TRP is a tool to judge which program are viewed the most. By using TRP tool we
find the index choice of people and also find the popularity of a particular channel [2]. For
calculation purpose the device is attached to TV set in a few thousand viewer’s houses for judging
purpose. The number are treated as a sample form the overall TV shows in different sectors. TRP
tool records the time and the program that viewers watches on a particular day. The average is
taken for 30 days periods which gives the viewership status for particular channel[3]. TRP system
is used to measure popularity of TV shows using people’s meter. TRP can be compared among
different shows. We have k- mean and incremental k-mean algorithm to compare the TRP.
Data Mining: “Data Mining is nothing but the extracting information from huge sets of data.”Data
Mining is the process of sorting through large data sets to identify the patterns and establish
relationship to solve problems through data analysis. Data mining tools allows enterprises to
predict future trends[4].Data mining is the process of discovering patterns in large data sets
involving methods at the intersection of machine learing sataistics, and database system.
Dept. of Comp. Sci. & Application, G S College, Khamgaon Page 1
Fig 1 Data Mining
In the term data mining the goal of extraction of patterns and knowledge from large amount of
data not the extraction of data itself. There is a huge amount of data available to the providers.
There is no of use of data until it is converted into useful information. It is important to analyze
this huge amount of data and extract useful information from it. Data mining is an
interdisciplinary subfield with an overall goal to extract information from a data set and transform
the information into a comprehensible structure for further use. Data mining is analysis step of
KDD [5].
Fig 2 Inside Data Mining
We need to perform extraction of information is not the only process; DM is also involves the
processes such as Data Cleaning, Data Integration, Data Transformation, Data Mining, Pattern
Evaluation and Data Presentation. Once all these processes are over, we would be able to use this
information in many applications such as Fraud Detection, Market Analysis, Production Control,
Science Exploration, etc [6].
Clustering: - Clustering is a grouping of a particular set of objects based on their characterizes ,
aggregating them according to their similarities. We can say that cluster means objects of similar
group [7]. The process of collection of that different clusters. This clustering analysis allows an
object not to part of cluster. At the time of cluster analysis, we first partition the set of data into
Dept. of Comp. Sci. & Application, G S College, Khamgaon Page 2
groups. That analysis on data similarity and then assign the labels to the groups. Clustering is the
main task in many fields for statistical analyzing the data in the data mining.
DATA MINING APPLICATION : Data mining is the wide and applications. Find patterns and
connections data mining can be used. This technology is popular ,because it allows them to learn
more about their customers and make smart marketing decisions. DM can be used to find out the
connections. This technology is popular because it allows to more about the customer and making
a smart decision [8].The data mining applications can be generic or domain specific. To be an
intelligent system the generic application is required by its own certain decisions like: selection of
data, selection of data mining method, presentation and interpretation of the result. Some
applications cannot take its own these decisions in generic data mining but guide the users for
select the data, selection of data mining method and for the interpretation of the results. Data
mining multi agent based on application has automatic selection capability of data mining
technique can be applied [9] .
Data mining in Finance:- Data mining in finance is used to increase the customer
loyalty by collecting and analyzing customer behavior data. Finance in data mining is help
to that predict customer behavior and launch relevant products and services. It also helps
in discovering hidden correlations between various financial indicators that needs to find
the suspicious activities with high potential risk. It identifies non- fraudulent or fraudulent
actions. It is done by collection historical data. And then Turing it into useful and valid
data.
Market basket analysis (MBA):-In data mining technique MBA applies it helps to
understanding what channels are likely to be purchased together according to association
rules, primarily with the aim of identifying cross-selling opportunities [10]. Clues as given
to a customer might have bought if an idea had occurred to MBA. So, it can be used in
deciding the location .Also used in promotion of goods by means of combo-package.
Aid to marketing or retailing:- Data mining help to direct marketers by providing
useful and accurate trends on purchasing behavior of their customers and also help them in
predicting which channels their customers may be interested in buying. Data mining
allows companies to identify their best customers, attract customers, aware customers via
mail marketing, and maximize profitability by means of identifying profitable customers
[11].
Customer Segmentation:-Data mining can be used in clustering. In Data mining
clustering can be helps providers to improve their customers base , providers can works on
Dept. of Comp. Sci. & Application, G S College, Khamgaon Page 3
target area and based on customers purchase history and customers interest or monitoring
the activity of customers [12]. Here is a white paper on how telecom providers can group
of pre paid customers to identify pattern in term of money spend in recharging. Clustering
customer based on the behaviors, which is helps to manage the customers relationship.
Telecommunication: - One of the first industry to adopt data mining technology is
Telecommunication. Telecommunication is the base of data so that data minig is used to
perform operations on data and obtain the desired result [13]. Some of the reasons to use
data mining are as follows:-[14]
To detect frauds
To retain customers
To know the customers
Products and Services which yield highest amount of profit
Factors that influence customers to call more at certain times
SYSTEM USE TO FIND TRP : The below Fig.3, shows that the architecture of TV shows
popularity prediction system. The system flow is divided into followings way. In this system
firstly fetches TV show .Where text reviews related to the particular show, actor, and director are
given.
Fig.3: Architecture of TV Show Popularity Prediction using Sentiment Analysis in Social Network
A. Hash tagged data set :-
Dept. of Comp. Sci. & Application, G S College, Khamgaon Page 4
We first filter out duplicate tweets, non-English tweets, and tweets that do not contain the hashtags
to create the hashtagged dataset. From the remaining set, we investigate the distribution of
hashtags and identify what we hope will be sets of frequent hashtags that are indicative of
positive, negative and neutral messages.For development and training hashtags are used to select
the tweets. In text mining pre-processing is one of the important steps ,Natural Language
Processing (NLP) and information retrieval (IR) [15]. which gives tokenization, normalization
.that means remove @,remove #and URL. Extract interesting and non-trivial knowledge from
unstructured text data here Data pre-processing is used . For deciding retrivalinformation is
important which documents in a collection should be retrieved so we can satisfy a user's need for
information.
B. Tokenization
The action of breaking the terms of a law of text into words, symbols, phrases, or other
meaningful elements called tokens. The list of tokens becomes input for the furtherprocessing
such as parsing or text mining. It splits sentences into words. Textual is only a block of characters
at the beginning[15].All processes in order recovery require the words of the data set. F.
C.Sentiment Analysis
Another primary use case for NLP is Sentiment analysis ., data scientists can assess comments on
social media by Using sentiment analysis to see how their business's brand is performing, for
example, customer review notes service teams is help to identify areas where people want the
business and to perform better.
D. Analysis
Day Wise Popularity Analysis: In the day wise popularity we can calculate popularity os shows by
day wise. We can analyzes one day popularity like live show is a one day show so user want to
find particular date wise analysis for eg:- Cricket , Aword shows etc. Season wise Popularity
Analysis: In these Season wise popularity can we can calculate season wise popularity.In three
seasons which type of shows was to hit in given particular period this type analysis done in season
wise analysis for eg:- reality shows[16]. Month wise Popularity Analysis : We can calculate
popularity of shows by month wise and list of these shows and watch it for eg daily sopas.
CONCLUSION: As per the rule every customer has to select the group of channels from the
available service providers. From the table given below, it is found that there may be one or two
channels that has more or better TRP so in place of selecting group of channels, customer should
have the rights to select the channels individually. It means each channel can be customize and
form new group as per the customer choice.
Sr No. TV Shows Channel Name Score
1 News Aaj Tak [17] 125034
Dept. of Comp. Sci. & Application, G S College, Khamgaon Page 5
2 News ABP News[17] 85738
3 News Zee News[17] 84053
4 Indian Idol Sony TV 8451
5 Naagin Colors TV[18] 8148
6 Kundali Bhagya Zee TV[18] 7128
7 Taarak Mehta ka Oolta chashma Sab TV[18] 6409
8 Radha krishan Star Bharat[19] 5984
9 Dance Plus Star plus[20] 4510
10 Big Boss Colors Tv[20] 4395
REFERENCE:-
[1] Sunil Bhutada, Aishwarya Lakshmi,V.Mary Shravya , J.Sneha Reddy, “Reality Show Analytics
For TRP Rating Based On Viewers Opinion” Vol.05 Issue.04 Apr-2018.
[2] Asst Prof. KLUniversity, “Analysis and prediction of Television Shows Popularity Rating
using K-Mean Algorithm”,Vol-9,Issue 1,Jan 2018.
[3] Priyank Jain,Prateek Jakate,Aksh Dhotre,Jigar Bhati, “A Novel Approach To Analysis of TV
Shows using Social Media,Machine Learning and Big Data”, Vol 4 No.6, Dec2015
[4] http://searchsqlserver.techtarget.com
[5] https://en.m.wikipedia.org
[6] https://www.tutorialspoint.com/data_mining/dm_overview.htm
[7] https://www.quora.com/What-is-clustering-in-data-mining-What-is-its-significance
[8] Mr S.P. Deshpande and Dr. V.M Thakare “ DM System and Application A review”
International Journal of Distributed and Parallel System (IJDPS) Vol.1,No.1,Sept 2010].
[9] Y. Ramamohan, K. Vasantharao, C. Kalyana Chakravarti, A.S.K.Ratnam “A Study of Data
Mining Tools in Knowledge Discovery Process” International Journal of Soft Computing and
Engineering (IJSCE) ISSN: 2231-2307, Volume-2, Issue-3, July 2012 .
[10] Vikas Gupta, Prof.Devanand “A survey on Data Mining: Tools, Techniques, Application.
trends and issue” , Vol-4,Issue 3,March-2013.
[11 Vikas Gupta & prof Devanad “ A survey on Data mining tools , techniques , Applications ,
trends and issue” , march-2013.
[12] http:// www.tutorialspoint.com/data_mining/dm_cluster_analysis.htm
[13] “Data mining in tele-communication”, MohsinNadaf and Vidya Kadam ,2013.
[14] Mohsin Nadaf and Vidya Kadam,”Data Mining in Telecommunication”, Vol-2,Issue-3,2013.
[15] Tejaswi Kadam,Gaurav Saraf,Vikas Dewadkar,P.J Chate”TV Shiw Popularity Prediction
Using Semtiment Analysis in Social Network”, Vol- 04Issue-11 Nov2017
[16] Jun Ai, Linzhi li ,Zhan Su, Chunxue Wu “Online –rating prediction based on an improved”
[17] http://www.quora.com/which-TV-news-channels-ha.
[18] http://mtwiki.blogspot.com/2018/05/top-10-hindi-reality-tv-shows-by-trp-rating.html.
[19] http://mtwiki.blogspot.com/2018/10/top-10-hindi-reality-tv-shows-by-trp-rating.html.
[20] http://mtwiki.blogspot.com/2015/09/top-10-hindi-reality-tv-shows-by-trp-rating.html.
Dept. of Comp. Sci. & Application, G S College, Khamgaon Page 6