Profiling television viewing using data mining

A dissertation submitted to the Faculty of Science, University of the Witwatersrand, Johannesburg, in fulfilment of the requirements for the degree of Master of Science Johannesburg, February 2013 === This study conducted a critical review of data-mining techniques used to extract meaningful informa...

Full description

Bibliographic Details
Main Author:	Chanza, Martin Mudongo
Format:	Others
Language:	en
Published:	2013
Subjects:	Data mining. Television viewers - South Africa.
Online Access:	http://hdl.handle.net/10539/12688

id	ndltd-netd.ac.za-oai-union.ndltd.org-wits-oai-wiredspace.wits.ac.za-10539-12688
record_format	oai_dc
spelling	ndltd-netd.ac.za-oai-union.ndltd.org-wits-oai-wiredspace.wits.ac.za-10539-126882019-05-11T03:41:20Z Profiling television viewing using data mining Chanza, Martin Mudongo Data mining. Television viewers - South Africa. A dissertation submitted to the Faculty of Science, University of the Witwatersrand, Johannesburg, in fulfilment of the requirements for the degree of Master of Science Johannesburg, February 2013 This study conducted a critical review of data-mining techniques used to extract meaningful information from very large databases. The study aimed to determine cluster analysis methods suitable for the analysis of binary television-viewing data. Television-viewing data from the South African Broadcasting Corporation was used for the analysis. Partitioning and hierarchical clustering methods are compared in the dissertation. The study also examines distance measures used in the clustering of binary data. Particular consideration was given to methods for determining the most appropriate number of clusters to extract. Based on the results of the cluster analysis, four television-viewer profiles were determined. These viewer profiles will enable the South African Broadcasting Corporation to provide viewer-targeted programming. 2013-04-25T12:22:06Z 2013-04-25T12:22:06Z 2013-04-25 Thesis http://hdl.handle.net/10539/12688 en application/pdf application/pdf
collection	NDLTD
language	en
format	Others
sources	NDLTD
topic	Data mining. Television viewers - South Africa.
spellingShingle	Data mining. Television viewers - South Africa. Chanza, Martin Mudongo Profiling television viewing using data mining
description	A dissertation submitted to the Faculty of Science, University of the Witwatersrand, Johannesburg, in fulfilment of the requirements for the degree of Master of Science Johannesburg, February 2013 === This study conducted a critical review of data-mining techniques used to extract meaningful information from very large databases. The study aimed to determine cluster analysis methods suitable for the analysis of binary television-viewing data. Television-viewing data from the South African Broadcasting Corporation was used for the analysis. Partitioning and hierarchical clustering methods are compared in the dissertation. The study also examines distance measures used in the clustering of binary data. Particular consideration was given to methods for determining the most appropriate number of clusters to extract. Based on the results of the cluster analysis, four television-viewer profiles were determined. These viewer profiles will enable the South African Broadcasting Corporation to provide viewer-targeted programming.
author	Chanza, Martin Mudongo
author_facet	Chanza, Martin Mudongo
author_sort	Chanza, Martin Mudongo
title	Profiling television viewing using data mining
title_short	Profiling television viewing using data mining
title_full	Profiling television viewing using data mining
title_fullStr	Profiling television viewing using data mining
title_full_unstemmed	Profiling television viewing using data mining
title_sort	profiling television viewing using data mining
publishDate	2013
url	http://hdl.handle.net/10539/12688
work_keys_str_mv	AT chanzamartinmudongo profilingtelevisionviewingusingdatamining
_version_	1719083365721702400

Profiling television viewing using data mining

Similar Items