Article: Evaluation of video news classification techniques for automatic content personalisation Journal: International Journal of Advanced Media and Communication (IJAMC) 2009 Vol.3 No.4 pp.383 - 403 Abstract: Personalisation tasks require the use of semantic information, extracted from multimedia streams, in order to achieve the benefits of automatic matching user preferences with multimedia content meaning. Text-based classification techniques may be used in closed-captions captured from news programmes, which can define the subject of each piece of news. Latent Semantic Indexing (LSI)-based systems are widely used for information retrieval purposes, and may be adapted to classification tasks; however, some drawbacks of the technique may impose limitations, mainly when considering multiple collections. In this paper, we compare an LSI implementation with a Genetic Algorithm (GA)-based system which was designed with the same objective. We show that the GA alternative achieves better results when used to automatically classify pieces of news video programmes. Inderscience Publishers - linking academia, business and industry through research

Title: Evaluation of video news classification techniques for automatic content personalisation

Authors: Marcelo G. Manzato, Alessandra A. Macedo, Rudinei Goularte

Addresses: Departamento de Ciencias de Computacao, Instituto de Ciencias Matematicas e de Computacao (ICMC), Universidade de Sao Paulo (USP), Campus de Sao Carlos, Caixa Postal 668, 13560-970 Sao Carlos, SP, Brazil. ' Informatica Biomedica, Faculdade de Filosoﬁa, Ciencias e Letras de Ribeirao Preto (FFCLRP), Departamento de Fisica e Matematica (DFM), Universidade de Sao Paulo (USP), Av. Bandeirantes 3900 – Monte Alegre, 14040-901 Ribeirao Preto, SP, Brazil. ' Departamento de Ciencias de Computacao, Instituto de Ciencias Matematicas e de Computacao (ICMC), Universidade de Sao Paulo (USP), Campus de Sao Carlos, Caixa Postal 668, 13560-970 Sao Carlos, SP, Brazil

Abstract: Personalisation tasks require the use of semantic information, extracted from multimedia streams, in order to achieve the benefits of automatic matching user preferences with multimedia content meaning. Text-based classification techniques may be used in closed-captions captured from news programmes, which can define the subject of each piece of news. Latent Semantic Indexing (LSI)-based systems are widely used for information retrieval purposes, and may be adapted to classification tasks; however, some drawbacks of the technique may impose limitations, mainly when considering multiple collections. In this paper, we compare an LSI implementation with a Genetic Algorithm (GA)-based system which was designed with the same objective. We show that the GA alternative achieves better results when used to automatically classify pieces of news video programmes.

Keywords: news classification; GAs; genetic algorithms; LSI; latent semantic indexing; evaluation; content personalisation; news video.

DOI: 10.1504/IJAMC.2009.028709

International Journal of Advanced Media and Communication, 2009 Vol.3 No.4, pp.383 - 403

Published online: 23 Sep 2009 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Evaluation of video news classification techniques for automatic content personalisation

Keep up-to-date