• Refine Query
  • Source
  • Publication year
  • to
  • Language
  • 1
  • Tagged with
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • About
  • The Global ETD Search service is a free service for researchers to find electronic theses and dissertations. This service is provided by the Networked Digital Library of Theses and Dissertations.
    Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
1

Máquinas de classificação para detectar polaridade de mensagens de texto em redes sociais / Sentiment analysis on social networks using ensembles

Von Lochter, Johannes 18 November 2015 (has links)
Submitted by Milena Rubi (milenarubi@ufscar.br) on 2016-10-17T13:16:57Z No. of bitstreams: 1 LOCHTER_Johannes_2015.pdf: 611113 bytes, checksum: 55a3009a4bb5c0fe9f30edf98fe0bc77 (MD5) / Approved for entry into archive by Milena Rubi (milenarubi@ufscar.br) on 2016-10-17T13:17:13Z (GMT) No. of bitstreams: 1 LOCHTER_Johannes_2015.pdf: 611113 bytes, checksum: 55a3009a4bb5c0fe9f30edf98fe0bc77 (MD5) / Approved for entry into archive by Milena Rubi (milenarubi@ufscar.br) on 2016-10-17T13:17:24Z (GMT) No. of bitstreams: 1 LOCHTER_Johannes_2015.pdf: 611113 bytes, checksum: 55a3009a4bb5c0fe9f30edf98fe0bc77 (MD5) / Made available in DSpace on 2016-10-17T13:17:36Z (GMT). No. of bitstreams: 1 LOCHTER_Johannes_2015.pdf: 611113 bytes, checksum: 55a3009a4bb5c0fe9f30edf98fe0bc77 (MD5) Previous issue date: 2015-11-18 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) / The popularity of social networks have attracted attention of companies. The growing amount of connected users and messages posted per day make these environments fruitful to detect needs, tendencies, opinions, and other interesting information that can feed marketing and sales departments. However, the most social networks impose size limit to messages, which lead users to compact them by using abbreviations, slangs, and symbols. Recent works in literature have reported advances in minimizing the impact created by noisy messages in text categorization tasks by means of semantic dictionaries and ontology models. They are used to normalize and expand short and messy text messages before using them with a machine learning approach. In this way, we have proposed an ensemble of machine learning methods and natural language processing techniques to find the best way to combine text processing approaches with classification methods to automatically detect opinion in short english text messages. Our experiments were diligently designed to ensure statistically sound results, which indicate that the proposed system has achieved a performance higher than the individual established classifiers. / A popularidade das redes sociais tem atraído a atenção das empresas. O crescimento do número de usuários e das mensagens enviadas por dia transforma esse ambiente em uma rica fonte de informações para descoberta de necessidades, tendências, opiniões e outras informações que podem auxiliar departamentos de vendas e marketing. Contudo,a maioria das redes sociais impõe limite no tamanho das mensagens, o que leva os usuários a usarem abreviações e gírias para compactarem o texto. Trabalhos na literatura demonstraram avanço na minimização do impacto de mensagens ruidosas nas tarefas de categorização textual através da utilização de dicionários semânticos e modelos ontológicos. Com a aplicação destes, as amostras são normalizadas e expandidas antes de serem apresentadas aos métodos preditivos. Assim, nesta dissertação é proposto um comitê de máquinas de classificação utilizando técnicas de processamento de linguagem natural para detectar opiniões automaticamente em mensagens curtas de texto em inglês. Os resulta-dos apresentados foram validados estatisticamente e indicaram que o sistema proposto obteve capacidade preditiva superior aos métodos preditivos isolados.

Page generated in 0.0786 seconds