• JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
 
  Bookmark and Share
 
 
Doctoral Thesis
DOI
10.11606/T.3.2016.tde-19072016-115713
Document
Author
Full name
Renata Lopes Rosa
E-mail
Institute/School/College
Knowledge Area
Date of Defense
Published
São Paulo, 2015
Supervisor
Committee
Bressan, Graça (President)
Goularte, Rudinei
Kovach, Stephan
Oliveira, José Maria Parente de
Ruggiero, Wilson Vicente
Title in Portuguese
Análise de sentimentos e afetividade de textos extraídos das redes sociais.
Keywords in Portuguese
Análise de dados
Comunicação
Internet
Redes sociais
Abstract in Portuguese
Atualmente, os usuários expressam seus desejos e preferências em relação a um objeto, conteúdo ou evento por meio das redes sociais; portanto, analisar os sentimentos de uma pessoa no mundo digital sobre o que a rodeia tem sido cada vez mais frequente com o intuito de conhecer as preferências desta pessoa. O estudo propõe um novo mecanismo e cálculo de sentimentos e afetividade, aperfeiçoando a análise de sentimentos. Um mecanismo de cálculo de sentimentos associado a um fator de correção correspondente a n-gramas, tempos verbais, expressões e às características pessoas, tais como idade, gênero e escolaridade é desenvolvido neste trabalho. Os sentimentos negativos, neutros e positivos são extraídos de frases das redes sociais. As frases são classificadas em intensidade de sentimentos e em polaridade positiva, negativa ou neutra, por meio de um novo dicionário de palavras em português e de um novo cálculo de sentimentos. O cálculo de sentimentos possui regras específicas para tempos verbais (presente e passado) e advérbios. Os sentimentos das palavras são extraídos por meio de adjetivos, substantivos, palavras únicas (unigramas) e palavras que associadas (bigramas e trigramas) possuem um significado diferente de palavras únicas. Para validação do desempenho do dicionário e do novo mecanismo de cálculo de sentimentos, os resultados sao comparados com uma ferramenta de análise de sentimentos j´a existente, a SentiStrength e são validados por meio de testes subjetivos, com avaliadores remotos, com uma técnica denominada de crowdsourcing e por aprendizagem de máquina. O estudo também analisa a afetividade das frases e propõe uma métrica denominada de Brazillian Affective Metric (AFMBr), extraindo emoções de raiva, alegria, tristeza, surpresa e nojo. A solução de análise de sentimentos e afetividade é aplicada em um sistema de recomendação de músicas, como estudo de caso, o qual sugere conteúdos conforme o estado sentimental da pessoa.
Title in English
Sentiment analysis and affection of texts extracted from social networks.
Keywords in English
Communication
Data analysis
Internet
Social networks
Abstract in English
Currently, users express their wishes and preferences in relation to an object, content or event through social networks; therefore analyze the sentiments of a person in the digital world about what surrounds the person has been increasingly used in order to know the preferences of this person. The study proposes new metrics of sentiments and affection, improving the sentiment analysis. The sentiment analysis metric associated with a corresponding correction factor for n-grams, tenses, expressions and personal characteristics such as age, gender and education is developed in this work. Negative, neutral and positive sentiments are extracted from social networks phrases. The sentences are ranked in positive, neutral or negative sentiment intensity or polarity by a new dictionary of words in Portuguese language and is extracted the sentiments. The calculation of sentiments has specific rules for verb tenses (present and past) and adverbs. The sentiments are extracted by means of adjectives, nouns, unigrams and associated words (bigrams and trigrams) that have a different meaning of single words. To validate the dictionary performance and new sentiments calculation mechanisms, the results are compared with an analysis tool of sentiments named of SentiStrength and are validated by subjective tests, with remote evaluators, with a technique named of crowdsourcing and machine learning. The study also analyzes the affection of sentences and proposes a metric called Brazillian Affective Metric (AFM-Br), that extracts emotions of anger, joy, sadness, surprise and disgust. The sentiment analysis solution and affection is applied in a music recommendation system, as a case study, which suggests content according to the emotional state of the person.
 
WARNING - Viewing this document is conditioned on your acceptance of the following terms of use:
This document is only for private use for research and teaching activities. Reproduction for commercial use is forbidden. This rights cover the whole data about this document as well as its contents. Any uses or copies of this document in whole or in part must include the author's name.
RenataLopesRosa2015.pdf (972.56 Kbytes)
Publishing Date
2016-07-22
 
WARNING: The material described below relates to works resulting from this thesis or dissertation. The contents of these works are the author's responsibility.
  • RODRIGUEZ, D. Z., et al. A Video Complexity Index for Cluster Computing. International Journal of Computing and Digital Systems [online], 2014, vol. 3, p. 29-35. Available from: http://www.uob.edu.bh/uob__files/651/v3-1/V3-N1-04.pdf.
  • RODRIGUEZ, D. Z., et al. Intelligent Learning Techniques applied to Quality Level in Voice over IP Communications. International Journal on Advances in Internet Technology [online], 2013, vol. 6, p. 145-155. Available from: http://www.iariajournals.org/internet_technology/tocv6n34.html.
  • RODRIGUEZ, DEMOSTENES, et al. Quality metric to assess video streaming service over TCP considering temporal location of pauses [doi:10.1109/tce.2012.6311346]. IEEE Transactions on Consumer Electronics [online], 2012, vol. 58, p. 985-992.
  • ROSA, Renata Lopes, Bressan, Graca, and Geraldo Luciano Toledo. Analysis of Online Survey Services for Marketing Research. International Journal of Electronic Commerce Studies [online], 2012, vol. 3, p. 135-144. Available from: http://https://docs.google.com/a/academic-journal.org/viewer?a=v&pid=sites&srcid=YWNhZGVtaWMtam91cm5hbC5vcmd8aWplY3N8Z3g6NWMyMzJmMTAzM2Q0OTAyZA.
  • LOPES ROSA, RENATA, RODRIGUEZ, DEMOSTENES ZEGARRA, and Bressan, Graca. SentiMeter-Br: Facebook and Twitter Analysis Tool to Discover Consumers' Sentiment. In ICT 2013, The Ninth Advanced International Conference on Telecommunications, Roma, 2013. Proceedings of The Seventh International Conference on Digital Society. : IARIA, 2013.
  • ZEGARRA RODRÍGUEZ, DEMÓSTENES, et al. Video quality subjective assessment considering cognitive criteria and user preferences on video content [doi:10.1145/2382636.2382693]. In 18th Simpósio Brasileiro de Sistemas Multimídia e Web - WebMedia, São Paulo/SP, 2012. Proceedings of the 18th Brazilian symposium on Multimedia and the web - WebMedia '12.New York : ACM Press, 2012.
  • RODRIGUEZ, D. Z., ROSA, Renata Lopes, and BRESSAN, Graça. A Business Model for Video Transmission Services using Dynamic Adaptation Streaming over HTTP. In AICT 2013, The Ninth Advanced International Conference on Telecommunications, Roma, 2013. AICT 2013, The Ninth Advanced International Conference on Telecommunications. : IARIA, 2013.
  • RODRIGUEZ, DEMOSTENES ZEGARRA, ROSA, Renata Lopes, and Bressan, Graca. A billing system model for voice call service in cellular networks based on voice quality [doi:10.1109/ISCE.2013.6570267]. In 2013 IEEE 17th International Symposium on Consumer Electronics (ISCE), Hsinchu City. 2013 IEEE International Symposium on Consumer Electronics (ISCE). : IEEE, 2013.
  • ROSA, Renata Lopes, et al. Recommendation system based on user profile extracted from an IMS network with emphasis on social network and digital TV [doi:10.1145/2078216.2078224]. In Latin America Networking Conference, Quito, 2011. LANC '11 Proceedings of the 6th Latin America Networking Conference.New York : ACM, 2011.
  • ROSA, Renata Lopes, BRESSAN, Graça, and Geraldo Luciano Toledo. Analysis of online surveys services for marketing research. In International Conference on Marketing Studies - ICMS2011, Kuala Lumpur, 2011. Proceedings of International Conference on Marketing Studies - ICMS2011.New Taipei City, Taiwan : Academy of Taiwan Information Systems Research - ATISR, 2011, 2011.
  • ROSA, Renata Lopes, RODRIGUEZ, DEMOSTENES ZEGARRA, and Bressan, Graca. SentiMeter-Br: A new social web analysis metric to discover consumers' sentiment [doi:10.1109/ISCE.2013.6570158]. In 2013 IEEE 17th International Symposium on Consumer Electronics (ISCE), Hsinchu City, 2013. 2013 IEEE International Symposium on Consumer Electronics (ISCE). : IEEE, 2013.
  • ROSA, Renata Lopes, RODRIGUEZ, DEMOSTENES ZEGARRA, and Bressan, Graca. SentiMeter-Br: A Social Web Analysis Tool to Discover Consumers' Sentiment [doi:10.1109/MDM.2013.80]. In 2013 14th IEEE International Conference on Mobile Data Management (MDM), Milan, 2013. 2013 IEEE 14th International Conference on Mobile Data Management. : IEEE, 2013.
All rights of the thesis/dissertation are from the authors
CeTI-SC/STI
Digital Library of Theses and Dissertations of USP. Copyright © 2001-2020. All rights reserved.