ETRI Journal

Electronics and Telecommunications Research Institute (한국전자통신연구원)
권호 표지
DOI QR코드

DOI QR Code

Intensified Sentiment Analysis of Customer Product Reviews Using Acoustic and Textual Features

  • Received : 2015.07.28
  • Accepted : 2016.01.18
  • Published : 2016.06.01
Download PDF
⟨ Previous Next ⟩

Abstract

Sentiment analysis incorporates natural language processing and artificial intelligence and has evolved as an important research area. Sentiment analysis on product reviews has been used in widespread applications to improve customer retention and business processes. In this paper, we propose a method for performing an intensified sentiment analysis on customer product reviews. The method involves the extraction of two feature sets from each of the given customer product reviews, a set of acoustic features (representing emotions) and a set of lexical features (representing sentiments). These sets are then combined and used in a supervised classifier to predict the sentiments of customers. We use an audio speech dataset prepared from Amazon product reviews and downloaded from the YouTube portal for the purposes of our experimental evaluations.

Keywords

References

  1. J. Wiebe and E. Riloff, "Creating Subjective and Objective Sentence Classifiers from Unannotated Texts," Int. Conf. Intell. Text Process. Computational Linguistics, Mexico City, Mexico, 2005, pp. 486-497.
  2. A. Esuli and F. Sebastiani, "SentiWordNet: A Publicly Available Lexical Resource for Opinion Mining," Language Resources Evaluation Conf., Genoa, Italy, May 2006, pp. 417-422.
  3. A.L. Maas et al., "Learning Word Vectors for Sentiment Analysis," Proc. Ann. Meeting Association Computational Linguistics: Human Language Technol., Portland, OR, USA, 2011, pp. 142-150.
  4. L.P. Morency, R. Mihalcea, and P. Doshi, "Towards Multimodal Sentiment Analysis: Harvesting Opinions from the Web," Int. Conf. Multimodal Interfaces, Alicante, Spain, 2011, pp. 169-176.
  5. J. Wagner et al., "Exploring Fusion Methods for Multimodal Emotion Recognition with Missing Data," IEEE Trans. Affective Comput., vol. 2, no. 4, Dec. 2011, pp. 206-218. https://doi.org/10.1109/T-AFFC.2011.12
  6. F. Eyben, M. Wollmer, and B. Schuller, "OpenEAR - Introducing the Munich Open-Source Emotion and Affect Recognition Toolkit," Int. Conf. Affective Comput. Intell. Interaction Workshop, Amsterdam, Netherlands, Sept. 10-12, 2009, pp. 8-12.
  7. C. Busso, S. Lee, and S. Narayanan, "Analysis of Emotionally Salient Aspects of Fundamental Frequency for Emotion Detection," IEEE Trans. Audio, Speech Language Process., vol. 17, no. 4, May 2009, pp. 582-596. https://doi.org/10.1109/TASL.2008.2009578
  8. D. Ververidis, C. Kotropoulos, and I. Pitas, "Automatic Emotional Speech Classification," Int. Conf. Acoust., Speech Signal Process., Montreal, Canada, May 2004, pp. 593-596.
  9. Y. Han, G. Wang, and Y. Yang, "Speech Emotion Recognition based on MFCC," J. ChongQing University Posts Telecommun., vol. 20, no. 15, 2008, pp. 1162-1181.
  10. D. Povey et al., "The Kaldi Speech Recognition Toolkit," IEEE Workshop Automat. Speech Recog. Understanding, Hawaii, USA, Dec. 2011, pp. 1-4.
  11. T.L. Pao et al., "Mandarin Emotional Speech Recognition Based on SVM and NN," Int. Conf. Pattern Recogn., vol. 1, Hong Kong, China, Sept. 2006, pp. 1096-1100.
  12. P.D. Turney, "Thumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification of Reviews," Ann. Proc. Meeting Assoc. Computational Linguistics, Philadelphia, PA, USA, 2002, pp. 417-424.
  13. M. Hu and B. Liu, "Mining and Summarizing Customer Reviews," Proc. ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining, Seattle, WA, USA, 2004, pp. 168-177.
  14. M. Taboada et al., "Lexicon-Based Methods for Sentiment Analysis," Computational Linguistics, vol. 37, no. 2, May 2011, pp. 267-307. https://doi.org/10.1162/COLI_a_00049
  15. B. Yang and C. Cardie, "Extracting Opinion Expressions with Semi-markov Conditional Random Fields," Conf. Empirical Methods Natural Language Process. Computational Natural Language Learn., Jeju, Rep. of Korea, 2012, pp. 1335-1345.
  16. C.O. Alm, D. Roth, and R. Sproat, "Emotions from Text: Machine Learning for Text-Based Emotion Prediction," Conf. Empirical Methods Natural Language Process., Vancouver, Canada, 2005, pp. 347-354.
  17. K. Balog, G. Mishne, and M. de Rijke, "Why are They Excited? Identifying and Explaining Spikes in Blog Mood Levels," Proc. Conf. European Chapter Assoc. Computational Linguistics, Trento, Italy, 2006, pp. 207-210.
  18. P. Carvalho et al., "Liars and Saviors in a Sentiment Annotated Corpus of Comments to Political Debates," Proc. Ann. Meeting Assoc. Computational Linguistics, Portland, OR, USA, 2011, pp. 564-568.
  19. J.H. Oh et al., "Why Question Answering Using Sentiment Analysis and Word Classes," Joint Conf. Empirical Methods Natural Language Process. Computational Natural Language Learn., Jeju, Rep. of Korea, 2012, pp. 368-378.
  20. G. Carenini, R. Ng, and X. Zhou, "Summarizing Emails with Conversational Cohesion and Subjectivity," Assoc. Computational Linguistics: Human Language Technol., Columbus, OH, USA, 2008, pp. 773-782.
  21. A. Athar and S. Teufel, "Context-Enhanced Citation Sentiment Detection," Conf. North America Chapter Assoc. Computational Linguistics: Human Language Technol., Montreal, Canada, 2012, pp. 597-601.
  22. B. Pang, L. Lee, and S. Vaithyanathan, "Thumbs Up?: Sentiment Classification Using Machine Learning Techniques," Assoc. Computational Linguistics Conf. Empirical Methods Natural Language Process., Morristown, NJ, USA, 2002, pp. 79-86.
  23. S. Ezzat, N. el Gayar, and M. Ghanem, "Sentiment Analysis of Call Centre Audio Conversations Using Text Classification," Int. J. Comput. Inf. Syst. Ind. Manag. Appl., vol. 4, no. 1, 2012, pp. 619-627.
  24. E. Dragut and C. Fellbaum, "The Role of Adverbs in Sentiment Analysis," Frame Semantics NLP: Workshop Honor Chuck Fillmore (1929-2014), Baltimore, MA, USA, 2004, pp. 38-41.
  25. X. Hu et al., "Unsupervised Sentiment Analysis with Emotional Signals," Proc. Int. Conf. World Wide Web, Rio de Janeiro, Brazil, 2013, pp. 607-618.
  26. M. Charfuelan and M. Schroder, "Correlation Analysis of Sentiment Analysis Scores and Acoustic Features in Audiobook Narratives," Int. Workshop Corpora Res. Emotion Sentiment Social Signals, Istanbul, Turkey, 2012, pp. 1-5.
  27. S. Moghaddam and M. Ester, "Opinion Digger: An Unsupervised Opinion Miner from Unstructured Product Reviews," Proc. ACM Int. Conf. Inf. Knowl. Manag., Toronto, Canada, Oct. 2010, pp. 1825-1828.
  28. C. Busso et al., "Analysis of Emotion Recognition Using Facial Expressions, Speech and Multimodal Information," Proc. Int. Conf. Multimodal Interfaces, State College, PA, USA, Oct. 13, 2004, pp. 205-211.
  29. R. Tato et al., "Emotional Space Improves Emotion Recognition," Int. Conf. Spoken Language Process., CO, USA, 2002, pp. 2029-2032.
  30. M. El Ayadi, M. Kamel, and F. Karray, "Survey on Speech Emotion Recognition: Features, Classification Schemes, and Databases," Pattern Recogn., vol. 44, no. 3, 2011, pp. 572-587. https://doi.org/10.1016/j.patcog.2010.09.020
  31. D. Ververidis and C. Kotropoulos, "Emotional Speech Recognition: Resources, Features, and Methods," Speech Commun., vol. 48, no. 9, Sept. 2006, pp. 1162-1181. https://doi.org/10.1016/j.specom.2006.04.003
  32. M.C. de Marneffe and C.D. Manning, "The Stanford Typed Dependencies Representation," Proc. Workshop Crossframework Cross-Domain Parser Evaluation, Manchester, UK, Aug. 23, 2008, pp. 1-8.
  33. V. Perez-Rosas, R. Mihalcea, and L. Morency, "Utterance-Level Multimodal Sentiment Analysis," Ann. Meeting Association Computational Linguistics, Sofia, Bulgaria, Aug. 4, 2013, pp. 973-982.
  34. S. Poria et al., "Fusing Audio, Visual and Textual Clues for Sentiment Analysis from Multimodal Content," Neurocomputing, vol. 174, Jan. 2016, pp. 50-59. https://doi.org/10.1016/j.neucom.2015.01.095
  35. K.L. Wuensch, "What is a Likert Scale? and How Do You Pronounce 'Likert?'," Ph.D. dissertation, East Carolina University, Greenville, North Carolina , USA, Apr. 30, 2009.
  36. H. Drucker, D. Wu, and V. Vapnik, "Support Vector Machines for Spam Categorization," IEEE Trans. Neural Netw., Sept. 1999, pp. 1048-1054. https://doi.org/10.1109/72.788645
  37. S. Dumais et al., "Inductive Learning Algorithms and Representations for Text Categorization," Int. Conf. Inf. Knowl. Manag., Washington, DC, USA, Nov. 1998, pp. 148-155.
  38. T. Joachims, "Text Categorization with Support Vector Machines: Learning with Many Relevant Features," European Conf. Mach. Learn., Chemnitz, Germany, Apr. 21-23, 1998, pp. 137-142.
  39. C. Chang and C. Lin, "LIBSVM: A Library for Support Vector Machines," ACM Trans. Intell. Syst. Technol., vol. 2, no. 3, Apr. 2011, pp. 27-54.