دسته‌بندی احساسی عقاید مبتنی بر یادگیری انتقالی چندمنبعی با استفاده از دسته‌بند متناظر ساختاری وزن‌دار

نوع مقاله: مقاله پژوهشی فارسی

نویسندگان

1 پردیس فنی و مهندسی، دانشکده مهندسی کامپیوتر، دانشگاه یزد، یزد، ایران

2 گروه مهندسی کامپیوتر، دانشگاه شهرکرد، شهرکرد، ایران

چکیده

دسته‌بندی احساسی عقاید زمینه‌ای در پردازش زبان طبیعی است که در سال‌های اخیر با محبوب شدن فروشگاه‌های اینترنتی و امکان درج عقیده در مورد کالا یا سرویس خریداری‌شده مورد توجه پژوهشگران قرار گرفته است. برای آموزش مدل‌های دسته‌بند، به مجموعه داده‌های برچسب‌خورده نیاز است؛ اما عدم وجود نمونه‌های برچسب‌خورده در همه دامنه‌ها و با توجه به دشواری فرایند برچسب زدن نمونه‌ها، می‌بایست به‌نوعی از نمونه‌هایی که در دامنه‌های دیگر وجود دارد برای ساخت مدل‌ها استفاده نمود. در این مقاله روشی برای دسته‌بندی احساسی عقاید به دو دسته مثبت و منفی، مبتنی بر یادگیری انتقالی چندمنبعی ارائه می‌شود. روش پیشنهادی این مقاله با استفاده از یادگیری متناظر ساختاری، اقدام به تطبیق دامنه‌های مختلف نموده و بر اساس روال تکرارشونده یک الگوریتم بوستینگ به نمونه‌های دسته‌بندی‌شده دامنه‌های مختلف، وزنی را تخصیص داده و با ادغام هر یک از دسته‌بندها، در مورد دسته هر عقیده تصمیم‌گیری می‌نماید. وزن‌دهی به نمونه‌ها برای تقویت فرایند دسته‌بندی مبنتی بر فرایند بوستینگ و ترکیب آن با یادگیری متناظر ساختاری مهم‌ترین نوآوری پژوهش جاری است. از مجموعه داده‌های آمازون برای 4 رده مختلف که هر کدام شامل 1000 نمونه مثبت و 1000 نمونه منفی هستند برای آموزش مدل پیشنهادی استفاده شده است. مقدار معیار درستی 89٫64%، 93٫97%، 92٫39% و 90٫17% به ترتیب برای رده‌های الکترونیک، دی‌وی‌دی، کتاب و آشپزخانه به دست آمده و حاکی از مؤثر بودن روش پیشنهادی در قیاس با روش‌های مشابه است.

کلیدواژه‌ها


[1]          L. Deng, “A tutorial survey of architectures, algorithms, and applications for deep learning,” APSIPA Transactions on Signal Information Processing., Vol. 3, no 2, pp. 1-29, 2014.

[2]          S. J. Pan and Q. Yang, “A survey on transfer learning,” IEEE Transactions on Knowledge and Data Engineering, Vol. 22, No 10, pp. 1345–1359, 2010.

[3]          W. Pan, E. Zhong, and Q. Yang, “Transfer learning for text mining,” Mining Text Data, pp. 223–257, 2012.

[4]          J. Pan, X. Hu, Y. Zhang, P. Li, Y. Lin, H. Li, W. He, and L. Li, “Quadruple Transfer Learning: Exploiting both shared and non-shared concepts for text classification,” Knowledge-Based Systems, Vol. 90, pp. 199–210, 2015.

[5]          G. Vinodhini and R. M. Chandrasekaran, “Sentiment analysis and opinion mining: a survey,” International Journal of Advanced Research in Computer Science and Software Engineering, Vol. 2, No 6, pp. 282–292, 2012.

[6]          B. Pang, L. Lee, and S. Vaithyanathan, “Thumbs up? Sentiment Classification using Machine Learning Techniques,” in Proceedings of the conference on Empirical methods in natural language processing (EMNLP), pp. 79-86, 2002.

[7]          M. Thomas, B. Pang, and L. Lee, “Get out the vote: Determining support or opposition from Congressional floor-debate transcripts,” in Proceedings of the 2006 conference on empirical methods in natural language processing, pp. 327–335, 2006.

[8]          B. Pang and L. Lee, “Seeing stars: Exploiting class relationships for sentiment categorization with respect to rating scales,” in Proceedings of the 43rd annual meeting on association for computational linguistics, pp. 115–124, 2005.

[9]          A. B. Rosario, F. Sotgiu, K. De Valck, and T. H. A. Bijmolt, “The effect of electronic word of mouth on sales: A meta-analytic review of platform, product, and metric factors,” Journal of Marketing Science, Vol. 53, no 3, pp. 297-318, 2016.

[10]        A. Hervas-Drane, “Recommended for you: The effect of word of mouth on sales concentration,” International Journal of Research in Marketing., Vol. 32, No 2, pp. 207–218, 2015.

[11]        D.-H. Park and S. Kim, “The effects of consumer knowledge on message processing of electronic word-of-mouth via online consumer reviews,” Electronic Commerce Research and Applications, Vol. 7, No 4, pp. 399–410, 2008.

[12]        M. Hu and B. Liu, “Mining and summarizing customer reviews,” in Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining, pp. 168-177, 2004.

[13]        S.-M. Kim, P. Pantel, T. Chklovski, and M. Pennacchiotti, “Automatically assessing review helpfulness,” in Proceedings of the 2006 Conference on empirical methods in natural language processing, pp. 423–430, 2006.

[14]        S. Basuroy, S. Chatterjee, and S. A. Ravid, “How critical are critical reviews? The box office effects of film critics, star power, and budgets,” Journal of Marketing, Vol. 67, No 4, pp. 103–117, 2003.

[15]        J. A. Chevalier and D. Mayzlin, “The effect of word of mouth on sales: Online book reviews,” Journal of Marketing Research, Vol. 43, No 3, pp. 345–354, 2006.

[16]        H. Baek, J. Ahn, and Y. Choi, “Helpfulness of online consumer reviews: Readers’ objectives and review cues,” International Journal of Electronic Commerce, Vol. 17, No 2, pp. 99–126, 2012.

[17]        Q. Cao, W. Duan, and Q. Gan, “Exploring determinants of voting for the ‘helpfulness’ of online user reviews: A text mining approach,” Decision Support Systems, Vol. 50, No 2, pp. 511–521, 2011.

[18]        N. S. Koh, N. Hu, and E. K. Clemons, “Do online reviews reflect a product’s true perceived quality? An investigation of online movie reviews across cultures,” Electronic Commerce Research and Applications, Vol. 9, No 5, pp. 374–385, 2010.

[19]        W. Duan, B. Gu, and A. B. Whinston, “The dynamics of online word-of-mouth and product sales—An empirical investigation of the movie industry,” Journal of Retailing, Vol. 84, No 2, pp. 233–242, 2008.

[20]        M. Li, L. Huang, C.-H. Tan, and K.-K. Wei, “Helpfulness of online product reviews as seen by consumers: Source and content features,” International Journal of Electronic Commerce, Vol. 17, No 4, pp. 101–136, 2013.

[21]        M. L. Kushwaha and S. D. Rathod, “New Opinion Mining Technique For Online Product Reviews And Features,” Multidisciplinary Journal of Research in Engineering and Technology, Vol. 2, No 4, pp. 852–858, 2015.

[22]        Y. Liu, X. Huang, A. An, and X. Yu, “Modeling and predicting the helpfulness of online reviews,” ICDM ’08 Proceedings of Eighth IEEE International Conference on Data Mining, pp. 443–452, 2008.

[23]        C. Banea, R. Mihalcea, J. Wiebe, and S. Hassan, “Multilingual subjectivity analysis using machine translation,” in Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 127–135, 2008.

[24]        P. Prettenhofer and B. Stein, “Cross-lingual adaptation using structural correspondence learning,” ACM Transactions on Intelligent Systems and Technology, Vol. 3, No 1, pp. 13:1-13:22, 2011.

[25]        J. Blitzer, R. McDonald, and F. Pereira, “Domain adaptation with structural correspondence learning,” in Proceedings of the 2006 conference on empirical methods in natural language processing, pp. 120–128, 2006.

[26]        P. Wang, C. Domeniconi, and J. Hu, “Using wikipedia for co-clustering based cross-domain text classification,” ICDM ’08 Proceedings of Eighth IEEE International Conference on Data Mining, pp. 1085–1090, 2008.

[27]        E. W. Xiang, B. Cao, D. H. Hu, and Q. Yang, “Bridging domains using world wide knowledge for transfer learning,” IEEE Transactions on Knowledge and Data Engineering, Vol. 22, No 6, pp. 770–783, 2010.

[28]        Y. He, C. Lin, and H. Alani, “Automatically extracting polarity-bearing topics for cross-domain sentiment classification,” in Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Vol. 1, pp. 123–131, 2011.

[29]        K. Denecke, “Are SentiWordNet scores suited for multi-domain sentiment classification?,” 2009 Fourth International Conference on Digital Information Management (ICDIM 2009), pp. 1–6, 2009.

[30]        D. Bollegala, D. Weir, and J. Carroll, “Using multiple sources to construct a sentiment sensitive thesaurus for cross-domain sentiment classification,” in Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Vol. 1, pp. 132–141, 2011.

[31]        N. Manjunathan, “Cross-Domain Opinion Mining Using a Thesaurus in Social Media Content,” International Journal of Innovative Research in Computer and Communication Engineering, Vol. 2, No 5, 2014.

[32]        Liang, J., Zhang, K., Zhou, X., Hu, Y., Tan, J., and S. Bai,  "Leveraging Latent Sentiment Constraint in Probabilistic Matrix Factorization for Cross-domain Sentiment Classification", The International Conference on Computational Science (ICCS 2016),  Vol. 80, 366-375, 2016.

 [33]       Zhou, G., Zhou, Y., Guo, X., Tu, X., and T. He, "Cross-domain sentiment classification via topical correspondence transfer", Neurocomputing, Vol. 159, Issue C, pp. 298-305, 2015.

 [34]       C. Cagatay, and M. Nangir. "A sentiment classification model based on multiple classifiers", Applied Soft Computing, Vol. 50, pp. 135-141, 2017.‏

[35]        V. Malik, and  A. Kumar, "Sentiment Analysis of Twitter Data Using Naive Bayes Algorithm", International Journal on Recent and Innovation Trends in Computing and Communication, Vol. 6, No 4, pp.120-125, 2018.

[36]        A. Hasan, S. Moin, A. Karim and S. Shamshirband, "Machine Learning-Based Sentiment Analysis for Twitter Accounts", Mathematical and Computational Applications, Vol. 23, No 11, pp. 2297-8747, 2018.

[37]        H. M. Keerthi Kumar, B. S. Harish and H. K. Darshan, "Sentiment Analysis on IMDb Movie Reviews Using Hybrid Feature Extraction Method", International Journal of Interactive Multimedia and Artificial Intelligence,  Vol. 5, No 5, pp. 109-114, 2018.

 [38]       M. Chen and Y. Sun, "Sentiment Analysis with Amazon Review Data", Standford University, 2017, Available at http://cs229.stanford.edu/proj2017/final-reports/5163147.pdf.

[39]        T. Haque, N. N. Saber and F. M. Shah, “Sentiment Analysis on Large Scale Amazon Product Reviews”, IEEE International Conference on Innovative Research and Development (ICIRD), pp. 1-6, 2018.

[40]        Y. Freund and R. E. Schapire, “A desicion-theoretic generalization of on-line learning and an application to boosting,” in European conference on computational learning theory, pp. 23–37, 1995.

[41]        S. J. Pan, X. Ni, J.-T. Sun, Q. Yang, and Z. Chen, “Cross-domain sentiment classification via spectral feature alignment,” in Proceedings of the 19th international conference on World Wide Web, pp. 751–760, 2010.