1. NCCU Academic Hub
  2. Publications
  3. College of Commerce
  4. Theses
  5. Item

Publications-Theses

Article View/Open

Publication Export

Google ScholarTM

NCCU Library

Citation Infomation

Related Publications in TAIR

題名 應用情感分析於產品比較與品牌推薦系統-以美妝產品為例
Application of Sentiment Analysis in Product Comparison and Brand Recommendation System - Taking Cosmetics as an Example
作者 俞舒禔
Yu, Shu-Ti
貢獻者 鄭宇庭<br>郭訓志
Cheng , Yu Ting<br>Kuo , Hsun Chih
俞舒禔
Yu, Shu-Ti
關鍵詞 文字探勘
Word2vec
CRF
PMI
情感分析
日期 2018
上傳時間 1-Jun-2018 17:34:45 (UTC+8)
摘要 近年來，社群商業智慧（SBI, Social Business Intelligence）興盛，且IBM公司指出「在現今社會當中早已不再是B to B（企業對企業）或是B to C（企業對客戶）的關係，而是P to P（人對人）」，多數企業看準了P to P消費者互動模式之繁榮而從中衍生出龐大商機。因此本研究欲藉由三大美妝評論網站蒐集之文字資料進行文字探勘，將非結構化資料轉為結構化資料後，利用字典比對法搭配機器學習方法，自定義詞典後透過Google於2013年開源之Word2vec深度學習方法擴建辭典，接著透過CRF詞性辨識方法建模，用以辨識出形容詞與屬性詞，以便後續進行PMI相似性比對，此法可大幅降低自然語言處理在分析上的人工作業時間，本研究在情感分析上設計一套專屬於美妝產品情感取向之算分方式且對文章進行分類（正面、中性、負面），所建構之情感取向辨識系統預測文章之準確率約為78 %；本研究之另一研究為利用統計方法將單篇美妝文章對於各屬性辭典（顏色、味道、效果、價格）給予星等。從消費者角度出發，消費者可透過選定之品牌以及產品畫出雷達圖進行比較，進而得知自家美妝產品以及他牌美妝產品的優缺點，透過顏色、味道、效果以及價錢上的平均星等數，可以迅速得知哪一品牌的美妝產品較受美妝部落客以及廣大網路評論者的歡迎；從美妝品牌公司角度出發，若在某項屬性之平均星等數與他牌有所差距，可自我檢討並改進，若在某屬性有較高的平均星等數，可維持其優良的部分並提升自家美妝產品的競爭力。
參考文獻 王志瑋，2011，數位口碑探勘法於商品推薦之研究，國立成功大學資訊管理研究所碩士論文。
何偉豪，2010，使用最大熵值法於產品評論之評價等級預測-以Amazon 為例，國立東華大學數為知識管理碩士學位學程。
李日斌，2014，探討臺灣網民對鄰國的情感，國立中山大學資訊管理學系碩士論文。
李啟菁，2010，中文部落格文章之意見分析，國立台北科技大學資訊工程系研究所碩士論文。
李淑惠，2014，運用文字探勘技術於口碑分析之研究，東吳大學資訊管理學系論文。
張育蓉，2012，使用情緒分析於圖書館使用者滿意度評估之研究，國立中興大學圖書資訊學研究所碩士學位論文。
張莊平，2011，中文文法剖析應用於電影評論之意見情感分類，國立臺灣師範大學資訊工程研究所碩士論文。
陳立，2009，中文情感語意自動分類之研究，國立臺灣師範大學資訊工程研究所碩士論文。
楊惠淳，2011，以主客觀分析與相互資訊檢索探討情感分析之準確度-以電影評論為例，國立臺北科技大學資訊與運籌管理研究所碩士論文。
蕭瑞祥、姜青山、曹金豐、簡之文，2012，部落格文章情感分析之研究，私立淡江大學資訊管理學系。
謝邦昌、鄭宇廷、謝邦彥、硬是愛數據應用股份有限公司，2017，玩轉社群:文字大數據實作，五南出版社。
簡智宏，2015，應用文字探勘技術於概念股輿情與股價共同移動之研究-以蘋果供應鏈為例，國立政治大學資訊管理研究所碩士論文。
鐘任明、李維平、吳澤民，2007，運用文字探勘於日內股價漲跌趨勢預測之研究，中華管理評論國際學報。

Benamara, F., Cesarano, C., Picariello, A. & Subrahmanian. (2007). Sentiment analysis:Adjectives and adverbs are better than adjectives alone. In ICWSM Boulder, CO USA.
Blair-Goldensohn, S., Hannan, K., McDonald, R., Neylon, T., Reis, G. & Reynar, J. (2008). Building a sentiment summarizer for local service reviews. In paper presented at the www 2008 workshop on NLP challenges in the information explosion era (NLPIX 2008), Beijing, April, 22.
Bollen, J., Mao, H. & Zeng, X.(2010). Twitter mood predicts the stock market, Journal of computational science. Vol. 2, p.1-8.
Culnan,M., McHugh, P. & Zubillaga, J.(2010).How large U.S. companies can use twitter and other social media to gain business value. MIS Quarterly Executive, 9(4), p.243-259.
Dey, L., Haque, S. M., Khurdiya, A. & Shroff, G. (2011). Acquiring competitive intelligence from social media. In Proceedings of the 2011 joint workshop on multilingual OCR and analytics for noisy unstructured text data Article3.
Gamon, M. (2004). Sentiment classification on customer feedback data: Noisy data, large feature vectors, and the role of linguistic analysis. In Proceedings of the 20th International Conference on Computational Linguistics, p.841.
Gary, K., Jennifer, P. & Margaret, E. R.(2013). How Censorship in China Allows Government Criticism but Silences Collective Expression. American Political Science Review, 107, 2 (May), p.1-18. Copy at http://j.mp/2nxNUhk
Gidofalvi, G.(2001). Using news articles to predict stock price movements. Department of Computer Science. University of California, San Diego.
Governatori, G. & Iannella, R.(2011). A medeling and reasoning framework for social networks policies. Enterprise Information Systems, 5(1), p.145-167.
Hassan, S., Yulan, H. & Harith, A.(2012). Semantic Sentiment Analysis of Twitter. In: Cudré-Mauroux P. et al. (eds) The Semantic Web – ISWC 2012. ISWC 2012. Lecture Notes in Computer Science, Vol. 7649.
Kaplan, A. & Haenlein, M.(2010). User of the world, unite! The challenges and opportunities of social media. Business Horizons, 53, p.59-68.
Ku, L. W. & Chen, H. H.(2007). Mining Opinions from the Web:Beyond Relevance Retrieval. Journal of American Society for Information Science and Technology, 58, p.1838-1850.
Larsson, A. & Moe, H.(2011). Studying political microblogging: Twitter users in the 2010 Swedish election campaign. New Media and Society. Vol. 14, p.727-747.
Lim, M.(2012). Clicks, cabs, and coffee houses: Social media and oppositional movements in Egypt, 2004-2011. Journal of Communication. Vol.62, p.231-248.
Liu, Y., Huang, X., An, A. & Yu, X.(2007). ARSA: A sentiment-aware model for predicting sales performance using blogs. In Proceedings of the 30th annual international ACMSIGIR conference on research and development in information retrieval. p.607-614. New York.
Liu, B.(2009). Sentiment analysis and opinion mining. Synthesis Lectures on Human Language Technologies, Vol.5, No.1, p.1-167.
Manning, C. & Schutze, H.(1999). MITCogNet. Foundations of statistical natural language processing, Vol.59. MIT Press.
Mostafa, M.(2013). More than words: Social networks’text mining for customer brand sentiments. Expert systems with applications, Vol.40, Issue 10, p.4241-4251.
Mukherjee, S.(2012). Sentiment analysis-A literature survey, Indian Institute of Technology, Bombay.
Na, J., Thet, T., & Khoo, C.(2010). Comparing sentiment expression in movie reviews from four online genres. Online Information Review. Vol. 34, p.317-338.
Pang, B., Lee, L. & Viathyanathan, S.(2002). Thumbs up? Sentiment classification using machine learning techniques. In Proceeding of the ACL-02 conference on empirical methods in natural language processing, Vol. 10, p. 79-86, Association for Computational Linguistics.
Park, N., Kee, K. F. & Valenzuela, S. (2009). Being immersed in social networking environment:Facebook groups, uses and gratifications, and social outcomes. Cyber Psychology & Behavior, 12(6), p.729-733.
Popescu, A., & Etzioni, O.(2005). Extracting product features and opinions from reviews. In Proceedings of the conference on human language technology and empirical methods in natural language processing, p.339-346. Association for Computational Linguistics.
Schumaker, R. & Chen, H.(2006). Textual Analysis of Stock Market Prediction Using Financial News Articles. 12th Americas Conference on Information Systems (AMCIS).
Thet, T., Na, J. & Khoo, C.(2008). Aspects-based sentiment analysis of movie reviews on discussion boards. Journal of Information Science. Vol. 36, p. 823-848.
Tsantis, L. & Castellani, J.(2001).Enhancing learning environments through solution-based knowledge discovery tools, Journal of Special Education Technology,Vol.16, Issue 4, p.1-35.
Tumasjan, A., Sprenger, T., Sandner, P. & Welpe, I.(2011). Election forecasts with Twitter: How 140 characters reflect the political landscape. Social Science Computer Review. Vol. 29, p.402-418.
Turney, P. D.(2002). Thumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification of Reviews. Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL), Philadelphia, July, p.417-424.
Wang, S. G., Wei, Y. J., Zhang,W., Li, D.Y. & Li, W.(2007). A hybrid method of feature selection for Chinese text sentiment classification. In Proceedings of the 4th International Conference on Fuzzy Systems and Knowledge Discovery, p.435-439.IEEE Computer Society.
Williams, C. & Gulati, G.(2008). What is a social network worth? Facebook and vote share in the 2008 presidential primaries. In the annual meeting of the American political science association, p.1-17. Boston, MA: APSA.
Yessenov, K. & Misailovic, S.(2009). Sentiment analysis of movie review comments. Methodology, p.1-17.
Yi, J., Nasukawa, T., Bunescu, R. & Niblack, W.(2003). Sentiment analyzer: Extracting sentiment about a given topic using natural language-processing techniques. In proceedings of the 3rd IEEE international conference on data mining (ICDM’ 2003), p.427-434. Los Alamitos, CA.
Yong, Y., Qiang Y., Guirong, X. & Wenyuan D.(2002). Transferring Naïve Bayes classifiers for text classification. In Conference of the American Association for Artificial Intelligence (AAAI).
Zhang,W., Xu, H. & Wan, W.(2012). Weakness Finder: Find product weakness from Chinese reviews by using aspects based sentiment analysis. Expert System with Applications, Vol.39, Issue 11, p.10283-10291.
描述 碩士
國立政治大學
統計學系
105354006
資料來源 http://thesis.lib.nccu.edu.tw/record/#G1053540061
資料類型 thesis
dc.contributor.advisor 鄭宇庭<br>郭訓志zh_TW
dc.contributor.advisor Cheng , Yu Ting<br>Kuo , Hsun Chihen_US
dc.contributor.author (Authors) 俞舒禔zh_TW
dc.contributor.author (Authors) Yu, Shu-Tien_US
dc.creator (作者) 俞舒禔zh_TW
dc.creator (作者) Yu, Shu-Tien_US
dc.date (日期) 2018en_US
dc.date.accessioned 1-Jun-2018 17:34:45 (UTC+8)-
dc.date.available 1-Jun-2018 17:34:45 (UTC+8)-
dc.date.issued (上傳時間) 1-Jun-2018 17:34:45 (UTC+8)-
dc.identifier (Other Identifiers) G1053540061en_US
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/117444-
dc.description (描述) 碩士zh_TW
dc.description (描述) 國立政治大學zh_TW
dc.description (描述) 統計學系zh_TW
dc.description (描述) 105354006zh_TW
dc.description.abstract (摘要) 近年來，社群商業智慧（SBI, Social Business Intelligence）興盛，且IBM公司指出「在現今社會當中早已不再是B to B（企業對企業）或是B to C（企業對客戶）的關係，而是P to P（人對人）」，多數企業看準了P to P消費者互動模式之繁榮而從中衍生出龐大商機。因此本研究欲藉由三大美妝評論網站蒐集之文字資料進行文字探勘，將非結構化資料轉為結構化資料後，利用字典比對法搭配機器學習方法，自定義詞典後透過Google於2013年開源之Word2vec深度學習方法擴建辭典，接著透過CRF詞性辨識方法建模，用以辨識出形容詞與屬性詞，以便後續進行PMI相似性比對，此法可大幅降低自然語言處理在分析上的人工作業時間，本研究在情感分析上設計一套專屬於美妝產品情感取向之算分方式且對文章進行分類（正面、中性、負面），所建構之情感取向辨識系統預測文章之準確率約為78 %；本研究之另一研究為利用統計方法將單篇美妝文章對於各屬性辭典（顏色、味道、效果、價格）給予星等。從消費者角度出發，消費者可透過選定之品牌以及產品畫出雷達圖進行比較，進而得知自家美妝產品以及他牌美妝產品的優缺點，透過顏色、味道、效果以及價錢上的平均星等數，可以迅速得知哪一品牌的美妝產品較受美妝部落客以及廣大網路評論者的歡迎；從美妝品牌公司角度出發，若在某項屬性之平均星等數與他牌有所差距，可自我檢討並改進，若在某屬性有較高的平均星等數，可維持其優良的部分並提升自家美妝產品的競爭力。zh_TW
dc.description.tableofcontents 目 錄 I
表目錄 II
圖目錄 III
第壹章 緒論 1
第一節 研究背景 1
第二節 研究動機與目的 2
第三節 研究流程 3
第貳章 文獻探討 5
第一節 文字探勘之相關研究 5
第二節 情感分析之相關研究 5
第三節 情感分數計算之相關研究 8
第四節 情感分析應用之相關研究 9
第參章 研究方法 12
第一節 研究架構 12
第二節 文字預處理 13
第三節 WORD2VEC介紹 14
第四節 條件隨機場 CRF 詞性辨識 16
第肆章 實證分析 21
第一節 資料蒐集及方法 21
第二節 資料預處理 23
第三節 詞性辨識 26
第四節 PMI 互信息比對 27
第五節 文章情緒分數之算法設計 29
第六節 文章各屬性情緒分數之算法設計 35
第七節 產品比較與品牌推薦 41
第伍章 結論與未來研究 49
第一節 結論 49
第二節 未來研究 50
參考文獻 53		zh_TW
dc.format.extent 1679070 bytes-
dc.format.mimetype application/pdf-
dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G1053540061en_US
dc.subject (關鍵詞) 文字探勘zh_TW
dc.subject (關鍵詞) Word2veczh_TW
dc.subject (關鍵詞) CRFzh_TW
dc.subject (關鍵詞) PMIzh_TW
dc.subject (關鍵詞) 情感分析zh_TW
dc.title (題名) 應用情感分析於產品比較與品牌推薦系統-以美妝產品為例zh_TW
dc.title (題名) Application of Sentiment Analysis in Product Comparison and Brand Recommendation System - Taking Cosmetics as an Exampleen_US
dc.type (資料類型) thesisen_US
dc.relation.reference (參考文獻) 王志瑋，2011，數位口碑探勘法於商品推薦之研究，國立成功大學資訊管理研究所碩士論文。
何偉豪，2010，使用最大熵值法於產品評論之評價等級預測-以Amazon 為例，國立東華大學數為知識管理碩士學位學程。
李日斌，2014，探討臺灣網民對鄰國的情感，國立中山大學資訊管理學系碩士論文。
李啟菁，2010，中文部落格文章之意見分析，國立台北科技大學資訊工程系研究所碩士論文。
李淑惠，2014，運用文字探勘技術於口碑分析之研究，東吳大學資訊管理學系論文。
張育蓉，2012，使用情緒分析於圖書館使用者滿意度評估之研究，國立中興大學圖書資訊學研究所碩士學位論文。
張莊平，2011，中文文法剖析應用於電影評論之意見情感分類，國立臺灣師範大學資訊工程研究所碩士論文。
陳立，2009，中文情感語意自動分類之研究，國立臺灣師範大學資訊工程研究所碩士論文。
楊惠淳，2011，以主客觀分析與相互資訊檢索探討情感分析之準確度-以電影評論為例，國立臺北科技大學資訊與運籌管理研究所碩士論文。
蕭瑞祥、姜青山、曹金豐、簡之文，2012，部落格文章情感分析之研究，私立淡江大學資訊管理學系。
謝邦昌、鄭宇廷、謝邦彥、硬是愛數據應用股份有限公司，2017，玩轉社群:文字大數據實作，五南出版社。
簡智宏，2015，應用文字探勘技術於概念股輿情與股價共同移動之研究-以蘋果供應鏈為例，國立政治大學資訊管理研究所碩士論文。
鐘任明、李維平、吳澤民，2007，運用文字探勘於日內股價漲跌趨勢預測之研究，中華管理評論國際學報。

Benamara, F., Cesarano, C., Picariello, A. & Subrahmanian. (2007). Sentiment analysis:Adjectives and adverbs are better than adjectives alone. In ICWSM Boulder, CO USA.
Blair-Goldensohn, S., Hannan, K., McDonald, R., Neylon, T., Reis, G. & Reynar, J. (2008). Building a sentiment summarizer for local service reviews. In paper presented at the www 2008 workshop on NLP challenges in the information explosion era (NLPIX 2008), Beijing, April, 22.
Bollen, J., Mao, H. & Zeng, X.(2010). Twitter mood predicts the stock market, Journal of computational science. Vol. 2, p.1-8.
Culnan,M., McHugh, P. & Zubillaga, J.(2010).How large U.S. companies can use twitter and other social media to gain business value. MIS Quarterly Executive, 9(4), p.243-259.
Dey, L., Haque, S. M., Khurdiya, A. & Shroff, G. (2011). Acquiring competitive intelligence from social media. In Proceedings of the 2011 joint workshop on multilingual OCR and analytics for noisy unstructured text data Article3.
Gamon, M. (2004). Sentiment classification on customer feedback data: Noisy data, large feature vectors, and the role of linguistic analysis. In Proceedings of the 20th International Conference on Computational Linguistics, p.841.
Gary, K., Jennifer, P. & Margaret, E. R.(2013). How Censorship in China Allows Government Criticism but Silences Collective Expression. American Political Science Review, 107, 2 (May), p.1-18. Copy at http://j.mp/2nxNUhk
Gidofalvi, G.(2001). Using news articles to predict stock price movements. Department of Computer Science. University of California, San Diego.
Governatori, G. & Iannella, R.(2011). A medeling and reasoning framework for social networks policies. Enterprise Information Systems, 5(1), p.145-167.
Hassan, S., Yulan, H. & Harith, A.(2012). Semantic Sentiment Analysis of Twitter. In: Cudré-Mauroux P. et al. (eds) The Semantic Web – ISWC 2012. ISWC 2012. Lecture Notes in Computer Science, Vol. 7649.
Kaplan, A. & Haenlein, M.(2010). User of the world, unite! The challenges and opportunities of social media. Business Horizons, 53, p.59-68.
Ku, L. W. & Chen, H. H.(2007). Mining Opinions from the Web:Beyond Relevance Retrieval. Journal of American Society for Information Science and Technology, 58, p.1838-1850.
Larsson, A. & Moe, H.(2011). Studying political microblogging: Twitter users in the 2010 Swedish election campaign. New Media and Society. Vol. 14, p.727-747.
Lim, M.(2012). Clicks, cabs, and coffee houses: Social media and oppositional movements in Egypt, 2004-2011. Journal of Communication. Vol.62, p.231-248.
Liu, Y., Huang, X., An, A. & Yu, X.(2007). ARSA: A sentiment-aware model for predicting sales performance using blogs. In Proceedings of the 30th annual international ACMSIGIR conference on research and development in information retrieval. p.607-614. New York.
Liu, B.(2009). Sentiment analysis and opinion mining. Synthesis Lectures on Human Language Technologies, Vol.5, No.1, p.1-167.
Manning, C. & Schutze, H.(1999). MITCogNet. Foundations of statistical natural language processing, Vol.59. MIT Press.
Mostafa, M.(2013). More than words: Social networks’text mining for customer brand sentiments. Expert systems with applications, Vol.40, Issue 10, p.4241-4251.
Mukherjee, S.(2012). Sentiment analysis-A literature survey, Indian Institute of Technology, Bombay.
Na, J., Thet, T., & Khoo, C.(2010). Comparing sentiment expression in movie reviews from four online genres. Online Information Review. Vol. 34, p.317-338.
Pang, B., Lee, L. & Viathyanathan, S.(2002). Thumbs up? Sentiment classification using machine learning techniques. In Proceeding of the ACL-02 conference on empirical methods in natural language processing, Vol. 10, p. 79-86, Association for Computational Linguistics.
Park, N., Kee, K. F. & Valenzuela, S. (2009). Being immersed in social networking environment:Facebook groups, uses and gratifications, and social outcomes. Cyber Psychology & Behavior, 12(6), p.729-733.
Popescu, A., & Etzioni, O.(2005). Extracting product features and opinions from reviews. In Proceedings of the conference on human language technology and empirical methods in natural language processing, p.339-346. Association for Computational Linguistics.
Schumaker, R. & Chen, H.(2006). Textual Analysis of Stock Market Prediction Using Financial News Articles. 12th Americas Conference on Information Systems (AMCIS).
Thet, T., Na, J. & Khoo, C.(2008). Aspects-based sentiment analysis of movie reviews on discussion boards. Journal of Information Science. Vol. 36, p. 823-848.
Tsantis, L. & Castellani, J.(2001).Enhancing learning environments through solution-based knowledge discovery tools, Journal of Special Education Technology,Vol.16, Issue 4, p.1-35.
Tumasjan, A., Sprenger, T., Sandner, P. & Welpe, I.(2011). Election forecasts with Twitter: How 140 characters reflect the political landscape. Social Science Computer Review. Vol. 29, p.402-418.
Turney, P. D.(2002). Thumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification of Reviews. Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL), Philadelphia, July, p.417-424.
Wang, S. G., Wei, Y. J., Zhang,W., Li, D.Y. & Li, W.(2007). A hybrid method of feature selection for Chinese text sentiment classification. In Proceedings of the 4th International Conference on Fuzzy Systems and Knowledge Discovery, p.435-439.IEEE Computer Society.
Williams, C. & Gulati, G.(2008). What is a social network worth? Facebook and vote share in the 2008 presidential primaries. In the annual meeting of the American political science association, p.1-17. Boston, MA: APSA.
Yessenov, K. & Misailovic, S.(2009). Sentiment analysis of movie review comments. Methodology, p.1-17.
Yi, J., Nasukawa, T., Bunescu, R. & Niblack, W.(2003). Sentiment analyzer: Extracting sentiment about a given topic using natural language-processing techniques. In proceedings of the 3rd IEEE international conference on data mining (ICDM’ 2003), p.427-434. Los Alamitos, CA.
Yong, Y., Qiang Y., Guirong, X. & Wenyuan D.(2002). Transferring Naïve Bayes classifiers for text classification. In Conference of the American Association for Artificial Intelligence (AAAI).
Zhang,W., Xu, H. & Wan, W.(2012). Weakness Finder: Find product weakness from Chinese reviews by using aspects based sentiment analysis. Expert System with Applications, Vol.39, Issue 11, p.10283-10291.		zh_TW