隨著網際網路的普及化及消費者習慣的改變，現今消費者可以經由網路上各討論區或論壇來閱讀網友們的使用心得及詢問網友們的經驗或其意見，這種即時互動訊息所得到的結果，有非常大的機率左右消費者的決定，倘若能將這些網路上的口碑做追蹤及量化，相信這些訊息會重新定位業者在審核行銷效益的觀念。這項研究是經由使用探勘技術分析網絡論壇輿論，其目的為1.將四個影響客戶汽車購買決策之面向，二手、新車、服務、保養維修等主要考慮因素預先定義且推導並得出結論。2.車商可針對負向評價做長期性的追蹤，使其更加了解消費者的需求，提供改善的進步方向。我們收集並下載從汽車論壇Mobile01網站包含關鍵字“Toyota”的討論，將評論文章匯入至中文意見探勘系統，該系統就可以分析及產出基於四個面向的正面和負面評價成果之表格與圖表。該結果可以使用在無論是作為客戶汽車購買決策的一個參考資料，或提供給車商在製造銷售策略和產品/服務改進的重要資訊。

Along with the popularization of Internet and the change of consumer habits, consumers can now read the articles of product review posted in discussion forum by people in Internet and query their use experiences or opinions. The result from these online and interactive messages is very likely to change the consumer’s decision. If these public praise could be tracked and quantified effectively, it will reset the concept to evaluate the efficiency of marketing activities for industry. This research is to analyze the public opinions in Internet forums by using data mining technology. The purposes are listed below: 1. There are four features to affect consumers to choose their car: new car, used car, customer service and car maintenance. This research will get the final conclusion by giving the accurate definition and deduction for these four features. 2. Car manufacturer could have better understanding of consumer need and the direction of improvement by the long-term trace of the negative criticism. We collected and downloaded the posts that include the keyword ‘Toyota’ from the car forum in Mobile01 (www.mobile01.com) and import these comments into the Chinese data mining system. This system will analyze these data based on the four factors mentioned before and output the positive and negative results to  tables and charts. These results are very important reference for both the consumers to choose their car and the car manufacturers to build their marketing strategy and improve their customer service.

第一章 緒論 1
1-1 研究動機與目的 1
1-2 研究架構 2
第二章 文獻探討	 4
2-1 意見單元定義 4
2-2 意見探勘系統 9
2-3 口碑行銷與網路口碑 20
第三章 系統架構及設定 23
3-1 主題關鍵字設定與下載文章 23
3-2 領域詞庫管理 26
3-3 領域詞庫關聯管理 38
3-4 爬文與主題設定 45
3-5 語意分析結果 54
第四章 口碑分析	62
4-1 ALTIS新車整體口碑分析 62
4-2 YARIS新車整體口碑分析 70
4-3 VIOS新車整體口碑分析 77
第五章 研究結論與未來展望 85
5-1 結論 85
5-2 未來展望 87
參考文獻 88
附錄A 英文論文 90
圖目錄
圖1  OPINION OBSERVER的比較畫面	10
圖2  人工標註系統畫面 11
圖3  WEBFOUNTAIN GUI 經過意見分析後的產品比較圖	12
圖4  WEBFOUNTAIN 可以讓使用者選擇產品、來源以及顯示評論	13
圖5  在手機上根據特徵分類(COMMON圖) 14
圖6  SPECIAL圖 15
圖7  CLOUD圖 15
圖8  CATEGORIES 圖 16
圖9  COPEOPI使用者選擇畫面 17
圖10  各個時間趨勢 17
圖11  包含主題的文章 18
圖12  可選擇有關的電影以及特徵，並且知道正負傾向評論等級	19
圖13  關鍵字設定介面截圖	25
圖14  領域詞庫管理相關功能示意圖	 26
圖15  領域詞彙群組設定介面_TOPIC	 27
圖16  汽車品牌.營業所.車款之關係圖 28
圖17  TOPIC階層設定介面	29
圖18  詞彙原意_以ALTIS為例 30
圖19  領域詞彙群組設定介面_FEATURE 31
圖20  FEATURE設定介面 32
圖21  領域詞彙群組設定介面_ITEM	33
圖22  ITEM設定介面_服務品質 34
圖23  領域詞彙群組設定介面_正面OP 35
圖24  領域詞彙群組設定介面_負面OP 36
圖25  通用正面意見詞(部分) 36
圖26  忽略詞設定介面 37
圖27  TOPIC-FEATURE關聯設定介面	38
圖28  FEATURE-ITEM關聯設定介面	39
圖29  FEATURE-OP關聯設定_正面OP介面 40
圖30  FEATURE-OP關聯設定_負面OP介面 40
圖31  ITEM-OP關聯設定_正面OP介面	 41
圖32  ITEM-OP關聯設定_負面OP介面	 42
圖33  ITEM-OP關聯設定_對應關係極性調整介面 43
圖34  TOPIC階層設定介面	44
圖35  文章主題分析與詞庫維護介面	 46
圖36  FEATURE-ITEM關聯設定介面	48
圖37  TOYOTA_FEATURE熱門趨勢分析 (201404~201409)	 56
圖38  TOPIC整體評價分析	57
圖39  TOYOTA新車回文數比例分析圖(201404~201409)	58
圖40  ALTIS_FEATURE_正面評價比例分析圖 59
圖41  ALTIS_FEATURE_負面評價比例分析圖 60
圖42  臺灣汽車市場銷售報告部分說明(2014年10月) 61
圖43  ALTIS_新車面向評價與趨勢分析(201404~201409) 63
圖44  ALTIS_新車_ITEM其正負評價分析(201404~201409) 64
圖45  沒有ITEM 之文章(舉例) 65
圖46  有ITEM 之文章(舉例) 65
圖47  ALTIS_新車_正面評價比例分析圖 66
圖48  ALTIS_新車_負面評價比例分析圖 67
圖49  ALTIS_新車_功能正、負向評價與分析說明(201404~201409) 68
圖50  ALTIS_新車_車體正、負向評價與分析說明(201404~201409) 69
圖51  ALTIS_新車_價格正、負向評價與分析說明(201404~201409) 69
圖52  YARIS_新車面向評價與趨勢分析(201404~201409) 70
圖53  YARIS_新車_ITEM其正、負評價分析(201404~201409) 71
圖54  YARIS_新車_正面評價比例分析圖 72
圖55  YARIS_新車_負面評價比例分析圖 73
圖56  YARIS_新車_功能正、負向評價與分析說明(201404~201409) 74
圖57  YARIS_新車_車體正、負向評價與分析說明(201404~201409) 75
圖58  YARIS_新車_價格正、負向評價與分析說明(201404~201409) 76
圖59  VIOS_新車面向評價與趨勢分析(201404~201409) 77
圖60  VIOS_新車_ITEM其正負評價分析(201404~201409) 79
圖61  VIOS_新車_正面評價比例分析圖 80
圖62  VIOS_新車_負面評價比例分析圖 81
圖63  VIOS_新車_功能正、負向評價與分析說明(201404~201409) 82
圖64  VIOS_新車_車體正、負向評價與分析說明(201404~201409) 83
圖65  VIOS_新車_價格正、負向評價與分析說明(201404~201409) 84
表目錄
表1  意見元素 5
表2  研究標的資訊表 47
表3  熱門文章回文排行榜1 49
表4  熱門文章回文排行榜2 50
表5  每月評價文章排行榜1 51
表6  每月評價文章排行榜2 52
表7  評估方式 54
表8  ALTIS、VIOS、YARIS之文章數、系統產出完整句數、準確率、回收率、F1值 55

[1]	P. D. Turney, "Thumbs up or thumbs down?: semantic orientation applied to unsupervised classification of reviews,," presented at the Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, Philadelphia, Pennsylvania, , 2002.
[2]	M. H. a. B. Liu, "Mining and summarizing customer reviews,," presented at the Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining, Seattle, WA, USA,, 2004.
[3]	L.-W. Ku and H.-H. Chen, "Mining opinions from the Web: Beyond relevance retrieval,," Journal of the American Society for Information Science and Technology, vol. 58, pp. 1838-1850,, 2007.
[4]	K. I. N. Kobayashi, and Y. Matsumoto,, "Opinion Mining from Web Documents: Extraction and Structurization,," Information and Media Technologies, vol. 2, pp. 326-337, 2007.
[5]	S.-M. Kim and E. Hovy, "Determining the sentiment of opinions,," presented at the Proceedings of the 20th international conference on Computational Linguistics, Geneva, Switzerland,, 2004.
[6]	B. Liu and L. Zhang, "A Survey of Opinion Mining and Sentiment Analysis Mining Text Data,," C. C. Aggarwal and C. Zhai, Eds., ed: Springer US,, 2012.
[7]	M. H. B. Liu, and J. Cheng,, "Opinion observer: analyzing and comparing opinions on the Web,," presented at the Proceedings of the 14th international conference on World Wide Web, Chiba, Japan,, 2005.
[8]	J. Y. a. W. Niblack, "Sentiment mining in WebFountain,," in Data Engineering, 2005. ICDE 2005. Proceedings. 21st International Conference, 2005.
[9]	O. E. J. Huang, L. Zettlemoyer, K. Clark, and C. Lee,, "RevMiner: an extractive interface for navigating reviews on a smartphone,," presented at the Proceedings of the 25th annual ACM symposium on User interface software and technology, Cambridge, Massachusetts, USA, , 2012.
[10]	H.-W. H. L.-W. Ku, and H.-H. Chen,, "Opinion mining and relationship discovery using CopeOpi opinion analysis system,," Journal of the American Society for Information Science and Technology, vol. 60, pp. 1486-1503,, 2009.
[11]	H.-D. Ciou, "Applying Opinion Mining to Chinese Movie Reviews,," 2011.
[12]	H. W.-H. L. Chien-Liang, L. Chia-Hoang, L. Gen-Chi, and E. Jou, , "Movie Rating and Review Summarization in Mobile Environment,," Systems, Man, and Cybernetics, Part C: Applications and Reviews, IEEE Transactions on, vol. 42, pp. 397-407,, 2012.
[13]	R. D. Blackwell, et al., "Consumer behavior, 10.," Aufl.,Mason., 2006.
[14]	R. A. Westbrook, "Product/consumption-based affective responses and postpurchase processes," Journal of marketing research, pp.258-270,, 1987.
[15]	L. J. Harrison-Walker, "The measurement of word-of-mouth communication and an investigation of service quality and customer commitment as potential antecedents,," Journal of Service Research , vol. 4,pp. 60-75,, 2001.
[16]	F. A. Buttle "Word of mouth: understanding and managing referral marketing.," 1998.
[17]	Y. X. T. Wu, "Electronic word of mouth in online social networks,," n Communication Systems, Networks and Applications (ICCSNA), 2010 Second International Conference 2010.
[18]	D. L. H. TH. P. Novak., "Marketing in hypermedia computermediated environments: conceptual fundamentals,," Journal of Marketing 60,, 2006.
[19]	K. Zeng, "Online Buying Impulsiveness and Word-of-Mouth Online in the E-Marketing Age: A Theoretical Model Approach,," in Management of e-Commerce and e-Government (ICMeCG), 2010 Fourth International Conference on, 2010,, 2010.
[20]	I. Okada, "Relationship between Online Word-of-Mouth Communication and Consumer Behavior,," in System Science (HICSS), 2012 45th Hawaii International Conference on, 2012,, 2012