相關研究指出，網路的文章(含新聞和意見)會對公司或事件的口碑造成一定
程度的影響；故已有許多公司和政府單位會利用日報系統來查看網路上的各種評
論文章，希望能及時回覆和平衡相關的負面評價。就實際訪談結果發現:使用者對
目前日報系統感到最大的問題:目前台灣市面上使用的中文意見探勘系統大都屬於
document-level 的系統，但此類系統除了很難應用多面向口碑分析，導致有些功能無法使用外；在查看網友評論文章的主旨和評價時亦很難滿足使用者的需求。
此計畫將對上述問題作探討：結合發展出的aspect-level 中文意見探勘系統技術於日報系統中，增加多面向口碑分析的正確率和回收率。其結果不但可縮短使用
者閱讀的時間，同時亦可結合視覺化圖表工具增加使用者對結果的易讀性；並且
透過結果與圖表並用，可新增新功能來強化現有日報系統來滿足使用者的需求，
本研究將對這些新功能做說明。

Related studies indicate that articles (include news and opinions) on the internet have significant influence to WOM (word of mouth) of the company or event, as a matter of fact, company and government start using daily report system to follow up with variety of articles. Therefore, they can immediately reply and mitigate some negative reviews. The result of the user trail test is that the users were having issue with analyzing WOM and may receive unwanted search results. Another issue is the search function is lacking more accurate search options.
  The Aspect-Level Chinese Opinion System from the previous project was combined with related search article function to create a new daily report system. The new system can not only help the users digest information more efficiently but also combined data visualization and results of related articles. The new system can also follow up with event/response tracking and analytical event summary.

目錄
第1章 緒論 1
1-1 研究動機與目的 1
1-2 研究架構 6
第2章 文獻探討 7
2-1 意見元素定義	7
2-2 中文意見探勘系統相關研究 8
2-3 本研究室開發的中文意見探勘系統研究 10
第3章 研究方法 12
3-1 不相關文章的判定方法 12
3-1-1 新聞頻道文章判定方法 13
3-1-2 論壇社群網站之討論標題判定方法 18
3-2 演算法 20
3-3 功能強化 23
3-3-1 新聞資料的處裡 23
3-3-2 論壇資料處裡 27
第4章 分析實例 37
4-1 資料來源 38
4-2 日報系統流程與發信單位介面說明 41
4-2-1 關鍵字設定 43
4-2-2 文章下載與排程設定 47
4-2-3 人工檢查 48
4-2-4 發送日報 50
4-2-5 追蹤設定 51
4-3 日報結果 53
4-3-1 主管單位介面 54
4-3-2 日報準確率 57
4-3-3 日報系統實例-MOD事件追蹤 59
第5章 結論 66
參考文獻 67
附錄A 英文論文 70 
圖目錄
圖2-1 系統架構圖	11
圖3-1 搜尋下載出現與新竹縣相關的新聞 範例3-1 14
圖3-2 搜尋下載出現與定義的新竹不相關的新聞 範例3-2 15
圖3-3 THE ALGORITHM 20
圖3-4 社會處的相關業務和議題的新聞 範例 3-6 26
圖3-5 五大電信業者討論文章數及比例2011-11~2013-02 30
圖3-6 五大電信業者討論文章數及比例2013-03~2014-04 30
圖3-7 中華、遠傳、台灣大哥大【價格】文章評價分析2011-11~2013-02 31
圖3-8中華、遠傳、台灣大哥大【價格】文章評價分析2013-03~2014-04 32
圖3-9 中華評價分佈(201406~201502) 34
圖3-10 中華評價分佈(201503~201506) 35
圖3-11 發文者評價面向分析 36
圖4-1 系統架構圖 37
圖4-2 日報系統操作流程圖 42
圖4-3 功能目錄介面 43
圖4-4 篩選關鍵字設定介面-以ISP為例 44
圖4-5 新增關鍵字視窗 45
圖4-6 新增關鍵字-狀態下拉選單 45
圖4-7 9月15日未經人工檢查之新竹市社會處新聞篇數 46
圖4-8 9月15日新竹市社會處日報 47
圖4-9 文章下載與排成設定 48
圖4-10 人工閱覽介面網址列 48
圖4-11 人工檢查介面 49
圖4-12 人工檢查介面-單篇新聞文章 49
圖4-13 人工檢查介面-以新竹市社會處為例 50
圖4-14 日報設定 51
圖4-15 追蹤設定-整體評價分析 52
圖4-16 綜合評價分析正負評價與文章比例 53
圖4-17 綜合評價分析歷史趨勢 53
圖4-18 正負面新聞統計 54
圖4-19 日報新聞列表 55
圖4-20 日報新聞文章原文 56
圖4-21 文章完整句 56
圖4-22 新聞文章數變化 57
圖4-23 新聞完整句準確率變化 58
圖4-24 論壇完整句準確率變化 59
圖4-25 MOD事件討論聲量 60
圖4-26 MOD事件正負面評價趨勢 61
圖4-27 MOD事件評價趨勢 62
圖4-28 中華電信正負面評價趨勢圖 63
圖4-29 中華電信評價趨勢圖 64
表目錄
表2-1 意見元素定義表 8
表3-1 篩選關鍵字與含關鍵字新聞內容對照表 16
表3-2 篩選關鍵字與新聞內容含關鍵字語句對照表 16
表3-3 關鍵字與討論標題對照表 19
表4-1 論壇頻道列表 39
表4-2 新聞頻道列表 40

[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. Hu and 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]	N. Kobayashi, K. Inui, 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, pp. 415-463.
[7]	Z. Li, M. Zhang, S. Ma, B. Zhou, and Y. Sun, "Automatic Extraction for Product Feature Words from Comments on the Web Information Retrieval Technology." vol. 5839, G. Lee, D. Song, C.-Y. Lin, A. Aizawa, K. Kuriyama, M. Yoshioka, et al., Eds., ed: Springer Berlin / Heidelberg, 2009, pp. 112-123.
[8]	M. Chen and T. Yao, "Combining dependency parsing with shallow semantic analysis for Chinese opinion-element relation identification," in Universal Communication Symposium (IUCS), 2010 4th International (pp. 299-305), 2010, pp. 299-305.
[9]	P. Ting-Chun and S. Chia-Chun, "Using Chinese part-of-speech patterns for sentiment phrase identification and opinion extraction in user generated reviews," in Digital Information Management (ICDIM), 2010 Fifth International Conference on (pp. 120-127), 2010, pp. 120-127.
[10]	V. Hatzivassiloglou and K. R. McKeown, "Predicting the semantic orientation of adjectives," 1997, pp. 174-181.
[11]	G. Qiu, B. Liu, J. Bu, and C. Chen, "Expanding domain sentiment lexicon through double propagation," presented at the Proceedings of the 21st international jont conference on Artifical intelligence (pp.1199-1204), Pasadena, California, USA, 2009.
[12]	M. Hu and B. Liu, "Mining and summarizing customer reviews," presented at the Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining (pp. 168-177), Seattle, WA, USA, 2004.
[13]	S.-M. Kim and E. Hovy, "Determining the sentiment of opinions," presented at the Proceedings of the 20th international conference on Computational Linguistics (pp. 1367), Geneva, Switzerland, 2004.
[14]	S. Bin and C. Kuiyu, "Mining Chinese Reviews," in Data Mining Workshops, 2006. ICDM Workshops 2006. Sixth IEEE International Conference on (pp. 585-589), 2006, pp. 585-589.
[15]	Y. Qiang, S. Wen, and L. Yijun, "Sentiment Classification for Movie Reviews in Chinese by Improved Semantic Oriented Approach," in System Sciences, 2006. HICSS '06. Proceedings of the 39th Annual Hawaii International Conference on (pp. 53b-53b), 2006, pp. 53b-53b.
[16]	L. Zhuang, F. Jing, and X.-Y. Zhu, "Movie review mining and summarization," presented at the Proceedings of the 15th ACM international conference on Information and knowledge management, Arlington, Virginia, USA, 2006.
[17]	X. Ding, B. Liu, and P. S. Yu, "A holistic lexicon-based approach to opinion mining," presented at the Proceedings of the 2008 International Conference on Web Search and Data Mining (pp. 231-240), Palo Alto, California, USA, 2008.
[18]	L. W. Ku, I. C. Liu, C. Y. Lee, K. Chen, and H. H. Chen, "Sentence-Level Opinion Analysis by CopeOpi in NTCIR-7," in Proceedings of the 7th NTCIR Workshop Meeting on Evaluation of Information Access Technologies: Information Retrieval, Question Answering, and Cross-Lingual Information Access (pp. 260-267), Tokyo, Japan, 2008, pp. 260-267.
[19]	M. Hu and B. Liu, "Mining and summarizing customer reviews," presented at the Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining (pp. 168-177), Seattle, WA, USA, 2004.
[20]	C. Zhang, D. Zeng, J. Li, F.-Y. Wang, and W. Zuo, "Sentiment analysis of Chinese documents: From sentence to document level," J. Am. Soc. Inf. Sci. Technol., vol. 60, pp. 2474-2487, 2009.
[21]	L.-W. Ku, H.-W. Ho, 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.
[22]	林憲嘉, "針對單一領域中文意見探勘系統之研究與實作," 淡江大學資訊工程學系資訊工程學系碩士在職專班碩士論文, 2015.
[23]	江珮儀, "中文意見探勘系統-關鍵字搜尋優化的研究," 淡江大學資訊工程學系資訊工程學系碩士在職專班碩士論文, 2018.
[24]	林炳志, "電信公司口碑比較之研究," 淡江大學資訊工程學系資訊工程學系碩士在職專班碩士論文, 2014.
[25]	朱庭樂, "4G電信業者口碑分析及研究," 淡江大學資訊工程學系資訊工程學系碩士在職專班碩士論文, 2015.