臺灣博碩士論文加值系統

當一個新聞事件發生時，相關訊息通常會被新聞媒體所報導，而民眾亦能透過網路上各種管道發表己見。近年來，社群媒體已成為記者與民眾散播訊息的重要平台，也是研究新聞發展的重要管道。但隨著時間累積的龐大訊息量，使用人工的方式來收集資料，以了解事件整體脈絡的方式往往事倍功半。本研究利用Twitter做為資料來源，透過各種視覺化的圖表及統計資訊，協助新聞研究者透過漸進的方式操作系統各階段的功能，逐步篩選出新聞事件的關鍵推文。系統可客製化參數的設計讓使用者能依觀察到的現象來調整系統推薦的推文，進而達到瞭解發展歷程的目標。我們邀請4位受試者，透過系統操作教學及引導式任務讓受試者學習如何使用系統，最後讓受試者自由探索，並透過問卷與訪談的方式來探討系統的優缺點。問卷的評分使用5分量表，實驗結果在有用性向度的平均分數為4.1，表示本系統能有效地幫助使用者分析事件的發展歷程；而易用性向度的平均分數為4.3，顯示受試者對本系統的易用性表示認同。本系統的主要目的，是希望能協助使用者找尋新聞事件中的關鍵推文，並瞭解其發展歷程，由實驗結果與受試者回饋顯示，本研究的視覺化分析系統具有幫助理解事件脈絡的能力，證實了本系統的發展價值。

When a new event happens, related messages can not only be released by the press but also through various network channels by the general public. In recent years, social media have become a popular and important platform for news reporters and the general public to propagate news messages. However, due to the massive amount of messages on the social media platforms, it is very time consuming to manually collect these data in order to grasp the development of a news event over time. In this research, we aim to develop a visualization system that can help researchers find key tweets on twitters for a news event in an incremental manner. Our system allows a user to customize design parameters for finding key tweets from various aspects in order to understand how a news event evolve over time on social media. We have invited four participants to test use our system through a tutorial, guided tasks, and free exploration. A questionnaire survey and interview were conducted after the experiments. The evaluation results show that the average score for the usability dimension is 4.1 out of 5, showing that the system can effectively assist the users in analyzing the development of a news event. The average score for the ease-of-use dimension is 4.3, meaning that most users agree that our system is easy to use. The results reveal that our research goals of helping users find key tweets and understand news development have been achieved and the development of such a visualization system is valuable for news analysis on social media.

第1章 導論 1
1.1 研究動機 1
1.2 研究目標 2
1.3 研究問題 2
1.4 論文貢獻 3
1.5 論文架構 4
第2章 相關研究 5
2.1 資訊視覺化 5
2.2 Twitter的分析工具 6
第3章 系統架構與設計 9
3.1 系統架構 9
3.2 資料來源 10
3.2.1 Twitter 10
3.2.2 Klout 11
3.2.3 Website 12
3.3 系統介面設計 13
3.3.1 資料選擇區 14
3.3.2 個人篩選區 19
3.3.3 關鍵事件分析區 22
第4章 系統實作 27
4.1 資料收集 27
4.2 文本處理 28
4.3 推文分群 29
4.4 視覺化呈現 32
第5章 實驗設計與結果分析 35
5.1 實驗目標 35
5.2 實驗對象 35
5.3 實驗流程 36
5.3.1 引導式任務 36
5.3.2 自由操作 37
5.3.3 問卷與訪談 37
5.4 實驗結果分析與討論 41
5.4.1 有用性評估 41
5.4.2 易用性評估 43
第6章 結論與未來展望 46
6.1 研究結論 46
6.2 未來發展與改進 46
參考文獻 48
附錄 51
附錄1 引導式任務熟悉介面 51

[1] 3C (商品代稱) - 維基百科，自由的百科全書. Available: https://zh.wikipedia.org/wiki/3C_(%E5%95%86%E5%93%81%E4%BB%A3%E7%A8%B1)
[2] D. Laney, "3D data management: Controlling data volume, velocity and variety," META Group Research Note, vol. 6, p. 70, 2001.
[3] S. LOHR. The Age of Big Data. Available: http://www.nytimes.com/2012/02/12/sunday-review/big-datas-impact-in-the-world.html
[4] U. Alliance. What is Big Data? Available: http://www.villanovau.com/resources/bi/what-is-big-data
[5] 鄭宇君 and 施旭峰, "探索 2012 台灣總統大選社交媒體之新聞來源引用," 中華傳播學刊, pp. 109-135, 2016.
[6] 鄭宇君 and 陳百齡, "探索 2012 年台灣總統大選之社交媒體浮現社群: 鉅量資料分析取徑," 新聞學研究, 2014.
[7] E. Segel and J. Heer, "Narrative visualization: Telling stories with data," Visualization and Computer Graphics, IEEE Transactions on, vol. 16, pp. 1139-1148, 2010.
[8] A. Satyanarayan and J. Heer, "Authoring narrative visualizations with ellipsis," in Computer Graphics Forum, 2014, pp. 361-370.
[9] S. Liu, W. Cui, Y. Wu, and M. Liu, "A survey on information visualization: recent advances and challenges," The Visual Computer, vol. 30, pp. 1373-1393, 2014.
[10] T. Kraft, D. X. Wang, J. Delawder, W. Dou, L. Yu, and W. Ribarsky, "Less after-the-fact: Investigative visual analysis of events from streaming twitter," in 2013 IEEE Symposium on Large-Scale Data Analysis and Visualization (LDAV), 2013, pp. 95-103.
[11] H. Bosch, D. Thom, F. Heimerl, E. Puttmann, S. Koch, R. Kruger, et al., "Scatterblogs2: Real-time monitoring of microblog messages through user-guided filtering," Visualization and Computer Graphics, IEEE Transactions on, vol. 19, pp. 2022-2031, 2013.
[12] E. Borra and B. Rieder, "Programmed method: developing a toolset for capturing and analyzing tweets," Aslib Journal of Information Management, vol. 66, pp. 262-278, 2014.
[13] C.-Y. Lin, T.-Y. Li, and P. Chen, "An Information Visualization System to Assist News Topics Exploration with Social Media," in Proceedings of the 7th 2016 International Conference on Social Media & Society, 2016, p. 23.
[14] X. Meng, F. Wei, X. Liu, M. Zhou, S. Li, and H. Wang, "Entity-centric topic-oriented opinion summarization in twitter," in Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining, 2012, pp. 379-387.
[15] S. Phuvipadawat and T. Murata, "Breaking news detection and tracking in Twitter," in Web Intelligence and Intelligent Agent Technology (WI-IAT), 2010 IEEE/WIC/ACM International Conference on, 2010, pp. 120-123.
[16] W. X. Zhao, J. Jiang, J. Weng, J. He, E.-P. Lim, H. Yan, et al., "Comparing twitter and traditional media using topic models," in Advances in Information Retrieval, ed: Springer, 2011, pp. 338-349.
[17] A. Rao, N. Spasojevic, Z. Li, and T. Dsouza, "Klout score: Measuring influence across multiple social networks," in Big Data (Big Data), 2015 IEEE International Conference on, 2015, pp. 2282-2289.
[18] Twitter Streaming APIs. Available: https://dev.twitter.com/streaming/overview
[19] Twitter Search APIs. Available: https://dev.twitter.com/rest/reference/get/search/tweets
[20] Klout.com. Available: https://klout.com
[21] List of HTTP status codes - Wikipedia. Available: https://en.wikipedia.org/wiki/List_of_HTTP_status_codes
[22] G. Salton and C. Buckley, "Term-weighting approaches in automatic text retrieval," Information processing & management, vol. 24, pp. 513-523, 1988.
[23] tf–idf - Wikipedia, the free encyclopedia. Available: https://en.wikipedia.org/wiki/Tf%E2%80%93idf
[24] 中文斷詞系統. Available: http://ckipsvr.iis.sinica.edu.tw/
[25] GitHub - fxsjy/jieba: 结巴中文分词. Available: https://github.com/fxsjy/jieba
[26] The Stanford Natural Language Processing Group. Available: http://nlp.stanford.edu/software/CRF-NER.shtml
[27] M. Bostock, V. Ogievetsky, and J. Heer, "D³ data-driven documents," Visualization and Computer Graphics, IEEE Transactions on, vol. 17, pp. 2301-2309, 2011.
[28] jasondavies/d3-cloud: Create word clouds in JavaScript. Available: https://github.com/jasondavies/d3-cloud
[29] sigma.js | a lightweight JavaScript graph drawing library. Available: http://sigmajs.org/
[30] M. Bastian, S. Heymann, and M. Jacomy, "Gephi: an open source software for exploring and manipulating networks," ICWSM, vol. 8, pp. 361-362, 2009.
[31] V. D. Blondel, J.-L. Guillaume, R. Lambiotte, and E. Lefebvre, "Fast unfolding of communities in large networks," Journal of statistical mechanics: theory and experiment, vol. 2008, p. P10008, 2008.
[32] T. M. Fruchterman and E. M. Reingold, "Graph drawing by force‐directed placement," Software: Practice and experience, vol. 21, pp. 1129-1164, 1991.
[33] Interactive JavaScript charts for your webpage | Highcharts. Available: http://www.highcharts.com/
[34] vis.js - A dynamic, browser based visualization library. Available: http://visjs.org/
[35] A. M. Lund, "Measuring Usability with the USE Questionnaire12."," Usability interface, vol. 8, pp. 3-6, 2001.
[36] F. D. Davis, "Perceived usefulness, perceived ease of use, and user acceptance of information technology," MIS quarterly, pp. 319-340, 1989.