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

Publications-Theses

Article View/Open

Publication Export

Google ScholarTM

NCCU Library

Citation Infomation

Related Publications in TAIR

題名 社群感測器：社群媒體分析工具之設計
Social Sensor: a Tool for Social Media Analysis
作者 吳君孝
Wu, Chun Hsiao
貢獻者 李蔡彥
Li, Tsai Yen
吳君孝
Wu, Chun Hsiao
關鍵詞 社群感測器
社群媒體
資料科學
鉅量資料分析
大數據
資料分析
資料探勘
自動化分析
系統設計
Social Sensor
Social Media
Data Science
Big Data Analysis
Big Data
Data Analysis
Data Mining
Automated Analysis
System Design
日期 2013
上傳時間 29-Jul-2014 16:11:51 (UTC+8)
摘要 社群媒體網絡的興起，架構起了龐大且複雜的新形態網路結構，而這些蓬勃興起的社群媒體，及其資料開放政策，帶動了全球社群媒體的資料分析狂潮。本研究剖析了國立政治大學水火計畫團隊的研究方法，將其社群媒體分析流程依序分為以下幾個步驟：事件發生、關鍵字收集、資料儲存與管理、等待收割、資料預處理、資料分析、資料視覺化、結果觀察與闡釋等八項步驟。並以「2012年台灣總統大選」分析個案作為實例說明，進一步將該個案分析流程歸納整理後，發現其普遍存在的問題，包含了，資料分析速度趕不上資料收集速度、分析步驟獨立且破碎、手動化分析居多且多使用人工傳遞做為資料交換模式、分析方法零散、個案多且缺乏管理、專家經驗難保留且不易重現、重啟花費成本高且等待結果時間長等問題。
因此，本研究以嶄新的概念提出了一套社群媒體資料分析工具，名為社群感測器（Social Sensor），設計上這是一種將實體感測器概念引入到社群媒體世界的一種創新思維，以可管理性、可模組化、可重用性的三大特色建構本系統。使用上，以觀測個案為中心，分析人員可選擇社群媒體類型，如Twitter，也可以自由的選擇分析資料集，與挑選合適的感測器來進行分析，而透過參數預設樣板可快速套用與保留專家的個案分析經驗，亦可針對觀測個案來進行管理。在本研究中亦將分析方法模組化為語系感測器與文本感測器，其中語系感測器的分析方法為本研究所提出。
實驗評估結果顯示，過去沒有現成的語系感測器工具，故模組化後相當好用，文本感測器則是強於時間序列分析以及可支援繁體中文。本系統的有用性評價也相當正面。可模組化、可重用性、可管理性評估結果亦為正面。另外在有助於縮短資料分析時程上被認為是很重要的貢獻，解決了過去社群媒體鉅量資料分析所遇上的難題，且確實可透過本系統獲得分析價值，證實了以感測器概念所設計之系統確實有用。
The rise of social media networks established a new style of network structure, and the policy of opening data led the data analysis of global social media frenzy. This research analyzed the process of National Chengchi University`s team in analyzing social media, which is divided into the following steps: event occur, keyword collection, data storage and management, waiting for harvest, data preprocessing, data analysis, data visualization, observation and interpretation. And we use the case study of "2012 Taiwan presidential election" to illustrate the problems in a typical analysis process such as unmatched speed of data analysis with the speed of data collecting, independent and fragmented analysis steps, labor-intensive manual analysis, manual file exchanges, lack of data and case management tools, difficulty to maintain domain expertise, high restart costs and long waiting time, etc.
Therefore, in this research, we propose a new concept for social media analysis called “Social Sensor,” which is an innovative design attempting to transform the concept of a physical sensor in a real world into the world of social media with three design features: manageability, modularity, reusability. The system is a case-centered design that allows analysts to select the type of social media (such as Twitter), the target data sets, and appropriate social sensors for analysis. By adopting parameter templates, one can quickly apply the experience of other experts in the beginning of a new case or even create their own templates. We have also modularized the analysis tools into two social sensors: Language Sensor and Text Sensor. Experimental results show that the Language Sensor is quite easy to use and the Text Sensor’s strength is on the functions of time se-ries analysis and the support for Traditional Chinese. The evaluation result of the system on usefulness, modularity, reusability, and manageability are all very positive. The results also show that this tool can greatly reduce the time needed to perform data analysis, solve the problems encountered in traditional analysis process, and obtain useful results. The experimental results reveal that the concept of social sensor and the proposed system design are shown to be use-ful.
參考文獻 [1] Kusnetzky, Dan. What is "Big Data?". ZDNet. http://www.zdnet.com/blog/virtualization/what-is-big-data/1708
[2] Big Data Now: 2013 Edition Current Perspectives from O`Reilly Media http://www.oreilly.com/data/free/files/bigdatanow2013.pdf
[3] 鄭宇君 and 陳百齡， “探索2012台灣總統大選之社交媒體浮現社群：鉅量資料分析取徑”， 2013中華傳播學會年會論文
[4] Kaplan, A. M., & Haenlein, M. （2010）. Users of the world, unite! The Chal-lenges and opportunities of social media.
[5] OECD.（2007）.Participative web and user-created content: Web 2.0, wikis, and social networking. Paris: Organisation for Economic Co-operation and Develop-ment.
[6] Short, J., Williams, E., & Christie, B. （1976）. The social psychology of tele-communications. Hoboken, NJ: John Wiley & Sons, Ltd.
[7] Howard Rheingold （1993）. The Virtual Community: Homesteading on the Electronic Frontier. London: MIT Press.
[8] Murthy, Dhiraj （2012）. Towards a Sociological Understanding of Social Media: Theorizing Twitter. Sociology, 46（6）: 1059-1073.
[9] Mark Stelzner（2009）. Social Media vs. Social Networking: What`s the difference? http://www.examiner.com/article/social-media-vs-social-networking-what-s-the-difference
[10] Scott, John. （1991）. Social network analysis: A handbook. London: Sage.
[11] Haythornthwaite, C. （1996）. Social network analysis: an approach and technique for the study of information exchange. Library and Information Science Research, 18（4）, 323-342.
[12] Elaine J. Yuan, Miao Feng, & James A. Danowski（2013）, ‘‘Privacy’’ in Semantic Networks on Chinese Social Media: The Case of Sina Weibo, Journal of Communication
[13] Kwak, Haewoon, Lee, Changhyun & Moon, Sue （2010）. What is twitter, a social network or a news media? Paper presented at the International World Wide Web Conference Committee, North Carolina, USA
[14] Bruns, Axel.; Burgess, Jean. （in press）. Researching News Discussion on Twitter. Journalism Studies.
[15] Wikipedia, the free encyclopedia. Social Network Analysis http://en.wikipedia.org/wiki/Social_network_analysis
[16] 資策會，創研所，"社群媒體分析服務平台" http://www.ideas.iii.org.tw/application.html
[17] Jean Burgess and Axel Bruns.（2012）. （Not） the Twitter Election: The Dy-namics of the #ausvotes Conversation in Relation to the Australian Media Ecolo-gy. Journalism Practice 20 Mar. 2012.
[18] Tamara A. Small （2011）: What the HASHTAG?, A content analysis of Canadian politics on Twitter. Information, Communication & Society, 14:6, 872-895.
[19] Himelboim, I. （2014）. Political Television Hosts on Twitter: Examining Patterns of Interconnectivity and Self Exposure in Twitter Political Talk Networks. Journal of Broadcasting & Electronic Media, 58 （1）, pp.76-96.
[20] Vieweg, S., A. L. Hughes, Starbird, K. and Palen, L. （2010）. Microblogging during two natural hazards events: what twitter may contribute to situational awareness. In Proc. CHI 2010, ACM Press, 1079-1088.
[21] 施旭峰，"災難事件下新媒體資訊傳播方式分析與自動化分類設計─ 以八八風災為例"，國立政治大學資訊科學系，中華民國一百零二年九月
[22] Venu Vasudevan, Jehan Wickramasuriya, Siqi Zhao, Lin Zhong. Is Twitter a Good Enough Social Sensor for Sports TV? Pervasive Collaboration and Social Net-working 2013 IEEE
[23] Takeshi Sakaki, Makoto Okazaki, Yutaka Matsuo. Earthquake Shakes Twitter Us-ers: Real-time Event Detection by Social Sensors. WWW2010, April 26-30, 2010, Raleigh, North Carolina.
[24] Takeshi Sakaki, Yutaka Matsuo, Tadashi Yanagihara, Naiwala P. Chandrasiri, Ka-zunari Nawa. Real-time Event Extraction for Driving Information. Proceedings of the 2012 IEEE International Conference on Cyber Technology in Automation, Control and Intelligent Systems May 27-31, 2012, Bangkok, Thailand
[25] 鄭宇君 and 陳百齡，"超越在地脈絡的全球社交媒體：以 2012 年台灣總統大選的中文Twitter 討論社群為例"，2012 中國網絡傳播學年會澳門國際會議
[26] 使用D3.js的知识组织系统 Ｗｅｂ动态交互可视化功能实现[J]，现代图书情报技术，2013（7/8）：127-131
[27] C.-H. Tsai. （2000）. MMSEG: A Word Identification System for Mandarin Chinese Text Based on Two Variants of the Maximum Matching Algorithm. Available: http://technology.chtsai.org/mmseg/
[28] Chih-Hao Tsai. MMSEG: A Word Identification System for Mandarin Chinese Text Based on Two Variants of the Maximum Matching Algorithm. http://technology.chtsai.org/mmseg/
[29] 國語辭典簡編本編輯小組. （1997）. 國語辭典簡編本編輯資料字詞頻統計報告. Available:http://www.edu.tw/files/site_content/M0001/pin/f11.html
[30] 王淑美, "傳播科技與生活韻律―關於研究方法的探討" ,傳播研究與實踐．第4 卷 第1 期．頁23-43．2014 年1 月
[31] Carney, T. F. (1990). Collaborative inquiry methodology. Windsor, Ontario, Can-ada:University of Windsor, Division for Instructional Development.
[32] 張芬芬, "質性資料分析的五步驟：在抽象階梯上爬升", 初等教育學刊 第三十五期 2010年4月 頁87-120
描述 碩士
國立政治大學
資訊科學學系
101971017
102
資料來源 http://thesis.lib.nccu.edu.tw/record/#G0101971017
資料類型 thesis
dc.contributor.advisor 李蔡彥zh_TW
dc.contributor.advisor Li, Tsai Yenen_US
dc.contributor.author (Authors) 吳君孝zh_TW
dc.contributor.author (Authors) Wu, Chun Hsiaoen_US
dc.creator (作者) 吳君孝zh_TW
dc.creator (作者) Wu, Chun Hsiaoen_US
dc.date (日期) 2013en_US
dc.date.accessioned 29-Jul-2014 16:11:51 (UTC+8)-
dc.date.available 29-Jul-2014 16:11:51 (UTC+8)-
dc.date.issued (上傳時間) 29-Jul-2014 16:11:51 (UTC+8)-
dc.identifier (Other Identifiers) G0101971017en_US
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/67902-
dc.description (描述) 碩士zh_TW
dc.description (描述) 國立政治大學zh_TW
dc.description (描述) 資訊科學學系zh_TW
dc.description (描述) 101971017zh_TW
dc.description (描述) 102zh_TW
dc.description.abstract (摘要) 社群媒體網絡的興起，架構起了龐大且複雜的新形態網路結構，而這些蓬勃興起的社群媒體，及其資料開放政策，帶動了全球社群媒體的資料分析狂潮。本研究剖析了國立政治大學水火計畫團隊的研究方法，將其社群媒體分析流程依序分為以下幾個步驟：事件發生、關鍵字收集、資料儲存與管理、等待收割、資料預處理、資料分析、資料視覺化、結果觀察與闡釋等八項步驟。並以「2012年台灣總統大選」分析個案作為實例說明，進一步將該個案分析流程歸納整理後，發現其普遍存在的問題，包含了，資料分析速度趕不上資料收集速度、分析步驟獨立且破碎、手動化分析居多且多使用人工傳遞做為資料交換模式、分析方法零散、個案多且缺乏管理、專家經驗難保留且不易重現、重啟花費成本高且等待結果時間長等問題。
因此，本研究以嶄新的概念提出了一套社群媒體資料分析工具，名為社群感測器（Social Sensor），設計上這是一種將實體感測器概念引入到社群媒體世界的一種創新思維，以可管理性、可模組化、可重用性的三大特色建構本系統。使用上，以觀測個案為中心，分析人員可選擇社群媒體類型，如Twitter，也可以自由的選擇分析資料集，與挑選合適的感測器來進行分析，而透過參數預設樣板可快速套用與保留專家的個案分析經驗，亦可針對觀測個案來進行管理。在本研究中亦將分析方法模組化為語系感測器與文本感測器，其中語系感測器的分析方法為本研究所提出。
實驗評估結果顯示，過去沒有現成的語系感測器工具，故模組化後相當好用，文本感測器則是強於時間序列分析以及可支援繁體中文。本系統的有用性評價也相當正面。可模組化、可重用性、可管理性評估結果亦為正面。另外在有助於縮短資料分析時程上被認為是很重要的貢獻，解決了過去社群媒體鉅量資料分析所遇上的難題，且確實可透過本系統獲得分析價值，證實了以感測器概念所設計之系統確實有用。		zh_TW
dc.description.abstract (摘要) The rise of social media networks established a new style of network structure, and the policy of opening data led the data analysis of global social media frenzy. This research analyzed the process of National Chengchi University`s team in analyzing social media, which is divided into the following steps: event occur, keyword collection, data storage and management, waiting for harvest, data preprocessing, data analysis, data visualization, observation and interpretation. And we use the case study of "2012 Taiwan presidential election" to illustrate the problems in a typical analysis process such as unmatched speed of data analysis with the speed of data collecting, independent and fragmented analysis steps, labor-intensive manual analysis, manual file exchanges, lack of data and case management tools, difficulty to maintain domain expertise, high restart costs and long waiting time, etc.
Therefore, in this research, we propose a new concept for social media analysis called “Social Sensor,” which is an innovative design attempting to transform the concept of a physical sensor in a real world into the world of social media with three design features: manageability, modularity, reusability. The system is a case-centered design that allows analysts to select the type of social media (such as Twitter), the target data sets, and appropriate social sensors for analysis. By adopting parameter templates, one can quickly apply the experience of other experts in the beginning of a new case or even create their own templates. We have also modularized the analysis tools into two social sensors: Language Sensor and Text Sensor. Experimental results show that the Language Sensor is quite easy to use and the Text Sensor’s strength is on the functions of time se-ries analysis and the support for Traditional Chinese. The evaluation result of the system on usefulness, modularity, reusability, and manageability are all very positive. The results also show that this tool can greatly reduce the time needed to perform data analysis, solve the problems encountered in traditional analysis process, and obtain useful results. The experimental results reveal that the concept of social sensor and the proposed system design are shown to be use-ful.		en_US
dc.description.tableofcontents 第一章 導論 1
1.1. 研究動機與目的 1
1.2. 問題描述與設計目標 5
1.3. 預期貢獻 7
第二章 相關研究 8
2.1. 社群媒體（Social Media）概述 8
2.2. 社群網絡（Social Network）分析技術 9
2.3. 社群網絡（Social Network）分析應用 10
2.4. 過去的社群感測器（Social Sensor） 11
第三章 實例問題定義 13
3.1. NCCU-QUT國際合作團隊（水火計畫團隊） 13
3.2. 總統大選個案分析主題 14
3.3. 總統大選分析個案流程 15
第四章 系統概念與設計 23
4.1. 系統概念 23
4.2. 系統設計架構 25
4.3. 社群感測器平台 26
4.4. 觀測個案管理與觀測個案 27
4.5. 資料來源 28
4.6. 資料集池與資料集 28
4.7. 感測器池與感測器 28
4.8. 參數預設樣板 30
第五章 系統與感測器實作 31
5.1. 系統技術架構 31
5.2. 觀測個案介面設計 32
5.3. 資料集 35
5.4. 語系感測器 36
5.5. 文本感測器 41
5.6. 參數預設樣板 47
第六章 實驗設計與結果評估 50
6.1 實驗設計與方法 50
6.2 實驗程序 51
6.3 日誌紀錄表設計 53
6.4 實驗評估方法與結果 58
6.5 小結 78
第七章 結論與未來研究 80
7.1 結論 80
7.2 未來研究 80
參考文獻 82
附錄一. 系統易用性分析編碼表 85
附錄二. 系統有用性分析編碼表 97		zh_TW
dc.format.extent 2759249 bytes-
dc.format.mimetype application/pdf-
dc.language.iso en_US-
dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0101971017en_US
dc.subject (關鍵詞) 社群感測器zh_TW
dc.subject (關鍵詞) 社群媒體zh_TW
dc.subject (關鍵詞) 資料科學zh_TW
dc.subject (關鍵詞) 鉅量資料分析zh_TW
dc.subject (關鍵詞) 大數據zh_TW
dc.subject (關鍵詞) 資料分析zh_TW
dc.subject (關鍵詞) 資料探勘zh_TW
dc.subject (關鍵詞) 自動化分析zh_TW
dc.subject (關鍵詞) 系統設計zh_TW
dc.subject (關鍵詞) Social Sensoren_US
dc.subject (關鍵詞) Social Mediaen_US
dc.subject (關鍵詞) Data Scienceen_US
dc.subject (關鍵詞) Big Data Analysisen_US
dc.subject (關鍵詞) Big Dataen_US
dc.subject (關鍵詞) Data Analysisen_US
dc.subject (關鍵詞) Data Miningen_US
dc.subject (關鍵詞) Automated Analysisen_US
dc.subject (關鍵詞) System Designen_US
dc.title (題名) 社群感測器：社群媒體分析工具之設計zh_TW
dc.title (題名) Social Sensor: a Tool for Social Media Analysisen_US
dc.type (資料類型) thesisen
dc.relation.reference (參考文獻) [1] Kusnetzky, Dan. What is "Big Data?". ZDNet. http://www.zdnet.com/blog/virtualization/what-is-big-data/1708
[2] Big Data Now: 2013 Edition Current Perspectives from O`Reilly Media http://www.oreilly.com/data/free/files/bigdatanow2013.pdf
[3] 鄭宇君 and 陳百齡， “探索2012台灣總統大選之社交媒體浮現社群：鉅量資料分析取徑”， 2013中華傳播學會年會論文
[4] Kaplan, A. M., & Haenlein, M. （2010）. Users of the world, unite! The Chal-lenges and opportunities of social media.
[5] OECD.（2007）.Participative web and user-created content: Web 2.0, wikis, and social networking. Paris: Organisation for Economic Co-operation and Develop-ment.
[6] Short, J., Williams, E., & Christie, B. （1976）. The social psychology of tele-communications. Hoboken, NJ: John Wiley & Sons, Ltd.
[7] Howard Rheingold （1993）. The Virtual Community: Homesteading on the Electronic Frontier. London: MIT Press.
[8] Murthy, Dhiraj （2012）. Towards a Sociological Understanding of Social Media: Theorizing Twitter. Sociology, 46（6）: 1059-1073.
[9] Mark Stelzner（2009）. Social Media vs. Social Networking: What`s the difference? http://www.examiner.com/article/social-media-vs-social-networking-what-s-the-difference
[10] Scott, John. （1991）. Social network analysis: A handbook. London: Sage.
[11] Haythornthwaite, C. （1996）. Social network analysis: an approach and technique for the study of information exchange. Library and Information Science Research, 18（4）, 323-342.
[12] Elaine J. Yuan, Miao Feng, & James A. Danowski（2013）, ‘‘Privacy’’ in Semantic Networks on Chinese Social Media: The Case of Sina Weibo, Journal of Communication
[13] Kwak, Haewoon, Lee, Changhyun & Moon, Sue （2010）. What is twitter, a social network or a news media? Paper presented at the International World Wide Web Conference Committee, North Carolina, USA
[14] Bruns, Axel.; Burgess, Jean. （in press）. Researching News Discussion on Twitter. Journalism Studies.
[15] Wikipedia, the free encyclopedia. Social Network Analysis http://en.wikipedia.org/wiki/Social_network_analysis
[16] 資策會，創研所，"社群媒體分析服務平台" http://www.ideas.iii.org.tw/application.html
[17] Jean Burgess and Axel Bruns.（2012）. （Not） the Twitter Election: The Dy-namics of the #ausvotes Conversation in Relation to the Australian Media Ecolo-gy. Journalism Practice 20 Mar. 2012.
[18] Tamara A. Small （2011）: What the HASHTAG?, A content analysis of Canadian politics on Twitter. Information, Communication & Society, 14:6, 872-895.
[19] Himelboim, I. （2014）. Political Television Hosts on Twitter: Examining Patterns of Interconnectivity and Self Exposure in Twitter Political Talk Networks. Journal of Broadcasting & Electronic Media, 58 （1）, pp.76-96.
[20] Vieweg, S., A. L. Hughes, Starbird, K. and Palen, L. （2010）. Microblogging during two natural hazards events: what twitter may contribute to situational awareness. In Proc. CHI 2010, ACM Press, 1079-1088.
[21] 施旭峰，"災難事件下新媒體資訊傳播方式分析與自動化分類設計─ 以八八風災為例"，國立政治大學資訊科學系，中華民國一百零二年九月
[22] Venu Vasudevan, Jehan Wickramasuriya, Siqi Zhao, Lin Zhong. Is Twitter a Good Enough Social Sensor for Sports TV? Pervasive Collaboration and Social Net-working 2013 IEEE
[23] Takeshi Sakaki, Makoto Okazaki, Yutaka Matsuo. Earthquake Shakes Twitter Us-ers: Real-time Event Detection by Social Sensors. WWW2010, April 26-30, 2010, Raleigh, North Carolina.
[24] Takeshi Sakaki, Yutaka Matsuo, Tadashi Yanagihara, Naiwala P. Chandrasiri, Ka-zunari Nawa. Real-time Event Extraction for Driving Information. Proceedings of the 2012 IEEE International Conference on Cyber Technology in Automation, Control and Intelligent Systems May 27-31, 2012, Bangkok, Thailand
[25] 鄭宇君 and 陳百齡，"超越在地脈絡的全球社交媒體：以 2012 年台灣總統大選的中文Twitter 討論社群為例"，2012 中國網絡傳播學年會澳門國際會議
[26] 使用D3.js的知识组织系统 Ｗｅｂ动态交互可视化功能实现[J]，现代图书情报技术，2013（7/8）：127-131
[27] C.-H. Tsai. （2000）. MMSEG: A Word Identification System for Mandarin Chinese Text Based on Two Variants of the Maximum Matching Algorithm. Available: http://technology.chtsai.org/mmseg/
[28] Chih-Hao Tsai. MMSEG: A Word Identification System for Mandarin Chinese Text Based on Two Variants of the Maximum Matching Algorithm. http://technology.chtsai.org/mmseg/
[29] 國語辭典簡編本編輯小組. （1997）. 國語辭典簡編本編輯資料字詞頻統計報告. Available:http://www.edu.tw/files/site_content/M0001/pin/f11.html
[30] 王淑美, "傳播科技與生活韻律―關於研究方法的探討" ,傳播研究與實踐．第4 卷 第1 期．頁23-43．2014 年1 月
[31] Carney, T. F. (1990). Collaborative inquiry methodology. Windsor, Ontario, Can-ada:University of Windsor, Division for Instructional Development.
[32] 張芬芬, "質性資料分析的五步驟：在抽象階梯上爬升", 初等教育學刊 第三十五期 2010年4月 頁87-120		zh_TW