政大機構典藏-National Chengchi University Institutional Repository(NCCUR):Item 140.119/134086

政大機構典藏-National Chengchi University Institutional Repository(NCCUR):Item 140.119/134086

English | 正體中文 | 简体中文 | Post-Print筆數 : 27 | 全文笔数/总笔数 : 113318/144297 (79%)
造访人次 : 50964965 在线人数 : 941

RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.

搜寻范围

查询小技巧：

您可在西文检索词汇前后加上"双引号"，以获取较精准的检索结果

若欲以作者姓名搜寻，建议至进阶搜寻限定作者字段，可获得较完整数据

进阶搜寻

主页 ‧ 登入 ‧ 上传 ‧ 说明 ‧ 关于政大典藏 ‧ 管理

到手机版

政大機構典藏 > 資訊學院 > 資訊科學系 > 學位論文 > Item 140.119/134086

请使用永久网址来引用或连结此文件: https://nccur.lib.nccu.edu.tw/handle/140.119/134086

题名:	以視覺化系統探索社群媒體中的使用者行為 A Visual Analytics System for Exploring User Behavior in Social Media
作者:	李柏彥 Li, Po-Yen
贡献者:	紀明德 Chi, Ming-Te 李柏彥 Li, Po-Yen
关键词:	視覺化社群媒體使用者行為探索系統 Visual Analytic System Social media User Behavior
日期:	2021
上传时间:	2021-03-02 14:32:33 (UTC+8)
摘要:	社群媒體是現代社會中獲取資訊的主要管道之一，同時也是人們發表意見的地方，然而，人們的意見經常被社群媒體上的意見領袖所左右，而意見領袖的聲量通常透過發表文章及評論來累積，但也有可能是特定集團抬轎而來，因此，本研究提出一個視覺化分析系統，將使用者之間的行為相似度表示成距離矩陣並排序，再以基於熱度圖的視覺化呈現，並且利用使用者與文章的二分關係將其繪製成具關聯矩陣風格的視覺化，結合上述兩者視覺化來觀察使用者活動情形並比較不同使用者類型的差異，可以幫助人們了解意見領袖的聲量是如何累積，以及他們是如何讓其關注的議題被更多人看見，最後，我們會做使用者研究來評估本論文的成效。 Social media is one of the main channels for obtaining information in modern society, and it is also a place where people can express their opinions. However, people`s views are often influenced by opinion leaders on social media. The influence of opinion leaders is usually accumulated by publishing articles and comments, but it may also be carried by specific groups. Therefore, this research proposes a visual analysis system, which expresses the behavior similarity between users as a sorted distance matrix, and then visualizes them based on an ordered heatmap. We also use bipartite relations between users and articles to draw it into visualization with an adjacency matrix style. By combining the above two visualizations, we can observe users` activities and compare the differences between different types of users. The system can help people understand how to accumulate the influence of the opinion leader and how they make their concerns more visible.
參考文獻:	[1] J. Heer, & D. Boyd. Vizster: visualizing online social networks, IEEE Symposium on Information Visualization (INFOVIS 2005), 2005. [2] Nan Cao, Yu-Ru Lin, Fan Du, & Dashun Wang. Episogram: Visual Summarization of Egocentric Social Interactions. IEEE Computer Graphics and Applications 36.5: 72-81, 2016. [3] Mengdie Hu, Krist Wongsuphasawat, & John Stasko. Visualizing Social Media Content with SentenTree. IEEE Transactions on Visualization and Computer Graphics, 23.1, 2017. [4] P. Xu, Y. Wu, E. Wei, T.-Q. Peng, S. Liu, J. J. H. Zhu, & H. Qu. Visual analysis of topic competition on social media. IEEE Transactions on Visualization and Computer Graphics, 19.12:2012–2021, 2013. [5] F. Viégas, M. Wattenberg, & J. Hebert. Google+Ripples: a native visualization of information flow. WWW `13: Proceedings of the 22nd international conference on World Wide Web, pages 1389-1398, 2013. [6] S. Chen, S. Chen, Z. Wang, J. Liang, X. Yuan, N. Cao, & Y. Wu. D-Map: Visual Analysis of Ego-centric Information Diffusion Patterns in Social Media. 2016 IEEE Conference on Visual Analytics Science and Technology (VAST), 2016. [7] M. Sun, P. Mi, C. North, & N. Ramakrishnan. Biset: Semantic edge bundling with biclusters for sensemaking. IEEE transactions on visualization and computer graphics, 22(1):310–319, 2016. [8] G. Y.-Y. Chan, P. Xu, Z. Dai, & L. Ren. Vibr: Visualizing bipartite relations at scale with the minimum description length principle. IEEE TVCG, 25(1):321–330, 2019. [9] M. Bostock, V. Ogievetsky, & J. Heer. D3 data-driven documents, IEEE transactions on visualization and computer graphics, 17.12: 2301-2309, 2011. [10] ptt-web-crawler is a crawler for the web version of ptt @ONLINE. [Online]. Available: https://github.com/jwlin/ptt-web-crawler. [11] S. Tilkov & S. Vinoski, "Node. js: Using JavaScript to build high-performance network programs," IEEE Internet Computing, vol. 14, no. 6, pp. 80-83, 2010. [12] Maoran Zhu, Xingkai Lin, Ting Lu, & Hongwei Wang. Identification of Opinion Leaders in Social Networks Based on Sentiment Analysis: Evidence from an Automotive Forum. International Conference on Modeling, Simulation and Optimization Technologies and Applications (MSOTA2016). [13] M. Behrisch, B. Bach, N. Henry Riche, T. Schreck, & J.-D. Fekete. Matrix reordering methods for table and network visualization. Computer Graphics Forum, 35(3):693–716, 2016. [14] FEKETE J.-D.. Reorder.js: A JavaScript Library to Reorder Tables and Networks. IEEE VIS 2015, Oct. 2015. Poster. [15] V.D. Blondel, J.-L. Guillaume, & R. Lambiotte, and E. Lefebvre. Fast unfolding of communities in large networks. J. of Statistical Mechanics, page P10008, 2008. [16] M. Newman. Modularity and community structure in networks. Proceedings of the National Academy of Sciences, 103(23):8577–8582, 2006.
描述:	碩士國立政治大學資訊科學系 107753033
資料來源:	http://thesis.lib.nccu.edu.tw/record/#G0107753033
数据类型:	thesis
DOI:	10.6814/NCCU202100352
显示于类别:	[資訊科學系] 學位論文

文件中的档案:

档案	描述	大小	格式	浏览次数
303301.pdf		6266Kb	Adobe PDF2	101	检视/开启

在政大典藏中所有的数据项都受到原著作权保护.

社群 sharing

著作權政策宣告 Copyright Announcement

1.本網站之數位內容為國立政治大學所收錄之機構典藏，無償提供學術研究與公眾教育等公益性使用，惟仍請適度，合理使用本網站之內容，以尊重著作權人之權益。商業上之利用，則請先取得著作權人之授權。
The digital content of this website is part of National Chengchi University Institutional Repository. It provides free access to academic research and public education for non-commercial use. Please utilize it in a proper and reasonable manner and respect the rights of copyright owners. For commercial use, please obtain authorization from the copyright owner in advance.

2.本網站之製作，已盡力防止侵害著作權人之權益，如仍發現本網站之數位內容有侵害著作權人權益情事者，請權利人通知本網站維護人員(nccur@nccu.edu.tw)，維護人員將立即採取移除該數位著作等補救措施。
NCCU Institutional Repository is made to protect the interests of copyright owners. If you believe that any material on the website infringes copyright, please contact our staff(nccur@nccu.edu.tw). We will remove the work from the repository and investigate your claim.

DSpace Software Copyright © 2002-2004 MIT & Hewlett-Packard / Enhanced by NTU Library IR team Copyright © - 回馈