Loading...
|
Please use this identifier to cite or link to this item:
https://nccur.lib.nccu.edu.tw/handle/140.119/152573
|
| Title: | 社群網路動態立場視覺化套件開發
Development of Social Network Dynamic Stance Visualization Tool |
| Authors: | 張雯鈞
Chang, Wen-Chun |
| Contributors: | 李蔡彥
Li, Tsai-Yen
張雯鈞
Chang, Wen-Chun |
| Keywords: | 機器學習
深度學習
社會網路
資訊視覺化系統
Machine Learning
Deep Learning
Social Network
Information Visualization Tool |
| Date: | 2024 |
| Issue Date: | 2024-08-05 12:46:03 (UTC+8) |
| Abstract: | 近年來社群媒體（Social Media）快速發展，許多社群媒體如Facebook、YouTube、Twitter等紛紛興起，用戶開始成為內容的主要生產者。報導指出全台約有85%的人口有在使用社群平台，這表示了大多數人都會透過社群媒體發表自己的觀點和意見。然而對於社群媒體研究者來說，要分析這些每日產生的大量資料是非常困難的，網路世界的多樣性讓研究者難以找出一個脈絡，加上社群媒體的互動非常多元，以Twitter為例，常見的互動方式包括按讚、追蹤、轉推等，研究者該如何透過這些互動觀察出特別的關係成為一個議題。透過和社群媒體研究者的需求訪談，本研究針對幾個研究者的需求做功能開發，主要有三個痛點，首先是無法快速的釐清社群媒體用戶在不同時間區段主要關注的主題有哪些，其二是社群媒體用戶是否會在不同的時間點有有不一樣的立場，最後則是在這麼多用戶中是否有特別重要的帳號能對其他用戶產生影響力。為了解決這些問題，本研究透過主題模型（Topic Modeling）快速的在大量資料中找出社群媒體用戶在關注的事件，並且藉由機器學習（Machine Learning）等技術預測用戶在不同時間區段的立場，結合社群網路圖（Social Network）做視覺化呈現，最後使用社群網路指標評估具有不同影響力的用戶。除此之外，為了使視覺化介面有更完善的互動操作，我們應用時下最新的視覺化套件，達成更好的使用者體驗（User Experience）。本研究將邀請多位受試者做測試，藉由設計問卷的方式來評估建構之系統的表現。
In recent years, social media platforms like Facebook, YouTube, and Twitter have rapidly developed, making users the main content creators. Reports show that about 85% of Taiwan's population uses social media, indicating widespread expression of views and opinions online. However, social media researchers find it challenging to analyze the vast amount of data generated daily. The diversity of the online world and the variety of interactions, such as likes, follows, and retweets on Twitter, complicate the identification of significant patterns and relationships.
Interviews with social media researchers revealed three main pain points. First, difficulty in quickly identifying key topics that users focus on at different times. Second, determining if users' stances change over time. Third, identifying influential accounts that impact other users.
To address these issues, this study uses topic modeling to identify key events from large datasets, machine learning to predict users' stances over time, and social network visualization to present findings. Social network indicators are also used to evaluate user influence. To enhance the visualization interface, the latest tools are applied for a better user experience. The system will be tested by multiple participants, and its performance will be evaluated through questionnaires. |
| Reference: | 1. Christos H. Papadimitriou, Prabhakar Raghavan, Hisao Tamaki, Santosh Vempala, Latent semantic indexing: A probabilistic analysis. In Proceedings of the 1998 17th ACM SIGART-SIGMOD-SIGART Symposium on Principles of Database Systems, PODS. 1998.
2. Thomas Hofmann, Probabilistic Latent Semantic Analysis. In Proceedings of the Fifteenth Conference on Uncertainty in Artificial Intelligence. 1999.
3. David M. Blei, Andrew Y. Ng, Michael I. Jordan, Latent dirichlet allocation. The Journal of Machine Learning Research, Volume 3, pp 993–1022. 2003.
4. Xiaohui Yan, Jiafeng Guo, Yanyan Lan, Xueqi Cheng, A biterm topic model for short texts. In Proceedings of the 22nd international conference on World Wide Web. 2013.
5. Christopher E Moody, Mixing Dirichlet Topic Models and Word Embeddings to Make lda2vec. arXiv preprint arXiv:1605.02019. 2016.
6. Abeer AlDayel, Walid Magdy, Stance Detection on Social Media: State of the Art and Trends. Information Processing & Management, Volume 58, Issue 4. 2021.
7. Yun-Shiuan Chuang, Tutorials on Stance Detection using Pre-trained Language Models: Fine-tuning BERT and Prompting Large Language Models. arXiv preprint arXiv:2307.15331. 2023.
8. Simmel, G.. The Sociology of Georg Simmel [translated, edited and with an introduction by Kurt H Wolff]. 1950.
9. Cartwright, D., Zander, A. (Eds.), Group dynamics research and theory. Row, Peterson. 1953.
10. F. Harary, R.Z. Norman, Graph Theory as a Mathematical Model in Social Science. Ann Arbor, University of Michigan, Institute for Social Research, VII, p. 45. 1953.
11. Kogut, B., & Walker, G, The small world of Germany and the durability of national networks. American Sociological Review, 66(3), 317–335. 2001.
12. Linton C. Freeman, A Set of Measures of Centrality Based on Betweenness. American Sociological Association, Volume 40, No. 1 pp. 35-41. 1977.
13. Bavelas, Communication patterns in task-oriented groups. Journal of the Acoustical Society of America, 22:271--282. 1950.
14. Xueqi Cheng, Xiaohui Yan, Yanyan Lan, Jiafeng Guo, BTM: Topic Modeling over Short Texts. IEEE Transactions on Knowledge and Data Engineering, Volume 26, Issue: 12, 01 December. 2014.
15. Bryan Perozzi, Rami Al-Rfou, Steven Skiena, DeepWalk: Online Learning of Social Representations, KDD '14: Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data miningAugust, Pages 701–710. 2014.
16. Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg Corrado, Jeffrey Dean, Distributed Representations of Words and Phrases and their Compositionality, arXiv:1310.4546. 2013.
17. Laurens van der Maaten, Geoffrey Hinton, Visualizing Data using t-SNE, Journal of Machine Learning Research, 9, 2579-2605. 2008.
18. Chen Chia Wei, Design of an intelligent visualization tool for analyzing social network dynamcis, master thesis of Department of Computer Science National Chengchi University. 2022.
19. Mohammad, S., Kiritchenko, S., Sobhani, P., Zhu, X., & Cherry, C., A dataset for detecting stance in tweets. In Proceedings of the tenth international conference on language resources and evaluation (pp. 3945–3952). 2016.
20. Darwish, K., Magdy, W., & Zanouda, T., Improved stance prediction in a user similarity feature space. In Proceedings of the 2017 IEEE/ACM international conference on advances in social networks analysis and mining. 2017.
21. Edmund Landau, Zur elative Wertbemessung der Turnierresultate, In Deutsches Wochenschach, 366–369. 1985.
22. John Brooke, SUS: A quick and dirty usability scale. Usability Eval. Ind., Volume 189, no. 194, pp. 4–7. 1996.
23. Aaron Bangor, PhD, CHFP, Philip Kortum, PhD, James Miller, PhD, Determining What Individual SUS Scores Mean: Adding an Adjective Rating Scale. Journal of Experience, Volume 4, Issue 3. 2009.
24. Giglietto, F., Righetti, N., Rossi, L., Marino, G.. It takes a village to manipulate the media: coordinated link sharing behavior during 2018 and 2019 Italian elections. Information. Communication and Society, 1–25. 2020.
25. Hugging Face. https://huggingface.co
26. Digital 2023: Taiwan. https://datareportal.com/reports/digital-2023-taiwan |
| Description: | 碩士
國立政治大學
資訊科學系
111753153 |
| Source URI: | http://thesis.lib.nccu.edu.tw/record/#G0111753153 |
| Data Type: | thesis |
| Appears in Collections: | [資訊科學系] 學位論文
|
Files in This Item:
| File |
Size | Format | |
|---|
| 315301.pdf | 4752Kb | Adobe PDF | 0 | View/Open |
|
All items in 政大典藏 are protected by copyright, with all rights reserved.
|
