學術產出-學位論文
文章檢視/開啟
書目匯出
-
題名 動態社群網絡之智慧型視覺化分析工具開發
Design of An Intelligent Visualization Tool for Analyzing Social Network Dynamics作者 陳嘉葳
Chen, Chai-Wei貢獻者 李蔡彥
Li, Tsai-Yen
陳嘉葳
Chen, Chai-Wei關鍵詞 機器學習
深度學習
社會網絡
社會資本
資訊視覺化系統
Machine learning
Deep learning
Social network
Social capital
Information visualization System日期 2022 上傳時間 1-七月-2022 16:21:23 (UTC+8) 摘要 近年來，社群網路 （Social Media）逐漸成為人們討論生活大小事的虛擬平台，例如在Twitter上，每秒6000則的貼文使得社群媒體上累積大量、豐富且多元的資料；然而，在資料龐大且複雜的情況下，如何有一套有效的整理、分析並解讀資料的機制變得相當重要的，也是近年火熱的研究議題之一。本研究的目的在於針對社群媒體複雜凌亂的資料，以社群媒體研究者為使用對象，建立一套以社會網絡 （Social Network）為基礎的視覺化工具，目的在於透過工具的探索與觀察，能夠剖析特定事件下社群媒體使用者凝聚成社群、甚至「結盟」的狀況；再者，透過「時間軸」的設計，希望能夠看到社群凝聚與消散過程的動態變化，以讓工具使用者能方便觀察社群動態變化及其涵意，並期待針對社會資本（Social Capital）、同質性理論（Homophily）等社群網路有名的理論，透過工具進行詮釋、探索以及分析。本研究透過實驗方式驗證系統設計的有效性。我們共邀請20位受試者協助本研究進行測試，於實驗過程中，受試者會依序進行「教學任務」與「正式任務」，以熟悉工具使用，並進行社群網絡資料的探索。我們會記錄受試者學習工具操作的時間，並請其填寫包含USE問卷與使用有效性問卷，以及進行開放性問題的深度訪談。我們從問卷結果與回饋中得到幾項發現：1. 雖然工具本身需要具有相關知識與經驗才能容易上手，也需要花時間學習，但對於社群研究者以及工作者來說，本研究所設計的系統可以提供一個有效且具備探索上高自由度與高度解釋性的工具進行社群探索；2. 在加入社會資本概念後，能明確觀察到社群資本的動態變化以及流動擴散，並能增加探索的多元性以及可解釋性。本研究所設計的系統除提供目標使用者有效的探索工具外，亦證明社會資本概念的加入能讓本社群探索工具更為直覺，並提供未來相關研究一個可以持續發展與實踐的方向。
In recent years, social media has become a platform for people to discuss many issues and trends. For example, due to the increasing number of tweets on Twitter, we have accumulated a large amount of rich and diverse information. However, how to effectively explore and in-terpret huge and complex data has become an important and popular research topic in recent years. The purpose of this research is to design a visualization tool for social media researchers such that they can explore and analyze the social network on these media. It can be used to analyze how the social media users coalesce into communities or even under specific events. Moreover, the tool allows the users to see the dynamics in the process of community coales-cence and dispersal. Through the time-line design of the visualization tool, we hope to allow the users to easily observe the dynamic changes of the community as well as the interpretation, exploration and analysis of well-known social network theories such as social capital and ho-mophily. We have designed an experiment to evaluate our system. A total of 20 subjects were invited to participate in the experiment. The subjects become familiar with the tools through an instruction mission and a main mission in sequence. The time for the subjects to learn the operations of the tool was recorded, and an questionnaire was used to evaluate the system. There are several findings from the questionnaires and feedback of the subjects: 1. Although the tool itself requires relevant knowledge and experience for the users to learn how to use the system, it provides an effective tool with a high degree of freedom for exploration and inter-pretation of social community; 2. The incorporation of the concept of social capital into the system can clearly help the users observe the dynamic changes and diffusion of community capital, which can increase the diversity and interpretability of the exploration. The tool was shown to be effective for the target users, and the implementation of the social capital con-cept makes community exploration more intuitive. The experimental results also shed some lights on the future research directions.參考文獻 1. Kossinets, G. and D.J. Watts, Origins of homophily in an evolving social network. American journal of sociology, 2009. 115(2): p. 405-450. 2. Ziems, C., B. He, S. Soni, and S. Kumar, Racism is a virus: Anti-asian hate and counterhate in social media during the covid-19 crisis. arXiv preprint arXiv:2005.12423, 2020. 3. Coleman, J.S., Social capital in the creation of human capital. American journal of sociology, 1988. 94: p. S95-S120. 4. Bourdieu, P., The forms of capital. 2018: Routledge. 5. Putnam, R.D., Bowling alone: The collapse and revival of American community. 2000: Simon and schuster. 6. Lin, N., Social capital: A theory of social structure and action. 2002: Cambridge university press. 7. Page, L., S. Brin, R. Motwani, and T. Winograd, The PageRank citation ranking: Bringing order to the web. 1999, Stanford InfoLab. 8. Granovetter, M.S., The strength of weak ties. American journal of sociology, 1973. 78(6): p. 1360-1380. 9. Smith, M.S. Social capital in online communities. in Proceedings of the 2nd PhD workshop on Information and knowledge management. 2008. 10. Venkatanathan, J., E. Karapanos, V. Kostakos, and J. Gonçalves. Network, personality and social capital. in Proceedings of the 4th annual ACM web science conference. 2012. 11. Subbian, K., D. Sharma, Z. Wen, and J. Srivastava. Social capital: the power of influencers in networks. in Proceedings of the 2013 international conference on Autonomous agents and multi-agent systems. 2013. 12. Geys, B. and Z. Murdoch, Measuring the ‘bridging’versus ‘bonding’nature of social networks: A proposal for integrating existing measures. Sociology, 2010. 44(3): p. 523-540. 13. Cao, Q., Y. Lu, D. Dong, Z. Tang, and Y. Li, The roles of bridging and bonding in social media communities. Journal of the American Society for Information Science and Technology, 2013. 64(8): p. 1671-1681. 14. Phua, J., S.V. Jin, and J.J. Kim, Uses and gratifications of social networking sites for bridging and bonding social capital: A comparison of Facebook, Twitter, Instagram, and Snapchat. Computers in human behavior, 2017. 72: p. 115-122. 15. Wallner, G., S. Kriglstein, and A. Drachen. Tweeting your destiny: Profiling users in the twitter landscape around an online game. in 2019 IEEE Conference on Games (CoG). 2019. IEEE. 16. Haupt, M.R., A. Jinich-Diamant, J. Li, M. Nali, and T.K. Mackey, Characterizing twitter user topics and communication network dynamics of the “liberate” movement during COVID-19 using unsupervised machine learning and social network analysis. Online Social Networks and Media, 2021. 21: p. 100114. 17. Gaol, F.L., A. Maulana, and T. Matsuo, News consumption patterns on Twitter: fragmentation study on the online news media network. Heliyon, 2020. 6(10): p. e05169. 18. Lam, A.J. and C. Cheng. Utilizing Tweet Content for the Detection of Sentiment-Based Interaction Communities on Twitter. in 2018 IEEE 5th International Conference on Data Science and Advanced Analytics (DSAA). 2018. IEEE. 19. Petersen, K. and J.M. Gerken, # Covid-19: An exploratory investigation of hashtag usage on Twitter. Health Policy, 2021. 125(4): p. 541-547. 20. Weaver, I.S., H. Williams, I. Cioroianu, M. Williams, T. Coan, and S. Banducci, Dynamic social media affiliations among UK politicians. Social Networks, 2018. 54: p. 132-144. 21. Cao, N., L. Lu, Y.-R. Lin, F. Wang, and Z. Wen, SocialHelix: visual analysis of sentiment divergence in social media. Journal of Visualization, 2014. 18(2): p. 221-235. 22. Spanner, S., M. Burghardt, and C. Wolff, Twista–An Application for the Analysis and Visualization of Tailored Tweet Collections. 2015. 23. Garimella, K., G. De Francisc iMorales, A. Gionis, and M. Mathioudakis, Mary, Mary, Quite Contrary, in Proceedings of the 26th International Conference on World Wide Web Companion - WWW `17 Companion. 2017. p. 201-205. 24. Twitter API - Standard v1.1 [Online]. Avaliable: https://developer.twitter.com/en/docs/api-reference-index#Twitter. 25. Perozzi, B., R. Al-Rfou, and S. Skiena. Deepwalk: Online learning of social representations. in Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining. 2014. 26. Flood and Fire, National Chengchi University [Online], Web Page: https://sites.google.com/view/floodfire/%E9%A6%96%E9%A0%81?authuser=0. 27. Ma, W.-Y. and K.-J. Chen. Introduction to CKIP Chinese word segmentation system for the first international Chinese word segmentation bakeoff. in Proceedings of the second SIGHAN workshop on Chinese language processing. 2003. 28. Jelodar, H., Y. Wang, C. Yuan, X. Feng, X. Jiang, Y. Li, and L. Zhao, Latent Dirichlet allocation (LDA) and topic modeling: models, applications, a survey. Multimedia Tools and Applications, 2019. 78(11): p. 15169-15211. 29. Devlin, J., M.-W. Chang, K. Lee, and K. Toutanova, Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805, 2018. 30. Xu, H., B. Liu, L. Shu, and Philip, BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis. arXiv pre-print server, 2019. 31. nlptown/bert-base-multilingual-uncased-sentiment [Online] Available: https://huggingface.co/nlptown/bert-base-multilingual-uncased-sentiment. 32. Su, X. and T.M. Khoshgoftaar, A survey of collaborative filtering techniques. Advances in artificial intelligence, 2009. 2009. 33. van der Maaten, L.J.P. t-Distributed Stochastic Neighbor Embedding [Online] Available: https://lvdmaaten.github.io/tsne/. 34. 蘇國賢, 〖作伙來想社會〗台灣人變得越來越孤獨？從社會網絡分析中，看見台灣近20年的社會變遷。. 台灣社會學會YouTube頻道。 Available: https://www.youtube.com/watch?v=LtksJhrT3Vc, 2021. 35. 張明宜、傅仰止, 社群媒體與大學生的網絡界限：伴遊圈、談話圈、接觸圈。. 台灣社會學，37，頁1-46。, 2019. 36. Lamont, M. and V. Molnár, The study of boundaries in the social sciences. Annual review of sociology, 2002. 28(1): p. 167-195. 37. Pollet, T.V., S.G. Roberts, and R.I. Dunbar, Extraverts have larger social network layers. Journal of Individual Differences, 2011. 38. Haerter, J.O., B. Jamtveit, and J. Mathiesen, Communication dynamics in finite capacity social networks. Physical review letters, 2012. 109(16): p. 168701. 39. Gonçalves, B., N. Perra, and A. Vespignani, Modeling users` activity on twitter networks: Validation of dunbar`s number. PloS one, 2011. 6(8): p. e22656. 40. Halpern, D., Social Capital (Cambridge: Polity). 2005. 41. Burt, R.S., From structural holes: The social structure of competition. The new economic sociology: a reader, 2004: p. 325-348. 42. Borgatti, S.P., Structural holes: Unpacking Burt’s redundancy measures. Connections, 1997. 20(1): p. 35-38. 43. Sievert, C. and K. Shirley. LDAvis: A method for visualizing and interpreting topics. in Proceedings of the workshop on interactive language learning, visualization, and interfaces. 2014. 44. Lund, A.M., Measuring usability with the use questionnaire12. Usability interface, 2001. 8(2): p. 3-6. 描述 碩士
國立政治大學
資訊科學系
109753134資料來源 http://thesis.lib.nccu.edu.tw/record/#G0109753134 資料類型 thesis dc.contributor.advisor 李蔡彥 zh_TW dc.contributor.advisor Li, Tsai-Yen en_US dc.contributor.author (作者) 陳嘉葳 zh_TW dc.contributor.author (作者) Chen, Chai-Wei en_US dc.creator (作者) 陳嘉葳 zh_TW dc.creator (作者) Chen, Chai-Wei en_US dc.date (日期) 2022 en_US dc.date.accessioned 1-七月-2022 16:21:23 (UTC+8) - dc.date.available 1-七月-2022 16:21:23 (UTC+8) - dc.date.issued (上傳時間) 1-七月-2022 16:21:23 (UTC+8) - dc.identifier (其他 識別碼) G0109753134 en_US dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/140662 - dc.description (描述) 碩士 zh_TW dc.description (描述) 國立政治大學 zh_TW dc.description (描述) 資訊科學系 zh_TW dc.description (描述) 109753134 zh_TW dc.description.abstract (摘要) 近年來，社群網路 （Social Media）逐漸成為人們討論生活大小事的虛擬平台，例如在Twitter上，每秒6000則的貼文使得社群媒體上累積大量、豐富且多元的資料；然而，在資料龐大且複雜的情況下，如何有一套有效的整理、分析並解讀資料的機制變得相當重要的，也是近年火熱的研究議題之一。本研究的目的在於針對社群媒體複雜凌亂的資料，以社群媒體研究者為使用對象，建立一套以社會網絡 （Social Network）為基礎的視覺化工具，目的在於透過工具的探索與觀察，能夠剖析特定事件下社群媒體使用者凝聚成社群、甚至「結盟」的狀況；再者，透過「時間軸」的設計，希望能夠看到社群凝聚與消散過程的動態變化，以讓工具使用者能方便觀察社群動態變化及其涵意，並期待針對社會資本（Social Capital）、同質性理論（Homophily）等社群網路有名的理論，透過工具進行詮釋、探索以及分析。本研究透過實驗方式驗證系統設計的有效性。我們共邀請20位受試者協助本研究進行測試，於實驗過程中，受試者會依序進行「教學任務」與「正式任務」，以熟悉工具使用，並進行社群網絡資料的探索。我們會記錄受試者學習工具操作的時間，並請其填寫包含USE問卷與使用有效性問卷，以及進行開放性問題的深度訪談。我們從問卷結果與回饋中得到幾項發現：1. 雖然工具本身需要具有相關知識與經驗才能容易上手，也需要花時間學習，但對於社群研究者以及工作者來說，本研究所設計的系統可以提供一個有效且具備探索上高自由度與高度解釋性的工具進行社群探索；2. 在加入社會資本概念後，能明確觀察到社群資本的動態變化以及流動擴散，並能增加探索的多元性以及可解釋性。本研究所設計的系統除提供目標使用者有效的探索工具外，亦證明社會資本概念的加入能讓本社群探索工具更為直覺，並提供未來相關研究一個可以持續發展與實踐的方向。 zh_TW dc.description.abstract (摘要) In recent years, social media has become a platform for people to discuss many issues and trends. For example, due to the increasing number of tweets on Twitter, we have accumulated a large amount of rich and diverse information. However, how to effectively explore and in-terpret huge and complex data has become an important and popular research topic in recent years. The purpose of this research is to design a visualization tool for social media researchers such that they can explore and analyze the social network on these media. It can be used to analyze how the social media users coalesce into communities or even under specific events. Moreover, the tool allows the users to see the dynamics in the process of community coales-cence and dispersal. Through the time-line design of the visualization tool, we hope to allow the users to easily observe the dynamic changes of the community as well as the interpretation, exploration and analysis of well-known social network theories such as social capital and ho-mophily. We have designed an experiment to evaluate our system. A total of 20 subjects were invited to participate in the experiment. The subjects become familiar with the tools through an instruction mission and a main mission in sequence. The time for the subjects to learn the operations of the tool was recorded, and an questionnaire was used to evaluate the system. There are several findings from the questionnaires and feedback of the subjects: 1. Although the tool itself requires relevant knowledge and experience for the users to learn how to use the system, it provides an effective tool with a high degree of freedom for exploration and inter-pretation of social community; 2. The incorporation of the concept of social capital into the system can clearly help the users observe the dynamic changes and diffusion of community capital, which can increase the diversity and interpretability of the exploration. The tool was shown to be effective for the target users, and the implementation of the social capital con-cept makes community exploration more intuitive. The experimental results also shed some lights on the future research directions. en_US dc.description.tableofcontents 致謝 i 摘要 ii Abstract iii 目錄 iv 圖目錄 vi 表目錄 viii 第一章、導論 1 1.1 研究動機 1 1.2 研究目標 1 1.3 預期貢獻 3 第二章、相關研究 5 2.1 社會網絡：從社會科學角度探討網路社群的演變與難題 5 2.2 社會資本概念操作化及公民參與程度探討 6 2.3 大數據、數位社會與社會網絡：虛擬社群中議題極化立場討論研究 8 2.4 小結 11 第三章、系統架構與設計 13 3.1 系統設計與概觀 13 3.2 第一部分（Phase 1）- 資料來源（Data Collection） 14 3.3 第二部分（Phase 2）- 核心演算法 16 3.3.1 主題探索與篩選（Topic Exploring） 16 3.3.2 社群偵測與探索（Community Detection） 20 3.4 第三部分（Phase 3）- 系統設計與建置 33 第四章、系統成果演示與演算法成果驗證 36 4.1工具開發與實驗資料選取 36 4.2第一階段核心演算法演示：Deep Walk社群轉發行為偵測演算法 39 4.3第二階段核心演算法演示：社會資本概念演算法及網路資源的累積 42 4.3.1 社會資本計算視覺化 42 4.3.2 社會資本功能與角色分析 43 4.4 演算法結果驗證：系統處理網絡結構前後差異 46 4.5 演算法結果驗證：社群討論變化驗證與Sliding Window參數選擇 47 4.6 演算法驗證小結 48 第五章、系統介面與操作流程演示 50 5.1 系統介面概況 50 5.2 系統核心探索界面介紹 – Network of Retweet Behavior 53 5.3 系統操作步驟與介面介紹 54 第六章、實驗 59 6.1 實驗流程、問卷與受試者基本資料 59 6.1.1 使用者背景與身分 60 6.1.2 USE問卷 62 6.1.3 系統有效性問卷 62 6.2 量化題目結果整理 63 6.2.1 問卷量化數據呈現與分析 63 6.2.2 專業知識對於系統使用之影響 66 6.3 受試者操作案例分析與回饋內容整理 67 6.3.1系統優點與特色 68 6.3.2系統缺點 72 6.3.3社群領域研究者與工作者回饋 73 第七章、結論與未來展望 75 7.1 結論 75 7.2 研究限制與未來展望 76 References 79 附錄一、實驗同意書 82 附錄二、受試者問卷 83 附錄三、實驗任務-教學與主要任務 86 附錄四、答題結果：USE問卷優缺點項目 94 附錄五、答題結果：系統有效性問卷-開放式問題 96 附錄六、受試者教學任務與主要任務回饋 101 zh_TW dc.format.extent 7682477 bytes - dc.format.mimetype application/pdf - dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0109753134 en_US dc.subject (關鍵詞) 機器學習 zh_TW dc.subject (關鍵詞) 深度學習 zh_TW dc.subject (關鍵詞) 社會網絡 zh_TW dc.subject (關鍵詞) 社會資本 zh_TW dc.subject (關鍵詞) 資訊視覺化系統 zh_TW dc.subject (關鍵詞) Machine learning en_US dc.subject (關鍵詞) Deep learning en_US dc.subject (關鍵詞) Social network en_US dc.subject (關鍵詞) Social capital en_US dc.subject (關鍵詞) Information visualization System en_US dc.title (題名) 動態社群網絡之智慧型視覺化分析工具開發 zh_TW dc.title (題名) Design of An Intelligent Visualization Tool for Analyzing Social Network Dynamics en_US dc.type (資料類型) thesis en_US dc.relation.reference (參考文獻) 1. Kossinets, G. and D.J. Watts, Origins of homophily in an evolving social network. American journal of sociology, 2009. 115(2): p. 405-450. 2. Ziems, C., B. He, S. Soni, and S. Kumar, Racism is a virus: Anti-asian hate and counterhate in social media during the covid-19 crisis. arXiv preprint arXiv:2005.12423, 2020. 3. Coleman, J.S., Social capital in the creation of human capital. American journal of sociology, 1988. 94: p. S95-S120. 4. Bourdieu, P., The forms of capital. 2018: Routledge. 5. Putnam, R.D., Bowling alone: The collapse and revival of American community. 2000: Simon and schuster. 6. Lin, N., Social capital: A theory of social structure and action. 2002: Cambridge university press. 7. Page, L., S. Brin, R. Motwani, and T. Winograd, The PageRank citation ranking: Bringing order to the web. 1999, Stanford InfoLab. 8. Granovetter, M.S., The strength of weak ties. American journal of sociology, 1973. 78(6): p. 1360-1380. 9. Smith, M.S. Social capital in online communities. in Proceedings of the 2nd PhD workshop on Information and knowledge management. 2008. 10. Venkatanathan, J., E. Karapanos, V. Kostakos, and J. Gonçalves. Network, personality and social capital. in Proceedings of the 4th annual ACM web science conference. 2012. 11. Subbian, K., D. Sharma, Z. Wen, and J. Srivastava. Social capital: the power of influencers in networks. in Proceedings of the 2013 international conference on Autonomous agents and multi-agent systems. 2013. 12. Geys, B. and Z. Murdoch, Measuring the ‘bridging’versus ‘bonding’nature of social networks: A proposal for integrating existing measures. Sociology, 2010. 44(3): p. 523-540. 13. Cao, Q., Y. Lu, D. Dong, Z. Tang, and Y. Li, The roles of bridging and bonding in social media communities. Journal of the American Society for Information Science and Technology, 2013. 64(8): p. 1671-1681. 14. Phua, J., S.V. Jin, and J.J. Kim, Uses and gratifications of social networking sites for bridging and bonding social capital: A comparison of Facebook, Twitter, Instagram, and Snapchat. Computers in human behavior, 2017. 72: p. 115-122. 15. Wallner, G., S. Kriglstein, and A. Drachen. Tweeting your destiny: Profiling users in the twitter landscape around an online game. in 2019 IEEE Conference on Games (CoG). 2019. IEEE. 16. Haupt, M.R., A. Jinich-Diamant, J. Li, M. Nali, and T.K. Mackey, Characterizing twitter user topics and communication network dynamics of the “liberate” movement during COVID-19 using unsupervised machine learning and social network analysis. Online Social Networks and Media, 2021. 21: p. 100114. 17. Gaol, F.L., A. Maulana, and T. Matsuo, News consumption patterns on Twitter: fragmentation study on the online news media network. Heliyon, 2020. 6(10): p. e05169. 18. Lam, A.J. and C. Cheng. Utilizing Tweet Content for the Detection of Sentiment-Based Interaction Communities on Twitter. in 2018 IEEE 5th International Conference on Data Science and Advanced Analytics (DSAA). 2018. IEEE. 19. Petersen, K. and J.M. Gerken, # Covid-19: An exploratory investigation of hashtag usage on Twitter. Health Policy, 2021. 125(4): p. 541-547. 20. Weaver, I.S., H. Williams, I. Cioroianu, M. Williams, T. Coan, and S. Banducci, Dynamic social media affiliations among UK politicians. Social Networks, 2018. 54: p. 132-144. 21. Cao, N., L. Lu, Y.-R. Lin, F. Wang, and Z. Wen, SocialHelix: visual analysis of sentiment divergence in social media. Journal of Visualization, 2014. 18(2): p. 221-235. 22. Spanner, S., M. Burghardt, and C. Wolff, Twista–An Application for the Analysis and Visualization of Tailored Tweet Collections. 2015. 23. Garimella, K., G. De Francisc iMorales, A. Gionis, and M. Mathioudakis, Mary, Mary, Quite Contrary, in Proceedings of the 26th International Conference on World Wide Web Companion - WWW `17 Companion. 2017. p. 201-205. 24. Twitter API - Standard v1.1 [Online]. Avaliable: https://developer.twitter.com/en/docs/api-reference-index#Twitter. 25. Perozzi, B., R. Al-Rfou, and S. Skiena. Deepwalk: Online learning of social representations. in Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining. 2014. 26. Flood and Fire, National Chengchi University [Online], Web Page: https://sites.google.com/view/floodfire/%E9%A6%96%E9%A0%81?authuser=0. 27. Ma, W.-Y. and K.-J. Chen. Introduction to CKIP Chinese word segmentation system for the first international Chinese word segmentation bakeoff. in Proceedings of the second SIGHAN workshop on Chinese language processing. 2003. 28. Jelodar, H., Y. Wang, C. Yuan, X. Feng, X. Jiang, Y. Li, and L. Zhao, Latent Dirichlet allocation (LDA) and topic modeling: models, applications, a survey. Multimedia Tools and Applications, 2019. 78(11): p. 15169-15211. 29. Devlin, J., M.-W. Chang, K. Lee, and K. Toutanova, Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805, 2018. 30. Xu, H., B. Liu, L. Shu, and Philip, BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis. arXiv pre-print server, 2019. 31. nlptown/bert-base-multilingual-uncased-sentiment [Online] Available: https://huggingface.co/nlptown/bert-base-multilingual-uncased-sentiment. 32. Su, X. and T.M. Khoshgoftaar, A survey of collaborative filtering techniques. Advances in artificial intelligence, 2009. 2009. 33. van der Maaten, L.J.P. t-Distributed Stochastic Neighbor Embedding [Online] Available: https://lvdmaaten.github.io/tsne/. 34. 蘇國賢, 〖作伙來想社會〗台灣人變得越來越孤獨？從社會網絡分析中，看見台灣近20年的社會變遷。. 台灣社會學會YouTube頻道。 Available: https://www.youtube.com/watch?v=LtksJhrT3Vc, 2021. 35. 張明宜、傅仰止, 社群媒體與大學生的網絡界限：伴遊圈、談話圈、接觸圈。. 台灣社會學，37，頁1-46。, 2019. 36. Lamont, M. and V. Molnár, The study of boundaries in the social sciences. Annual review of sociology, 2002. 28(1): p. 167-195. 37. Pollet, T.V., S.G. Roberts, and R.I. Dunbar, Extraverts have larger social network layers. Journal of Individual Differences, 2011. 38. Haerter, J.O., B. Jamtveit, and J. Mathiesen, Communication dynamics in finite capacity social networks. Physical review letters, 2012. 109(16): p. 168701. 39. Gonçalves, B., N. Perra, and A. Vespignani, Modeling users` activity on twitter networks: Validation of dunbar`s number. PloS one, 2011. 6(8): p. e22656. 40. Halpern, D., Social Capital (Cambridge: Polity). 2005. 41. Burt, R.S., From structural holes: The social structure of competition. The new economic sociology: a reader, 2004: p. 325-348. 42. Borgatti, S.P., Structural holes: Unpacking Burt’s redundancy measures. Connections, 1997. 20(1): p. 35-38. 43. Sievert, C. and K. Shirley. LDAvis: A method for visualizing and interpreting topics. in Proceedings of the workshop on interactive language learning, visualization, and interfaces. 2014. 44. Lund, A.M., Measuring usability with the use questionnaire12. Usability interface, 2001. 8(2): p. 3-6. zh_TW dc.identifier.doi (DOI) 10.6814/NCCU202200680 en_US
