1. NCCU Academic Hub
  2. 學術產出
  3. College of Informatics
  4. Theses
  5. Item

學術產出-Theses

Article View/Open

Publication Export

Google ScholarTM

政大圖書館

Citation Infomation

  • No doi shows Citation Infomation
題名 YouTube政治頻道異常使用者行為探勘
Detecting Abnormal User Behavior over YouTube Political Channels
作者 張恩慈
Chang, En-Cih
貢獻者 沈錳坤
Shan, Man-Kwan
張恩慈
Chang, En-Cih
關鍵詞 異常帳號
立場分析
時序探勘
共謀關係
日期 2023
上傳時間 1-Feb-2024 11:40:13 (UTC+8)
摘要 隨著社群媒體的日漸興盛，Facebook、Instagram、Twitter、Tiktok等社群軟體儼然成為人們日常生活中不可或缺的社交工具，其中YouTube更是全世界每日流量最高的影片串流平台。 社群平台進而成為行銷業者維持正面形象、提升曝光度的手段。政治勢力也開始在社群平台上宣傳政見和理念，尋求更廣泛的支持者。意想不到的後果是，社群媒體上不正常的活動漸漸萌芽，公關公司開始透過網軍，以人為的方式增加影片觀看次數、點讚、給予正面的評論及衝高頻道訂閱數，也運用經營的非真人帳號在文章或影片下留言，激起熱衷粉絲情緒性留言，也試圖帶動群眾意見風向。 近年來已陸續有社群平台異常帳號之研究。但YouTube與一般社群平台不同，影片內容不易分析，影片下方的留言討論不似一般社群平台即時且熱烈，且YouTube 站方沒有公開影片及留言按讚或按噓的帳號，提高了異常帳號分析的挑戰性。也因此現有YouTube 異常帳號的研究非常少，多數集中在色情暴力或盜版影片的偵測。 本研究旨在透過YouTube平台上公開顯示的欄位資訊，結合時間特徵值及社群帳號活動關聯性，提出異常帳號探勘的方法。本論文在大量政治相關頻道的評論樣本獲取使用者當中的隱含知識，並透過評論時間及獲得其他使用者之回饋，分析YouTube政治相關頻道立場及挖掘潛在的異常使用者同夥行為，作為政治頻道的生態探討。
參考文獻 [1] Aiyar, S., & Shetty, N. P. (2018). N-Gram Assisted Youtube Spam Comment Detection. International Conference on Computational Intelligence and Data Science (ICCIDS). Gurugram, India. [2] Alassad, M., Agarwal, N., & Hussain, M. N. (2019). Examining Intensive Groups in YouTube Commenter Networks. In Social, Cultural, and Behavioral Modeling. Washington, DC, USA: Springer. [3] Alberto, T. C., Lochter, J. V., & Almeida, T. A. (2015). TubeSpam: Comment Spam Filtering on YouTube. 14th International Conference on Machine Learning and Applications (ICMLA). Miami, FL, USA. [4] Alharbi, A., Dong, H., Yi, X., Tari, Z., & Khalil, I. (2021). Social Media Identity Deception Detection: A Survey. ACM Computing Surveys, Vol. 54, No. 3. [5] Bond, R. & Messing, S. (2015). Quantifying Social Media’s Political Space: Estimating Ideology from Publicly Revealed Preferences on Facebook. American Political Science Review, Vol. 109, No. 1. [6] Chowdury, R., Adnan, M. N., Mahmud, G. A., & Rahman, R. M. (2013). A Data Mining Based Spam Detection System for YouTube. Eighth International Conference on Digital Information Management (ICDIM). Islamabad, Pakistan. [7] Dutta, H. S., Jobanputra, M., Negi, H., & Chakraborty, T. (2021). Detecting and Analyzing Collusive Entities on YouTube. ACM Transactions on Intelligent Systems and Technology, Vol. 12, No. 5. [8] Ferrara, E., Varol, O., Davis, C., Menczer, F., & Flammini, A. (2016). The Rise of Social Bots. Communications of the ACM, Vol. 59, No. 7. [9] Hussain, M. N., Tokdemir, S., Agarwal , N., & Al-khateeb, S. (2018). Analyzing Disinformation and Crowd Manipulation Tactics on YouTube. IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM). Barcelona, Spain. [10] Kaushal, R., Saha, S., Bajaj, P., & Kumaraguru, P. (2016). KidsTube: Detection, Characterization and Analysis of Child Unsafe Content & Promoters on YouTube. 14th Annual Conference on Privacy, Security and Trust (PST). Auckland, New Zealand. [11] Korn, F., Labrinidis, A., Kotidis, Y., & Faloutsos C. (2000). Quantifiable Data Mining Using Ratio Rules. The VLDB Journal, Vol. 8. 78 [12] Singh, S., Kaushal, R., Buduru, A. B., & Kumaraguru, P. (2019). KidsGUARD: Fine Grained Approach for Child Unsafe Video Representation and Detection. Proceedings of the 34th ACM/SIGAPP Symposium on Applied Computing (SAC). Limassol, Cyprus. [13] Varol, O., Ferrara , E., Davis, C. A., Menczer, F., & Flammini, A. (2017). Online Human-Bot Interactions: Detection, Estimation, and Characterization. Proceedings of the International AAAI Conference on Web and Social Media. Proceedings of the International AAAI Conference on Web and Social Media. [14] Yusof, Y., & Sadoon, O. H. (2017). Detecting Video Spammers in YouTube Social Media. Proceedings of the 6 th International Conference on Computing and Informatics (ICOCI). Kuala Iumpur, Malaysia.
描述 碩士
國立政治大學
資訊科學系
109753109
資料來源 http://thesis.lib.nccu.edu.tw/record/#G0109753109
資料類型 thesis
dc.contributor.advisor 沈錳坤zh_TW
dc.contributor.advisor Shan, Man-Kwanen_US
dc.contributor.author (Authors) 張恩慈zh_TW
dc.contributor.author (Authors) Chang, En-Cihen_US
dc.creator (作者) 張恩慈zh_TW
dc.creator (作者) Chang, En-Cihen_US
dc.date (日期) 2023en_US
dc.date.accessioned 1-Feb-2024 11:40:13 (UTC+8)-
dc.date.available 1-Feb-2024 11:40:13 (UTC+8)-
dc.date.issued (上傳時間) 1-Feb-2024 11:40:13 (UTC+8)-
dc.identifier (Other Identifiers) G0109753109en_US
dc.identifier.uri (URI) https://nccur.lib.nccu.edu.tw/handle/140.119/149644-
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) 109753109zh_TW
dc.description.abstract (摘要) 隨著社群媒體的日漸興盛，Facebook、Instagram、Twitter、Tiktok等社群軟體儼然成為人們日常生活中不可或缺的社交工具，其中YouTube更是全世界每日流量最高的影片串流平台。 社群平台進而成為行銷業者維持正面形象、提升曝光度的手段。政治勢力也開始在社群平台上宣傳政見和理念，尋求更廣泛的支持者。意想不到的後果是，社群媒體上不正常的活動漸漸萌芽，公關公司開始透過網軍，以人為的方式增加影片觀看次數、點讚、給予正面的評論及衝高頻道訂閱數，也運用經營的非真人帳號在文章或影片下留言，激起熱衷粉絲情緒性留言，也試圖帶動群眾意見風向。 近年來已陸續有社群平台異常帳號之研究。但YouTube與一般社群平台不同，影片內容不易分析，影片下方的留言討論不似一般社群平台即時且熱烈，且YouTube 站方沒有公開影片及留言按讚或按噓的帳號，提高了異常帳號分析的挑戰性。也因此現有YouTube 異常帳號的研究非常少，多數集中在色情暴力或盜版影片的偵測。 本研究旨在透過YouTube平台上公開顯示的欄位資訊，結合時間特徵值及社群帳號活動關聯性，提出異常帳號探勘的方法。本論文在大量政治相關頻道的評論樣本獲取使用者當中的隱含知識，並透過評論時間及獲得其他使用者之回饋，分析YouTube政治相關頻道立場及挖掘潛在的異常使用者同夥行為，作為政治頻道的生態探討。zh_TW
dc.description.tableofcontents 第一章 前言 6 1.1 研究背景 6 1.2 研究動機與目的 8 第二章 相關研究 11 2.1 兒童不宜內容偵測 (Child Unsafe Content Detection) 12 2.2 垃圾影片偵測 (Video Spam Detection) 13 2.3 垃圾評論偵測 (Comment Spam Detection) 13 2.4 惡意使用者偵測 (Malicious User Detection) 14 第三章 研究方法 16 3.1 研究架構 16 3.2 資料類型 16 3.3 異常帳號在社群媒體上的行為特徵 17 3.4 政治立場分析 (Polarity Identification) 18 3.5 時序關係探勘(Temporal Relationship Discovery) 23 3.6 共謀關係探勘 (Collusive Relationship Discovery) 27 第四章 實驗設計與結果分析 30 4.1 資料蒐集 30 4.2 實驗設計與評估方法 35 4.3 實驗結果 37 4.3.1政治立場分析(Polarity Identification) 37 4.3.2活動行為分析(User Behaviour Analysis) 50 第五章 結論與未來研究 76 參考文獻 77zh_TW
dc.format.extent 3680602 bytes-
dc.format.mimetype application/pdf-
dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0109753109en_US
dc.subject (關鍵詞) 異常帳號zh_TW
dc.subject (關鍵詞) 立場分析zh_TW
dc.subject (關鍵詞) 時序探勘zh_TW
dc.subject (關鍵詞) 共謀關係zh_TW
dc.title (題名) YouTube政治頻道異常使用者行為探勘zh_TW
dc.title (題名) Detecting Abnormal User Behavior over YouTube Political Channelsen_US
dc.type (資料類型) thesisen_US
dc.relation.reference (參考文獻) [1] Aiyar, S., & Shetty, N. P. (2018). N-Gram Assisted Youtube Spam Comment Detection. International Conference on Computational Intelligence and Data Science (ICCIDS). Gurugram, India. [2] Alassad, M., Agarwal, N., & Hussain, M. N. (2019). Examining Intensive Groups in YouTube Commenter Networks. In Social, Cultural, and Behavioral Modeling. Washington, DC, USA: Springer. [3] Alberto, T. C., Lochter, J. V., & Almeida, T. A. (2015). TubeSpam: Comment Spam Filtering on YouTube. 14th International Conference on Machine Learning and Applications (ICMLA). Miami, FL, USA. [4] Alharbi, A., Dong, H., Yi, X., Tari, Z., & Khalil, I. (2021). Social Media Identity Deception Detection: A Survey. ACM Computing Surveys, Vol. 54, No. 3. [5] Bond, R. & Messing, S. (2015). Quantifying Social Media’s Political Space: Estimating Ideology from Publicly Revealed Preferences on Facebook. American Political Science Review, Vol. 109, No. 1. [6] Chowdury, R., Adnan, M. N., Mahmud, G. A., & Rahman, R. M. (2013). A Data Mining Based Spam Detection System for YouTube. Eighth International Conference on Digital Information Management (ICDIM). Islamabad, Pakistan. [7] Dutta, H. S., Jobanputra, M., Negi, H., & Chakraborty, T. (2021). Detecting and Analyzing Collusive Entities on YouTube. ACM Transactions on Intelligent Systems and Technology, Vol. 12, No. 5. [8] Ferrara, E., Varol, O., Davis, C., Menczer, F., & Flammini, A. (2016). The Rise of Social Bots. Communications of the ACM, Vol. 59, No. 7. [9] Hussain, M. N., Tokdemir, S., Agarwal , N., & Al-khateeb, S. (2018). Analyzing Disinformation and Crowd Manipulation Tactics on YouTube. IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM). Barcelona, Spain. [10] Kaushal, R., Saha, S., Bajaj, P., & Kumaraguru, P. (2016). KidsTube: Detection, Characterization and Analysis of Child Unsafe Content & Promoters on YouTube. 14th Annual Conference on Privacy, Security and Trust (PST). Auckland, New Zealand. [11] Korn, F., Labrinidis, A., Kotidis, Y., & Faloutsos C. (2000). Quantifiable Data Mining Using Ratio Rules. The VLDB Journal, Vol. 8. 78 [12] Singh, S., Kaushal, R., Buduru, A. B., & Kumaraguru, P. (2019). KidsGUARD: Fine Grained Approach for Child Unsafe Video Representation and Detection. Proceedings of the 34th ACM/SIGAPP Symposium on Applied Computing (SAC). Limassol, Cyprus. [13] Varol, O., Ferrara , E., Davis, C. A., Menczer, F., & Flammini, A. (2017). Online Human-Bot Interactions: Detection, Estimation, and Characterization. Proceedings of the International AAAI Conference on Web and Social Media. Proceedings of the International AAAI Conference on Web and Social Media. [14] Yusof, Y., & Sadoon, O. H. (2017). Detecting Video Spammers in YouTube Social Media. Proceedings of the 6 th International Conference on Computing and Informatics (ICOCI). Kuala Iumpur, Malaysia.zh_TW