網際網路與社群媒體的發達，造就人人隨時隨地上網打卡分享心情與狀態。然而凡事都有兩面，社群媒體除了帶來人們的喜悅，也讓些許人遭受霸凌煎熬。本研究希望透過Instagram社群媒體上的使用者文章，預測該使用者是否遭受網路霸凌。首先，本研究根據文獻探討的結果，提出研究架構。研究架構分為兩大階段：一、利用程式搜集主題標籤文章，再運用自然語言技術建立主題詞庫；二、統計問卷標記實際人格特質，並利用使用者的發文及人格特質詞庫，來判斷使用者的人格特質。再以實際人格特質，驗證根據發文判斷人格特質的準確性。最後，利用人格特質屬性來預測使用者是否遭受網路霸凌。本研究包含三大貢獻：一、透過主題式標籤能建立主題詞庫；二、運用使用者文章判斷使用者的人格特質；三、預測使用者是否被霸凌。實驗結果顯示預測被霸凌的精準度為0.8，F-measure值為0.727。

Due to popularity of the Internet and social media, people are eager to share their thoughts and feelings through the social media. However, the social media is a double-edged sword; it not only brought joys to the public for information sharing, it also brought agony to the public through cyber bullying. This research aims at identifying people who are suffering from cyber bullying by screening their posts on Instagram. To this end, we have built thesauruses for different personality traits. Then, we identified a user's personality trait by matching the contents of his posts on Instagram and the thesauruses, and used the personality trait to predict the possibility for the user being cyber bullied. The whole process has been performed in two steps. In the first step, we built four thesauruses according to the Big Five model and the posts on Instagram. Then, we conducted a survey by issuing questionnaires to the users of Instagram to collect a training dataset. The training dataset contains the personality traits and the yes's or no's for the users being cyber bullied. We used the training dataset to verify the accuracy on predicting a user's personality trait and to build a prediction model for cyber bullying. The contribution of this thesis includes (1) to use the posts in Hashtags and the Big Five model to construct thesauruses for personality traits, (2) to use the posts of a user to predict the user's personality trait, and (3) to use the predicted personality trait and other related attributes to predict whether or not a user is being cyber bullied. The experimental results showed that the precision and the F-Measure of the prediction are 0.8 and 0.727, respectively.

[1]Banks, R. (2015, June 29). Apps that changed the world: Instagram. Retrieved from http://www.mobileindustryreview.com/2015/06/apps-that-changed-the-world-instagram.html
[2]Eriko Otsuka, S. A. (2014, July). Design and Evaluation of a Twitter Hashtag Recommendation System. Proceedings of the 18th International Database Engineering & Applications Symposium.
[3]Lunden, I. (2014, November 25). Tumblr Overtakes Instagram As Fastest-Growing Social Platform, Snapchat Is The Fastest-Growing App. Retrieved from https://techcrunch.com/2014/11/25/tumblr-overtakes-instagram-as-fastest-growing-social-platform-snapchat-is-the-fastest-growing-app/
[4]TF-IDF - 維基百科，自由的百科全書. Retrieved from https://zh.wikipedia.org/wiki/TF-IDF
[5]Top Websites jun 2016 Social Network, Taiwan. (2016, June). (SimilarWeb.com) Retrieved from www.similarweb.com
[6]Wayne Xin Zhao, J. J.-P. (2011). Comparing Twitter and Traditional Media using Topic Models. European Conference on Information Retrieval . Ireland.
[7]王智弘. (2006). 解讀網路現象談關懷青少年的壓力調適. Retrieved from http://wang.heart.net.tw/paper-new/paper2006c.htm
[8]吳為恭. (2010, 4月). ＜學者看法＞網路訴苦 宣洩情緒出口. Retrieved from http://www.epochtimes.com/b5/10/4/24/n2886541.htm
[9]李長燦, 王. (2011). 五大人格特質量表中文版的信孝度研究. 2011社會服務與休閒產業研討會. 屏東縣.
[10]兒童福利聯盟. 2016年台灣兒少網路霸凌經驗調查報告.
[11]陳思雅. (2010, 1月). 《逾萬網誌 揭青年情緒受困》. 香港: 文匯報.
[12]陳茵嵐, 劉. (2011). e 世代的攻擊行為：網路霸凌（Cyber-Bullying）.
[13]曾元顯. (2012,10月). cosine similarity - 餘絃相似度. Retrieved from http://terms.naer.edu.tw/detail/1679004/
[14]黃郁欣. (2016,2月). 社群網站Instagram – 使用行為調查. Retrieved from http://www.ixresearch.com/news/news_02_05_16
[15]楊琬如. (2010). 人格特質、性別及學習成就對國小學童師生互動關係滿意度之研究. 國立政治大學教育學系碩士論文.
[16]楊德倫. (2014,12月). 文字探勘之前處理與TF-IDF介紹. Retrieved from http://www.cc.ntu.edu.tw/chinese/epaper/0031/20141220_3103.html
[17]蔡順良. (2006). 人格心理學基本概念（950227) . Retrieved from http://web.ntnu.edu.tw/~t05022/index.html/%E4%BA%BA%E6%A0%BC%E5%BF%83%E7%90%86%E5%AD%B8%E8%AC%9B%E7%BE%A9(950618%E4%BF%AE%E8%A8%82)/%E4%BA%BA%E6%A0%BC%E5%BF%83%E7%90%86%E5%AD%B8%E5%9F%BA%E6%9C%AC%E6%A6%82%E5%BF%B5%EF%BC%88950227).ppt
[18]薛秀宜, 陳. 洪. (2006). 人格理論新紀元：人格五因素模式之測驗工具與其研究應用.
[19]魏希聖、李致中與王宛雯. (2006). 高中職學生網路成癮之危險因子與偏差行為研究：以臺中縣霧峰大里地區為例. 臺中教育大學學報：教育類, pp. 89-105.