應用決策樹於YouTube影片受歡迎程度之分析

Applying Decision Trees to Explore the Popularity of Videos in YouTube

劉丁魁(Ting-Kuei Liu)

指導教授 ： 白炳豐

國立暨南國際大學/管理學院/高階經營管理碩士學位學程/碩士(2018年)

摘要

摘要
在行動網路及智慧型手機蓬勃發展的現在，越來越多人可隨時隨地的上網，網路逐漸成為生活之中不可或缺的一部分。因此許多決策者仰賴網路所蒐集到的大量數據來進行分析及研究，以輔助或修正決策的方向。
而為了迎接網路時代，廠商漸漸地將廣告重心從傳統媒體(如：報紙、電視)轉移到網路平台。在眾多網路平台之中，YouTube所產生的效益備受肯定。
YouTube藉由大量的影片吸引觀眾群，將廣告與影片做結合以提升效益，並將廣告部分收益與影片創作者共同分享，藉此鼓勵創作者持續製作並上傳影片，成為一個良性的循環，促使YouTube快速成長，吸引更多廠商在YouTube平台上投放廣告。
現今成為YouTuber已經成為很多新一代年輕人的目標，但是不知道應該如何做才會受歡迎，因此研究YouTube上受歡迎的影片，希望給目標是YouTuber的人或是已經是YouTuber的人一些參考，希望本研究可以讓他們更加的受到歡迎。
本論文為研究YouTube頻道，希望從中找到規律，分析何種影片會受歡迎、觀看次數較多。下載觀眾以使用中文為主的頻道，將頻道內的所有的影片資料下載下來，然後再以決策樹分析，希望找出受歡迎影片的規律。

關鍵字

YouTube ； 決策樹 ； C4.5 ； Random Committee ； 歡迎

並列摘要

Abstract
With the booming development of mobile networks and smart phones, people can access the Internet everywhere. Gradually, the Internet becomes an integral part of life of people. Many decision makers rely on the analysis and research of big number of data searched from internet to assist or correct the direction of strategy.
Along with the raise of Internet generation, companies gradually shift their advertising focus from traditional media (such as newspapers and television) to Internet platforms. Among many Internet platforms, YouTube is acknowledged by its benefit.
YouTube attracts audiences by using large amounts of videos. To enhance the benefit, YouTube combines the videos with advertising and share the revenue with YouTubers. This sharing strategy increases the willing of YouTuber to produce and upload the videos continuously which leads to a positive cycle and rapid growth. Besides, more and more companies are also attracted by its beneficial result and start advertising on YouTube.
Nowadays becoming a YouTuber is a goal of the young generation. This study aims to analyze popular videos in YouTube for finding out the regular pattern which increases the probability of catching more attentions. To achieve the objective of this paper, the study collected video data in Chinese channels and analyzed the collected data by decision trees.

並列關鍵字

YouTube ； Decision Trees ； C4.5 ； Random Committee ； Popular

參考文獻

參考文獻

一、英文部分

[1] Eibe Frank, Mark A. Hall, and Ian H. Witten (2016). The WEKA Workbench. Online Appendix for "Data Mining: Practical Machine Learning Tools and Techniques", Morgan Kaufmann, Fourth Edition, 2016.

[2] Mark Hall, Eibe Frank, Geoffrey Holmes, Bernhard Pfahringer, Peter Reutemann, and Ian H. Witten (2009). The WEKA Data Mining Software: An Update. SIGKDD Explorations, Volume 11, Issue 1.

[3] Remco R. Bouckaert,Eibe Frank,Mark Hall,Richard Kirkby,Peter Reutemann,Alex Seewald, and David Scuse (2017),WEKA Manual for Version 3-8-2, Retrieved from http://prdownloads.sourceforge.net/weka/WekaManual-3-8-2.pdf