黃寶儀Huang, Polly臺灣大學:電機工程學研究所黃得源Huang, Te-YuanTe-YuanHuang2010-07-012018-07-062010-07-012018-07-062008U0001-0108200814184900http://ntur.lib.ntu.edu.tw//handle/246246/187931如何量化網際網路使用者對於服務的滿意度，一直是網際網路服務提供者所重視的課題。藉由瞭解使用者的滿意度，服務提供者可以據此改善其服務品質。在本研究中，我們提出了可通用於各項網路服務的統計方法—將存活分析 (Survival Analysis)應用於使用者使用該服務的時間長度 (Session Time)—並據此量化使用者滿意度。和問卷調查比較起來，本方法只需用到被動式的網路效能量測 (passive measurement)，因此擁有較高的成本效益，同時也能較有效的將潛意識反應納入量測範圍之內。再者，利用使用服務的時間長度，可以將各式影響使用者滿意度的因子都納入考量。反觀，若是使用特定的滿意度指標來量化使用者滿意度，例如：網路電話傳輸聲音的失真度；則勢必無法將其他指標，例如：聲音大小、回音等等，一起納入考量。由於存活分析是一種計算複雜度低的數學模型建構法，因此本方法的計算成本亦低。在本論文中，我們將此演算法應用在『神州 Online』—一款在台灣上市的大型多人線上角色扮演遊戲，以及『Skype』—目前世界上使用人數最多的網路語音電話系統。同時，利用本方法，我們也可以在數學模型的建構過程當中，瞭解在不同的服務中，哪一些因素最為使用者所重視，並討論這些資訊該怎麼樣的被解讀及應用，以用來提升用戶體驗及改善服務提供者的資源配置。Quantifying user satisfaction is essential, because the results can help service providers deliver better services. In this work, we propose a generalizable methodology, based on survival analysis, to quantify user satisfaction in terms of session times, i.e., the length of time users stay with an application. Unlike subjective human surveys, our methodology is based solely on passive measurement, which is more cost-efficient and better able to capture subconscious reactions. Furthermore, by using session times, rather than a specific performance indicator, such as the level of distortion of voice signals, the effects of other factors like loudness and sidetone, can also be captured by the developed models. Like survival analysis, our methodology is characterized by low complexity and a simple model-developing process. The feasibility of our methodology is demonstrated through case studies of ShenZhou Online, a commercial MMORPG in Taiwan, and the most prevalent VoIP application in the world, namely Skype. Through the model development process, we can also identify the most significant performance factors and their impacts on user satisfaction and discuss how they can be exploited to improve user experience and optimize resource allocation.誌謝 ii要 ... iiibstract ... vist of Figures ... ixhapter 1 Introduction ... 1hapter 2 RelatedWork ... 4.1 Subjective Evaluation ...4.2 Objective Evaluation ... 6hapter 3 Methodology ... 7.1 Survival Analysis ... 8.2 Regression Modeling ...11.2.1 The Cox Regression Model ... 11.2.2 Proportional Hazards Check and Adjustment ... 12.2.3 Model Validation ...14hapter 4 Case Study ... 16.1 Online Game ... 16.1.1 Performance Factor Identification ... 17.1.2 Impact of Individual Factors ...19.1.3 Findings and Discussion ...21.2 VoIP ... 22.2.1 Performance Factor Identification ... 23.2.2 Impact of Individual Factors ... 25.2.3 Findings and Discussion ... 26hapter 5 Application ... 28hapter 6 Conclusion ... 30ibliography ... 31640650 bytesapplication/pdfen-US人類感官感受網路量測服務品質存活分析網路遊戲網路語音電話Human PerceptionInternet MeasurementQuality of ServiceSurvival AnalysisNetwork GamesVoIPthesishttp://ntur.lib.ntu.edu.tw/bitstream/246246/187931/1/ntu-97-R95921037-1.pdf