基於眼動軌跡之閱讀模式分析

• Main Authors: 張晉文, Chang, Chin Wen
• Language: 中文
• Published: 國立政治大學
• Subjects: 眼動資料; 閱讀模式; 眼動儀; 交叉驗證; Eye movement; Reading pattern; Eye tracker; Cross-validation
• Online Access: http://thesis.lib.nccu.edu.tw/cgi-bin/cdrfb3/gsweb.cgi?o=dstdcdr&i=sid=%22G0102971021%22.

閱讀是吸收知識的途徑，不同的閱讀模式所帶來的閱讀成效也會不同。如何透過機器學習的方式，從凝視點找出閱讀行為的關聯性，將是本研究的目標。實驗選擇低成本眼動儀紀錄讀者閱讀過程中的眼動資料，採用dispersion-based演算法找出凝視點，以計算凝視點特徵，包含凝視時間、凝視距離、凝視位置以及凝視方向。 本研究將閱讀模式分成五種類別，包含快讀、慢讀、精讀、跳讀與關鍵字識別，透過不同文章的呈現，引導30位測試者遵循其內容進行閱讀，藉此收集不同行為模式的眼動資料。實驗流程中所有的眼動資料會隨機被分成為兩份，依序建立不同維度的訓練資料，由交叉驗證的分類結果找出理想之特徵與維度。以每次挑選6位測試者的眼動數據為測試資料進行5次分類驗證，其平均正確率為78.24%、74.19%、93.75%、87.96%以及96.20%，均達到不錯的分類結果。 === Reading is one of the paths to acquire knowledge. The efficiency is different when different reading patterns are involved. It is the objective of this research to classify reading patterns from fixation data using machine learning techniques. In our experiment, a low-cost eye tracker is employed to record the eye movements during the reading process. A dispersion-based algorithm is implemented to identify fixation from the recorded data. Features pertaining to fixation including duration, path length, landing position and fixation direction are extracted for classification purposes. Five categories of reading pattern are defined and investigated in this study, namely, speed reading, slow reading, in-depth reading, skim-and-skip, and keyword spotting. We have recruited thirty subjects to participate in our experiment. The participants are instructed to read different articles using specific styles designated by the experimenter in order to assign label to the collected data. Feature selection is achieved by analyzing the predictive results of cross-validation from the training data obtained from all subjects. The average classification accuracies in five-fold cross-validation are 78.24%, 74.19%, 93.75%, 87.96% and 96.20% using the eye movements of the six randomly selected subjects as test data.