Instrumented Digital and Paper Reading (dataset)

THE PRESENT DATASET CONTAINS THREE FOLDERS: i. DEMOGRAPHIC AND ANNOTATION DATASET: this .xlsx spreadsheet contains the relevant demographic data for all 25 participants in our study. Also, it includes the participant evaluation for every paragraph read during our experiment for three factors: Interest, Attentiveness and Effort. Those values are important to correlate with the Flesch–Kincaid readability score. Please refer to the paper for more details. ii. EXPERIMENT DATASET: the folder contains all the data collected during our experiments. There were 25 participants, each one with the data obtained during 16 readings in our tests, organised in consecutive folders. Each folder contains the data generated through the readings of two apparatus used in our study, an Eye-tracking and an EEG helmet. Video feed has not been included as the dataset is anonymised. iii. OPENFACE DATASET: this folder includes, amongst other data, the HOG files obtained through the processing of the participant's videos, (not included) using OpenFace, a Python and Torch implementation of face recognition with deep neural networks (https://cmusatyalab.github.io/openface/#openface). The histogram of oriented gradients (HOG) is a feature descriptor used in computer vision and image processing for the purpose of object detection.

本数据集包含三个文件夹：
i. 人口统计与标注数据集（DEMOGRAPHIC AND ANNOTATION DATASET）：该.xlsx电子表格收录了本研究全部25名参与者的相关人口统计数据。此外，其还涵盖了参与者在实验过程中阅读每一段落时，针对三项指标的评价结果：兴趣度、专注度与投入程度。这些数值可用于与弗莱施-金凯德可读性评分（Flesch–Kincaid readability score）开展关联分析，更多细节请参阅相关研究论文。
ii. 实验数据集（EXPERIMENT DATASET）：该文件夹包含实验全程采集的全部数据。本研究共招募25名参与者，每位参与者在测试中完成16次阅读任务所获得的数据，均整理至连续命名的子文件夹中。每个子文件夹包含本研究使用的两种设备采集的阅读相关数据：眼动仪与脑电图（EEG）头盔。由于本数据集已完成匿名化处理，故未收录视频画面。
iii. OpenFace数据集（OPENFACE DATASET）：该文件夹包含通过OpenFace处理参与者视频（未纳入本数据集）所得到的方向梯度直方图（Histogram of Oriented Gradients，简称HOG）等多种数据。OpenFace是一款基于Python与Torch实现、采用深度神经网络进行人脸识别的工具（https://cmusatyalab.github.io/openface/#openface）。方向梯度直方图是计算机视觉与图像处理领域用于目标检测的特征描述符。