Questions from iFixit Answers Forum

This data contains 7,760 questions from iFixit's online question and answer forum, Answers, as well as user and textual features for each question. Data was used in a survival analysis of the time until a question posted on Answers forum received its first answer. A Cox proportional hazards model was developed to predict the survival probability of posted questions, as well as to identify variables associated with question response time. Variables found to be significantly associated with response time included: the device category the question pertains to, if the question was posted on a weekday or weekend, whether or not the question's title contained at least one term considered frequently-used among unanswered questions, and whether or not the question's title ended in a question mark. The additional file, data_key.csv, contains a description of each variable, as well as a column indicating if the variable was part of the original data or derived.

本数据集包含来自iFixit旗下在线问答社区Answers的7760条问题，以及每条问题对应的用户特征与文本特征。本数据集被用于对Answers社区中发布的问题直至获得首个回复的时长开展生存分析。研究构建了Cox比例风险模型（Cox proportional hazards model），用于预测已发布问题的生存概率，并识别与问题回复时长相关的变量。经检验，与回复时长显著相关的变量包括：问题所属的设备类别、问题发布时间为工作日还是周末、问题标题是否包含至少一个在未回复问题中高频出现的术语，以及问题标题是否以问号结尾。附加文件data_key.csv包含各变量的详细说明，以及一列用于标识该变量属于原始数据集还是衍生特征。