Dataset

text -> Original tweet text, as downloaded trough the Twitter APItext_final -> Text after cleanup, as used for lexicon matchinghour -> Date and time (only hour) at which the tweet was publishedtime_cat -> Dummy. Whether the tweet was published during the event [“cuenta”] or before/after the event [“no_cuenta”]rt_count -> Number of retweets at the moment of the download of the dataurl -> Dummy. The tweet text includes a urlmedia -> Dummy. The tweet had photo or videoEmoWord -> Total number of matches for emotional words or stems in the tweet textMoralWord -> Total number of matches for moral words or stems in the tweet textEmoMoralWord -> Total number of matches for both moral and emotional words or stems in the tweet textOnlyEmoWord -> Number of matches for emotional words or stems in tweet text (excluding those which also matched moral words or stems)OnlyMoralWord -> Number of matches for moral words or stems in tweet text (excluding those which also matched emotional words or stems)foll_div10 -> Number of followers of the account that published the tweet at the moment of the data download, divided by 10,000

text：原始推文文本，即通过推特API（Twitter API）下载得到的推文原文
text_final：经过清洗处理后的文本，用于词典匹配任务
hour：推文发布的日期与时间（仅保留小时维度）
time_cat：虚拟变量（Dummy），用于标记推文发布时段：属于事件时段["cuenta"]或事件前后时段["no_cuenta"]
rt_count：数据下载时刻该推文的转发次数
url：虚拟变量（Dummy），用于标记推文文本是否包含链接
media：虚拟变量（Dummy），用于标记推文是否包含图片或视频内容
EmoWord：推文文本中情感词汇或词干的匹配总次数
MoralWord：推文文本中道德词汇或词干的匹配总次数
EmoMoralWord：推文文本中同时匹配情感与道德词汇或词干的总次数
OnlyEmoWord：推文文本中仅匹配情感词汇或词干（排除同时匹配道德词汇的情况）的次数
OnlyMoralWord：推文文本中仅匹配道德词汇或词干（排除同时匹配情感词汇的情况）的次数
foll_div10：数据下载时刻发布该推文的账号的粉丝数，除以10000后的结果