Content Analysis of Twitter Data related to Trust and Covid-19

This is a public repository of the ongoing research work on ‘Content Analysis of Twitter Data related to Trust and Covid-19’ . For accessing the live streams of tweets , for downloading the existing tweets (hydration) based on the filters and for dehydrating the tweeter data twac tool, twitter api , tweepy libraries were utilized. The python code consists of two notebooks for the said purposes. it includes Master Data (Tweeter Data ) notebook having data cleaning function.The cleaning of the tweeter data include removal of emojis, unwanted characters and symbols , image links and other unwanted objects.本公开代码仓库对应一项持续推进的研究工作，该研究围绕「与信任及新冠疫情（COVID-19）相关的推特（Twitter）数据内容分析」展开。为实现推特实时数据流获取、基于筛选条件下载现有推文（水化（hydration））以及对推特数据进行反水化操作，本项目采用了twac工具、推特API（Twitter API）以及Tweepy库。本项目的Python代码包含两个适配上述需求的Jupyter笔记本（notebook），其中「主数据（推特数据）」笔记本内置了数据清洗模块，该流程涵盖表情符号、无效字符与符号、图片链接及其他无关内容的移除操作。