Select Language

AI社区

公开数据集

印度政治推文 2019 (2 月到 5 月)

印度政治推文 2019 (2 月到 5 月)

28.81M
163 浏览
0 喜欢
0 次下载
0 条讨论
Internet,Universities and Colleges,Politics,India Classification

数据结构 ? 28.81M

    Data Structure ?

    * 以上分析是由系统提取分析形成的结果,具体实际数据为准。

    README.md

    Motivation Analytics has been the buzz word of the current decade. I wanted to see how Twitter data can give insights about what people are talking about the Indian political parties and their leaders. And hence began the journey of collecting tweets from 14th Feb (didn't have much to do on that day). Data The total data collected from 14 Feb to 16th May summed up to a humongous 1.4 TB. This data was collected on my Azure servers and then later transferred to my organization's big data cluster. Due to other work commitments, I started processing the data very late on 20th May. With under 3 days to generate insights before election results on 23 May, we were left with no option other than taking a sample of the data. Hence we selected the tweets between 11PM to 12AM and code-named the analysis as 11th-hour analysis. **Note - The data is using pipe (|) as the delimiter. ** Predictions before results There are 29 States and 7 UT in India out of which 5 UTs had very less data (less than 15 tweets). Considering the remaining 31 States/UTs, we were correct in predicting the winning party edge for 24 States/UTs. Future score We are planning a much more comprehensive analysis using the full 1.4 TB data. The future case studies can give time-dependent insights or rebuttals to wild accusations like EVM tampering. Acknowledgements I work as a consultant Data Scientist and Academic Trainer at INSOFE. The data was processed on INSOFE's big data cluster using PySpark. If you are looking to get a headstart in the Data Science domain, do checkout [INSOFE's PGP program in Data Science](https://www.insofe.edu.in/) (6 months weekend delivery at Banglore, Hyderabad and Mumbai) Support Me I had to buy Azure servers and spend hours writing code and maintaining the server jobs for collecting the data. If you're interested in availing my data science services or purchasing the whole data and willing to sponsor or support me, please do reach-out on [LinkedIn](https://www.linkedin.com/in/codesagar/) or drop a mail at sagarpatel(dot)exe(at)gmail(dot)com [Support me on Patreon](https://www.patreon.com/codesagar)
    ×

    帕依提提提温馨提示

    该数据集正在整理中,为您准备了其他渠道,请您使用

    注:部分数据正在处理中,未能直接提供下载,还请大家理解和支持。
    暂无相关内容。
    暂无相关内容。
    • 分享你的想法
    去分享你的想法~~

    全部内容

      欢迎交流分享
      开始分享您的观点和意见,和大家一起交流分享.
    所需积分:0 去赚积分?
    • 163浏览
    • 0下载
    • 0点赞
    • 收藏
    • 分享