技术控

    今日:0| 主题:63445
收藏本版 (1)
最新软件应用技术尽在掌握

[其他] Know your followers with Machine Learning

[复制链接]
安静地在你身边. 发表于 2016-10-5 01:33:36
148 0
Tell me who your followers are and I tell you who you are.
  You have lots of followers, congrats! You’re popular, maybe an influencer. But, do you actually know who’s following you?
  If you have thousands of followers, that could be a tricky question to answer. Let’s use Machine Learning to try to answer that question.
  MonkeyLearn’s Twitter account as today (Oct 4th, 2016), has almost 20,000 followers. It would be great to know which kind of people follows us, knowing more about their interests, who they are, what they do, and try to figure out why they follow us. That could give us useful insights about our user base and product.
  We quickly used Twitter’s public API to download the bios of all of our followers. You can take a look at the          Pythonscript here    . In order to use it, you’ll need to get your    API tokens.  
  We stored all the data in a simple CSV file. First column:    user handle, second column:    user bio. Like this:  
                              edp3rez          Actively seeking to become wiser every day and attract people with a similar mindset so we can find ways to build a new world. Is that you?                          FintechArticle          Fintech Articles and News Analysis from around the web                          jahangeerbaluch          Computer Scientist                          MFENOGLIO          Don’t forget to stop and have fun from time to time . Si luchas por lo que realmente quieres vendra a ti. A buenas el mejor                          michaelyoungMBN          Founder/CEO @ https://t.co/vduvBZ6wHZ @mbnsolutions – Managing Partner @ https://t.co/OYk3xwFeyn @mbnconsilium – Founder of @DataSciTechScot                          brolouiemd          fashionate seasonal web developer, wordpress developer                          vexipoloxozo          Tнe 2015 Sαle ιѕ нere! yoυ cαɴ ɴow вυy 50,000 Twιттer Followerѕ ғor oɴly $146, Try ιт ɴow! αт https://t.co/pB6BOGQx3T                          PetroSemeniuk          Developer. Developer. Developer.                          SaurabhIAm          I am a Techno Freak, A Computer Science Geek, App. Developer, A Web Developer, A Kickass Gamer, and A Painting Artist!                          krkdev          Developer and Debugger                      Then we wrote a    simple      Pythoncommand    to read and concatenate all the bios of our users into a text variable and send it to ourKeyword Extractor module in MonkeyLearn.  
  You can execute the command like this:
      python    keywords_csv    .py    -    s    4000    -    c    1    -    k    100    -    t    <    YOUR    TOKEN    HERE    >    followers_bios    .csv  
  Where:
  -soption sets the    max number of rows(bios) to use. I suggest to limit to the last 4,000 samples, too much of them would take a lot of time to process.  
  -coption sets the    column number(starting on 0) where the bios are located in the CSV file.  
  -koption sets the    max number of keywordsto return.  
  -toption sets your    MonkeyLearn API token.  
  And lastly, the    followers_bios.csvis the    CSV filewhere you stored the bios.  
  The keywords returned will be sorted according to their relevance within the texts.
  You can even try to do the same process just copying and pasting the texts within MonkeyLearn’s GUI, just go to theAPI section. This will limit just to the top 10 keywords.  
  Results

  And the results for the top 100 keywords associated with MonkeyLearn’s followers are:
                              1-25                          26-50                          51-75                          76-100                                      Developer

          Python

          Machine Learning

          Tweets

          Marketing

          Web Developer

          Big Data

          Data Science

          Designer

          Data

          startups

          software developer

          Engineer

          Software

          Entrepreneur

          Web

          Analytics

          Technology

          Consultant

          Social Media

          tech

          Opinions

          enthusiast

          app developer

          Artificial Intelligence

                          Business

          Computer

          geek

          Manager

          views

          lover

          research

          innovation

          Programmer

          Founder

          music lover

          Natural Language Processing

          love

          Blogger

          Learning

          Java

          Interests

          graphic design

          digital marketing

          PHP

          Science

          world

          JavaScript

          Dev

          game developer

                          Business Developer

          fan

          life

          photographer

          companies

          student

          CTO

          music

          Scientist

          Product Manager

          open source

          Cloud

          Speaker

          CEO

          Analyst

          customers

          Linux

          app

          Mobile App Developer

          passion

          Android

          people

          mobile app

          Software Engineer

          Project Manager

                          Gamer

          Brand

          Travel

          Strategy

          things

          Network

          Product

          services

          Natural language

          Market Research

          Data Scientist

          Mobile Developer

          Business Intelligence

          writer

          Sci

          Creator

          father

          Author

          solutions

          SEO

          programming

          Coder

          endorsements

          Twitter

          Expert

                      Insights

  That’s great! Definitively what we wanted to see, but we also found some interesting insights:
  
       
  • Strong popularity within      Developers, we have keywords like       Developer, Web Developer, Software Developer, Engineer, App Developer, Programmer, Game developer, Mobile App Developer, Software Engineer, Data Scientist, Mobile Developer, Coder.  
  
       
  • Strong popularity within people in the      Data Science and      Technology space:      Machine Learning, Big Data, Data Science, Data, Analytics, Technology, Artificial Intelligence, Research, Innovation, Science, Natural Language Processing, Programming.  
  
       
  • Some      Other       Titles arose, which are very interesting besides the      Developerand      Data Scientist, all of them very related to the startup world:      Designer, Entrepreneur, Consultant, Manager, Founder, Blogger, Business Developer, Photographer, Student, CTO, Product Manager, Scientist, Speaker, CEO, Analyst, Project Manager, Writer, Author.  
  
       
  • Some      Technologies:      Python, Java, PHP, Javascript, Open Source, Cloud, Linux, Android.  
  
       
  •       Non-tech disciplineswhich have been growing a lot in our community and we plan to give more tools:      Marketing, Startups, Social Media, Business, Graphic Design, Digital Marketing, Music, Market Research, Business Intelligence, SEO.  
  
       
  •       Personal characteristicswhich clearly denote that we have very enthusiastic and geeky followers:      enthusiast, geek, lover, music lover, love, fan, life, passion, creator, father, expert.  
  Hope you enjoyed this quick post, I’d love to know your own insights with your followers!
我要投稿

推荐阅读


回页顶回复上一篇下一篇回列表
手机版/c.CoLaBug.com ( 粤ICP备05003221号 | 粤公网安备 44010402000842号 )

© 2001-2017 Comsenz Inc.

返回顶部 返回列表