No announcement yet.

Summary of Analysis of OPT Comments received

  • Filter
  • Time
  • Show
Clear All
new posts

  • Summary of Analysis of OPT Comments received

    Here are the steps I followed to obtain my results

    1) Obtaining Data - Signed up as Developer in "" and using an API Key, I downloaded JSON Data through an app. We can download upto 1000 comments with one REST API Call. Doing it recursively by changing request parameters, we can obtain all the other comments. These comments can be stored in a database for future use.

    2) Sentiment Analysis - A comment's sentiment can be found out by using software. Expected results from such analysis are generally positive, negative, neutral and unclassified. My original plan was to use SAS Sentiment Analysis Studio to find out the sentiment. But, having no access to the software made me search for other ways to do it.

    3) Free Sentiment Analysis API - My next stop was API, I made an application which downloads the comments from website, and then using a REST API call, find out about the sentiment of each comment from its reponse. Sentiment Analysis API. But, there are some comments, which the API was not able to categorize. I also used a dictionary to filter positive and negative comments based on words such as "strongly support", "support", "oppose", "strongly oppose".

    Based on the above process, here are my results
    Positive Comments = 12267
    Negative Comments = 4856
    Neutral = 93
    Unclassified/Errors = 4968

    P.S - I am still trying to get better results and also confidence intervals for the above results. Help me out, if you know any other way to get better results.

    Thank you,
    Dheeraj Jami

  • #2
    Sentiment Analysis on OPT STEM Extension Proposal Rule Comments

    Hey Dheeraj, Great work.

    Here is my analysis framework

    Here are my results
    Total Comments = 22582
    Positive Comments = 15149
    Negative Comments = 5420
    Neutral Comments = 1997
    Male:Female Ratio for 1000 comments = 3:1

    Sentiment Analysis API (
    Gender using first name API ([0]=janice).

    All, feel free to fork the repository and use the framework & data.
    You will have to request an API KEY through:



    • #3
      Your question will be reviewed by our moderator and posted on our wall at within 24-72 hours please follow the post and forum.
      *** Don't Miss Important Topics, Subscribe to our Newsletter at ***
      If you feel this community is useful, please invite your friends by following below steps
      1. Goto
      2. Find "Suggest to Your Friends" - Click on "See All" and Invite your friends
      3. If you can't find the link, refer

      In addition to the readers comments, You can also call attorneys for free advice. DesiOPT is collaborating with group of attorneys. You can contact them directly via email/ phone. Initial Consult is Free. Their information is listed on home page.
      we are providing direct links as well, please let us know your feedback after the call

      F1 visa students find OPT Jobs, CPT Jobs, OPT Employers, H1B Jobs, STEM OPT Jobs, OPT Students



      • #4
        you need to multiply them with number of stakeholders per comments


        • #5
          What stakeholder?


          • #6
            stakeholder = people representing comment = 1 comment of school representative = roughly 1000 comments of individual students


            • #7
              that's a very rough roughly smile emoticon. do we have any data regarding that?


              • #8
                absolutely brilliant. But its limited to bag of words. I exactly thought of doing this. But this may not give us correct answers. We need more features. let me see if we can come up with more factors. Remember its not polling. We need analyze the entire comment and find more meaning out of it.


                • #9
                  Your message was posted anonymously on our Facebook wall at November 14th - Please review comments from other users