Artificial Intelligence (AI) & Machine Learning Course for Managers

 Enroll Now

Hive - Project

8 / 17
   

In this step, we will create _l1_, _l2_ and _l3_ views which will help us in calculating sentiment of each tweet.

Steps

  1. Create view _l1_. _l1_ view converts each tweet into lower case and explodes it into a list of words. Run below command in Hive query editor in Hue.

    create view l1 as select id, words from tweets_raw lateral view explode(sentences(lower(text))) dummy as words;
    


    Sample rows of view _l1_ are

  2. Create view _l2_. _l2_ view stores every word of a tweet in a new row. Run below command in Hive query editor in Hue.

    create view l2 as select id, word from l1 lateral view explode( words ) dummy as word ;
    


    Sample rows of view _l2_ are


  3. Create view _l3_. _l3_ view joins _l2_ view with _dictionary_ table and stores polarity of each word. Run below command in Hive query editor in Hue.

    create view l3 as select 
    id, 
    l2.word,
    case d.polarity 
    when  'negative' then -1
    when 'positive' then 1 
    else 0 end as polarity 
    from l2 left outer join dictionary d on l2.word = d.word;
    


    Sample rows of view _l3_ are


Question-

What is the polarity of word "crushes"?