CODEWITHSUNDEEP
pythonibm-watsonpersonality-insights
Juliana Rivera
Juliana Rivera

Reputation: 1083

Personality Insight - Analyzing comments from different users

I am sending a JSON file with multiple comments and reviews from different users, but it seems the response is in general and not for every comment that I am sending through the "content" field in the JSON. Is the API able to return insights for every comment of every users? Or it treat as a multiple comments of a single user? For example, I have this reviews of different users:

{
       "contentItems": [
         {
           "content": "amazon's business model is incredible, is riding a number of secular trends (ecommerce, cloud, ai), and the stock is a winner. employees are making more money than expected.+ leadership principles drive a high performance culture that focuses on customers. it feels great to work on products that customers love.+ you get to work on very difficult problems with smart people. once you establish yourself as a high performer, you have a high level of job security and internal mobility. teams are constantly hiring and building really innovative things and you are encouraged to move around and explore.+ teams tend to be lean and you will be asked to learn a lot quickly. ownership is highly valued.+ office environment is really desirable. located in a great downtown seattle neighborhood, many people walk to work, bring dogs to the office, and restaurants and bars are very accessible.+ amazon veterans tend to be incredibly talented individuals, and other companies realize it. being successful at amazon is well respected in the industry.. - work/life balance can be a challenge. work demands are high and teams are often too lean. you have to set your own boundaries. even with kind managers, overachievers will feel under water.- frugality as a core value goes overboard. if amazon doesn't have to give it you, it won't. no perks, no free food or drinks, bad coffee, unsubsidized cafeterias, mediocre hardware for non-technical people. there doesn't seem to be a morale budget and you will have few official team outings.- compensation policies are not employee friendly: 401k matching is subpar. once your signing cash bonus is fully vested, your entire compensation will be base salary and stock. base salary is capped at ~$160k across the company. stock vests twice a year if you're below a director, so your compensation is very lumpy. stock price appreciation is taken into consideration in your total compensation targets (ie if the value of previously offered shares increases, the company will count that as a raise and might not grant you additional stock bonuses, despite strong performance).",
           "contenttype": "text/plain",
           "id": "19"
         },
         {
           "content": "--> culture & leadership principles - the amazon leadership principles are not a mission statement that was developed and then forgotten. we live and die by these principles and they drive our culture... and the culture is pretty great!--> work with super smart, very talented people",
           "contenttype": "text/plain",
           "id": "250"
         },
         {
           "content": "1) when christmas season is busy time, management seems nice to everyone and act like they love and respect that you came to work each day, you can do no wrong as long as your busy. after a year i now know that working for wal*mart just sucks monkey balls!!!!!",
           "contenttype": "text/plain",
           "id": "66674"
         }
       ]
     }

I expect an output with the Personalities insights for each review. Instead I have a general response for all the comments. So, I wonder if the service is able to do this, or if I have to send one JSON for every user? The question is related to This other question, but instead of 1000 tweets of a single user, I need to process 1000 or more reviews form different users.

Upvotes: 1

Views: 114

Answers (1)

Felipe Paixao
Felipe Paixao

Reputation: 411

You need to send one request per person, but even if it would be possible to send one request with various users, to get one profile for each, in your example, two contents would return as an error. Thats because PI needs at least 100 words to give a result and the two last tweets have less than 100 words, so you would not be able to get a profile.

This table can give you more information about the amount of words needed to get a profile and the disadvantages of using a small number of words.

If in your use case normally it would not be possible to get at least 100 words, it may not be viable to use PI, but you can at least get some information about the tone of the user, with Tone Analyzer, it's not the same thing, but can give some intel about each user.

Upvotes: 1

Related Questions