Update existing Python program that uses dictionary to score sentiment
- or -
Post a project like this2196
€50(approx. $54)
- Posted:
- Proposals: 4
- Remote
- #1959952
- Awarded
Description
Experience Level: Intermediate
An existing python program - can be accessed at https://github.com/abijith-kp/nlp-sentiment-analysis uses a dictionary to score words. This code would need to be updated to calculate sentiment and produce output in a spreadsheet.
Requirements:
1) As I do not understand the code, I would like a detailed description of what the current code is doing, and if it is working properly (i.e. if it is calculating the sentiment correctly for the relevant words).
2) Using the input file (output 11.csv) - I would like the program to read each tweet, and using the words with 'R', 'V' or 'A' in column D only, get the sentiwordnet.py program to calculate the score for each tweet.
Note: If score is populated on left - it is 'Positive', i.e. for the word 'hope' the scoring is - (0.375, 0), which shows a positive score.
Example:
Search for Tweet #799391092588343000 in the output11.csv file. It will appear as the GIF below, before processing:
See 'Tweet before processing' GIF.
To view the same tweet (with scoring), see GIF below:
See 'Tweet with scoring' GIF.
Breakdown of overall tweet scoring: For word ‘belated’, the scoring is on the right which denotes a negative scoring. For the word ‘Happy’, the scoring is on the left which denotes a positive scoring.
To calculate Score: Cumulative negative scoring = 0.375. Total positive scoring = 0.625. Calculated scoring would be (0.25, 0), which is mostly positive (and therefore given a score of ‘1’), as below. A score of mostly negative would result in score ‘0’.
Tweet ID Score
799391092588343000 1
The revised program will print out a scoring of '1' or '0' for each tweet (as above), or if no scoring (or calculated score produces a score of (0, 0),) then print out 'Neutral'.
Requirements:
1) As I do not understand the code, I would like a detailed description of what the current code is doing, and if it is working properly (i.e. if it is calculating the sentiment correctly for the relevant words).
2) Using the input file (output 11.csv) - I would like the program to read each tweet, and using the words with 'R', 'V' or 'A' in column D only, get the sentiwordnet.py program to calculate the score for each tweet.
Note: If score is populated on left - it is 'Positive', i.e. for the word 'hope' the scoring is - (0.375, 0), which shows a positive score.
Example:
Search for Tweet #799391092588343000 in the output11.csv file. It will appear as the GIF below, before processing:
See 'Tweet before processing' GIF.
To view the same tweet (with scoring), see GIF below:
See 'Tweet with scoring' GIF.
Breakdown of overall tweet scoring: For word ‘belated’, the scoring is on the right which denotes a negative scoring. For the word ‘Happy’, the scoring is on the left which denotes a positive scoring.
To calculate Score: Cumulative negative scoring = 0.375. Total positive scoring = 0.625. Calculated scoring would be (0.25, 0), which is mostly positive (and therefore given a score of ‘1’), as below. A score of mostly negative would result in score ‘0’.
Tweet ID Score
799391092588343000 1
The revised program will print out a scoring of '1' or '0' for each tweet (as above), or if no scoring (or calculated score produces a score of (0, 0),) then print out 'Neutral'.
Eddy S.
93% (17)Projects Completed
17
Freelancers worked with
13
Projects awarded
90%
Last project
3 May 2022
United States
New Proposal
Login to your account and send a proposal now to get this project.
Log inClarification Board Ask a Question
-
There are no clarification messages.
We collect cookies to enable the proper functioning and security of our website, and to enhance your experience. By clicking on 'Accept All Cookies', you consent to the use of these cookies. You can change your 'Cookies Settings' at any time. For more information, please read ourCookie Policy
Cookie Settings
Accept All Cookies