Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Create test using Amazon Comprehend and Translate #13

Open
pethers opened this issue Apr 10, 2018 · 9 comments
Open

Create test using Amazon Comprehend and Translate #13

pethers opened this issue Apr 10, 2018 · 9 comments

Comments

@pethers
Copy link
Member

pethers commented Apr 10, 2018

https://aws.amazon.com/translate/pricing/ and https://aws.amazon.com/comprehend/pricing/

approx 200.000+ documents total 2GB+ text

@pethers
Copy link
Member Author

pethers commented Apr 10, 2018

@pethers
Copy link
Member Author

pethers commented Apr 10, 2018

@pethers
Copy link
Member Author

pethers commented Jun 5, 2018

Test case :Personal insight
Take 5000 first text chars from each party program https://www.folkbildning.net/amnen/samhalle/politik/riksdagspartiernas-partiprogram/?sort=UpdateDate&dir=desc
Translate using: https://translate.google.com/

@pethers
Copy link
Member Author

pethers commented Jun 5, 2018

insight-sd.txt

@pethers
Copy link
Member Author

pethers commented Jun 5, 2018

insight-centern.txt

@pethers
Copy link
Member Author

pethers commented Jun 5, 2018

insight-v.txt

@pethers
Copy link
Member Author

pethers commented Jun 5, 2018

Cost estimate
Amazon translate total cost ($15 per million characters) : $0.000015 per character x 2Gb(2000-2018) approx $3200
Google translate total cost ($20 per million characters ) $0.00002 per character x 2Gb(2000-2018) approx $4300

about 10-15k documents annually $200-300

Personal Insight cost
Standard
– First 100 API calls per month are FREE.
– Additional 1 - 100,000 calls are $0.02 per call
– 100,001 - 250,000 calls are $0.01 per call
– 250,000+ calls are $0.005 per call

2000 politicians/10 parties /20 committe/20 ministry : 2000 api calls approx $40

@pethers
Copy link
Member Author

pethers commented Jun 5, 2018

natural language processing Cost

https://cloud.google.com/natural-language/
Entity Analysis
Entity Sentiment Analysis
Syntax Analysis
low usage : $1 per 1Mb per service

https://aws.amazon.com/comprehend/
Entity Recognition
Keyphrase Extraction
low usage : $1 per 1Mb per service

@pethers pethers modified the milestones: Election2018, Election2022 Oct 28, 2018
@pethers
Copy link
Member Author

pethers commented Nov 22, 2018

@pethers pethers added this to In progress in Citizen Intelligence Agency Jan 26, 2019
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
Development

No branches or pull requests

1 participant