sentiment-spanish
How does it work?
sentiment-spanish is a python library that uses convolutional neural networks to predict the sentiment of spanish sentences. The model was trained using over 800000 reviews of users of the pages eltenedor, decathlon, tripadvisor, filmaffinity and ebay. This reviews were extracted using web scraping with the project opinion-reviews-scraper
Using the rate in the user reviews we trained the model to learn from the language in them. For that we use the libraries Keras and Tensorflow. We achieved a validation accuracy (accuracy over fresh data, no used for training) of 88%. For more details regarding the training of the neural network model check the repo sentiment-analysis-model-neural-network
Why?
I believe there are not many solutions to sentiment analysis in spanish based on neural networks.
Install and use
First to install the package
pip install sentiment-analysis-spanish
You will also need keras and tensorflow
pip install keras tensorflow
Import the package
from sentiment_analysis_spanish import sentiment_analysis
run the sentiment analysis:
sentiment = sentiment_analysis.SentimentAnalysisSpanish()
print(sentiment.sentiment("me gusta la tombola es genial"))
you will see that it outputs
1
For instance if you use the text
sentiment = sentiment_analysis.SentimentAnalysisSpanish()
print(sentiment.sentiment("me parece terrible esto que me estás diciendo"))
you will see that it outputs
9.460418e-14s
which as you see is very close to 0.
Output and meaning
The function sentiment(text) returns a number between 0 and 1. This is the probability of string variable text of being "positive". Low probabilities mean that the text is negative (numbers close to 0), high probabilities (numbers close to 1) mean that the text is positive. The space in between corespond to neutral texts.
1 maintainer
Metadata
1 maintainer
Release files for sentiment-analysis-spanish 0.0.25
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| sentiment_analysis_spanish-0.0.25.tar.gz | 30.0 MB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| sentiment_analysis_spanish-0.0.25-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 60.0 MB
Release files / sentiment_analysis_spanish-0.0.25.tar.gz
| Download URL | sentiment_analysis_spanish-0.0.25.tar.gz |
|---|---|
| Size | 30.0 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
3ff8be0ac00398f4bbf2b3e8d728d493f75240bea9ab2f74cc11482275b2f122
|
|
BLAKE2b-256 checksum How to use checksums |
f7c93b7de30ed4ba6951eddb4596b8e1bb370d943de0fedc2929538816ba4b7e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.3.0 pkginfo/1.7.0 requests/2.25.1 setuptools/51.1.1 requests-toolbelt/0.9.1 tqdm/4.56.0 CPython/3.9.1
|
Release files / sentiment_analysis_spanish-0.0.25-py3-none-any.whl
| Download URL | sentiment_analysis_spanish-0.0.25-py3-none-any.whl |
|---|---|
| Size | 30.0 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
7b2bf32aab0dc1287c12118cd88bd111b349db1f168ef99fb0db429489c9a195
|
|
BLAKE2b-256 checksum How to use checksums |
cb3c104f7abeff16e347cf7b795ed9b5c841e1c5df9c1bfbd2d00d7684942a80
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.3.0 pkginfo/1.7.0 requests/2.25.1 setuptools/51.1.1 requests-toolbelt/0.9.1 tqdm/4.56.0 CPython/3.9.1
|
Security for sentiment-analysis-spanish 0.0.25
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
