emotext
emotext is a python library to analize sentiment it can be negative (0), positive (4) or neutral (2).
Installation
pip3 install emotext
Instructions for use
from emotext import SentimentProbability
prob = SentimentProbability()
prob.fit("positive_words.txt", "negative_words.txt", "stop_words.txt")
pred = prob.predict("hari ini sangat indah sekali")
print(pred)
# outout
# 4 or positive
| name | description |
|---|---|
| positive_words.txt | put all the positive words on this file it can be in any language. in this documentation i use indonesian language,so the positive words like example : optimis, kuat, menyenangkan and etc |
| negative_words.txt | all the negative words, example : mengganggu, menindas, kejam and etc |
| stop_words.txt | all the stop words, example : yang, di, dan itu, etc |
*note
all of those file wrote in indonesian language, it possible to change with any language. just put all of the word into .txt file and make sure 1 line for 1 word, look at example below :
# do
optimis
kuat
menyenangkan
# don't
optimis kuat menyenangkan
If you are indonesian i have created all of those file just look at folder data
warning
You don't have to worry about noise on your text like
- omoji : 🥸 😘 🤬
- punctuation : #?!^&*%@, etc
all of that will be removed automatically and if you grab the data from twitter it automatically remove username and hastag
Release files for emotext 0.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| emotext-0.1.tar.gz | 3.9 kB | Details |
Release files / emotext-0.1.tar.gz
| Download URL | emotext-0.1.tar.gz |
|---|---|
| Size | 3.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
55672058889180ad6ecd17a079fefe727e1026765fba1267afc79381e8dacb80
|
|
BLAKE2b-256 checksum How to use checksums |
9711332c38a0f1ad6c6e44f504af543aa0eeb50eea65e21a129b44c49e428b3a
|
| 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/44.0.0 requests-toolbelt/0.9.1 tqdm/4.56.0 CPython/3.8.6
|