2019-03-13 23:34:07 +08:00
2019-03-13 23:05:47 +08:00
2019-03-13 23:05:47 +08:00
2019-03-13 22:28:22 +08:00
2019-03-13 23:30:15 +08:00
2019-03-13 23:34:07 +08:00

Python-SentiStrength

Python 3 Wrapper for SentiStrength, reads a single or multiple input with options for binary class or scale output.

Ensure that you have SentiStrength.jar file and SentiStrengthData Language folders, otherwise you can download them from http://sentistrength.wlv.ac.uk/.

Installation

Pip:

pip install sentistrength

Examples

Example use (single string):

>>> from sentistrength import PySentiStr
>>> senti = PySentiStr()
>>> result = senti.getSentiment('What a lovely day')
>>> print(result)

... [0.25]

Example use (list of strings or pandas Series):

>>> from sentistrength import PySentiStr
>>> senti = PySentiStr()
>>> str_arr = ['What a lovely day', 'What a bad day']
>>> result = senti.getSentiment(str_arr)
>>> print(result)

... [0.25,-0.25]
# OR, if want binary scoring (a score each for positive rating and negativing rating) instead of scale
>>> result = senti.getSentiment(str_arr, score='binary')
>>> print(result)

... [(2, -1), (1, -2)]

Path Setup

Ensure that you have SentiStrength.jar file and SentiStrengthData folder in the same folder, otherwise you can specify the path:

>>> senti = PySentiStr()
>>> senti.setSentiStrengthPath = ... # e.g. 'C:\Documents\SentiStrength.jar'
>>> senti.setSentiStrengthLanguageFolderPath = ... # e.g. 'C:\Documents\SentiStrengthData\'

License

This project is licensed under the MIT License - see the LICENSE.md file for details

Acknowledgments

  • Big thanks to Dr. Mike Thelwall for access to SentiStrength.
S
Description
Better Python 3 wrapper for SentiStrength. SentiStrength is capable of automatic sentiment analysis of up to 16,000 social web texts per second with up to human level accuracy for English.
Readme 5.7 MiB
Languages
Python 94.4%
Shell 5.6%