HelaSentiLex (Hela Sentiment Lexicon)

Python API for Sinhala Sentiment Lexicon with 14000+ sentiment tagged Sinhala words

Setup environment

1. Make sure you have Python >= 3.6 by python --version
2. Additionally, you’ll need to make sure you have pip available by running pip --version
3. To install pip see installing pip
4. Install helasentilex package using the command pip install helasentilex

Getting started

Let's begin with showing how easy it is to find sentiments of Sinhala words using helasentilex

>>> import helasentilex
>>> helasentilex.sentiment('යහපත්')
1
>>> helasentilex.sentiment('අමිහිරි')
-1
>>> helasentilex.sentiment('පුටුව')
0

If the input word does not exist in our sentiment lexicon or the input is invalid then it will return None

>>> helasentilex.sentiment(23)
None

You can enter a sentence as a string and get sentiment scores for available words in the sentiment lexicon

>>> helasentilex.sentiments('ඔබේ සැප දුක කෙසේද')
{'ඔබේ': 0, 'සැප': 1, 'දුක': -1, 'කෙසේද': None}

If the input is invalid then it will return an empty dictionary

>>> helasentilex.sentiments(23)
{}

Defining labels

 1: POSITIVE (ධනාත්මක)
-1: NEGATIVE (ඍණාත්මක)
 0: OBJECTIVE (මධ්‍යස්ථ හෝ උදාසීන)

Contributing

Want to report a bug, contribute some code, or improve documentation? Excellent! fork our repository and start contributing.

Adding new words to the sentiment lexicon

To add new words along with their sentiment scores

1. Open helasentilex/lexicon.csv file
2. Append new_word,sentiment_score
3. Sort words in ascending order
4. Save changes to your forked repo and make a pull request

Love helasentilex? Give our repo a star!