search

cjhutto / vaderSentiment

VADER Sentiment Analysis. VADER (Valence Aware Dictionary and sEntiment Reasoner) is a lexicon and rule-based sentiment analysis tool that is specifically attuned to sentiments expressed in social media, and works well on texts from other domains.
MIT License
4.38k stars 1k forks source link

How can I add my own set of words in the dataset? #111

Open gmehta1996 opened 4 years ago

gmehta1996 commented 4 years ago

Is it possible to add more words into the words list and if yes how to do it and can I also add a phrase like 2-3 words together to make the program understand that these particular words together are either positive,negative,etc.

Suppose I use it in a review of a vehicle (sentence given below):

'It's vibrates too much while over speeding.'

It gives the following result:

{'neg': 0.0, 'neu': 1.0, 'pos': 0.0, 'compound': 0.0} The result is neutral but it should be negative . So. how can I add these types in the dataset to get a better result??

SemihDurmaz54 commented 3 years ago

Yea, go to C:\Users\yourUserName\AppData\Roaming\nltk_data\sentiment and you'll see a .txt file in vader_lexicon.zip You can add words, edit existing words' scores or delete some of the words