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

VADER can't parse the word 'bad ass'? #141

Open letitburn00 opened 2 years ago

letitburn00 commented 2 years ago

I am running a sentiment analysis on a large corpus of tweets in R. VADER successfully returned sentiment scores for all but five tweets, which returned 'ERROR' in the word scores field. Upon inspection of these tweets, I noticed that they all contained the word 'bad ass'. When replacing 'bad ass' with 'badass', sentiment scores are successfully returned. It seems like this is a bug?

Deepankar-98 commented 2 years ago

Can you confirm what error are you getting? I ran both the strings and its working fine for me. See below screenshot:

image
letitburn00 commented 2 years ago

Hi, the error may actually be unrelated to the word 'bad ass', but is somehow solved by replacing it with 'badass'? I wasn't able to replicate the problem on the exact strings I was working with before, but the same problem occurred for a new one: vader_error Scores were successfully returned for other tweets with 'bad ass'. I don't see any glaring issues with the above text, so I'm not sure what the problem could be.