search

trinker / sentimentr

Dictionary based sentiment analysis that considers valence shifters
Other
427 stars 84 forks source link

Same algorithm as in qdap's polarity function? #82

Closed Lucinho91 closed 6 years ago

Lucinho91 commented 6 years ago

Dear Mr. Rinker,

first of all thank you for your very helpful packages for text mining and sentiment analysis! I use them a lot and so you helped me so much with my master's thesis!

One question considering the algorithm of the "sentiment"-function: Is this the same approach used by qdap's "polarity"-function? If so, did I understand correctly that the difference is that "sentiment"-function can incorporate other dictionaries besides Hu & Liu (2004)? Anyways, your lexicon-based approach to sentiment analysis is very clever and I really like how you managed to include valence shifters, great work!

Thank you and best regards from Germany!

trinker commented 6 years ago

One question considering the algorithm of the "sentiment"-function: Is this the same approach used by qdap's "polarity"-function? If so, did I understand correctly that the difference is that "sentiment"-function can incorporate other dictionaries besides Hu & Liu (2004)? Anyways, your lexicon-based approach to sentiment analysis is very clever and I really like how you managed to include valence shifters, great work!

It is built from qdap's polarity but improved. Same basic idea though. qdap could also take other dictionaries but in the sentimentr package I have designed this process to be easier and there are ready to go dictionaries provided in the lexicon package already.