I am learning sentiment analysis on R by using Twitter data for almost month, but I am still lost and I have many questions don't have answers for it I hope found it here.
first I know how to get data and clean it from Punctuation m Hashtags, Mentions,.........etc.
second is sentiment analysis step, but I am working on Arabic language, so there isn't function do sentiment analysis like NRC, bing, AFINN.
so I need to build Arabic lexicon how can I do it what is the steps?
imagine there isn't any function do sentiment analysis in English, so how you will do it
I am actually writing two excel sheets, one has positive words and the other has negative words.
then I match between the tweets and sheets, for example, one tweet has 4 words positive and 7 negative that means the tweet is negative.
but I do not know is my work right?
and there is a lot of words a do not know where should I put it, like company , go, man .... etc.
in a positive file or negative or should I create other file or ignore them.
I hope you understand me and sorry for my poor English.