Dear Sibgha Anwar,

The answer of your question asked is better found at the source given below.

Mäntylä, M. V., Graziotin, D., & Kuutila, M. (2018). The evolution of sentiment analysis—A review of research topics, venues, and top cited papers. Computer Science Review, 27, 16-32.

Thanks,

Sobhan

Hi Sibgha

In point of fact, there are many different kinds of idea for researching in sentiment analysis. For example, here are some of the last investigation on this subject. I'm of the opinion that you should access an appropriate of data using for analyzing.

Article Application of Sentiment Analysis to Language Learning

Article Multi-Strategy Sentiment Analysis of Consumer Reviews Based ...

Article Multi-Strategy Sentiment Analysis of Consumer Reviews Based ...

Dear Sibgha Anwar,

The answer of your question asked is better found at the source given below.

Mäntylä, M. V., Graziotin, D., & Kuutila, M. (2018). The evolution of sentiment analysis—A review of research topics, venues, and top cited papers. Computer Science Review, 27, 16-32.

Thanks,

Sobhan

https://arxiv.org/pdf/1609.00536

https://arxiv.org/pdf/1612.01556

https://monkeylearn.com/sentiment-analysis

https://www.w3.org/2012/06/pmod/opinionmining.pdf

http://www.mdpi.com/2297-8747/23/1/11/pdf

so many problems in this issue. Such as,sarcasm,which feature that you want to extract from the data . the way you are going to pre-process your data.

the interesting thing in here how you can make your model works for different domains .

I hope this will help:)

I've explored sentiment analysis and its challenges in my thesis Thesis Opinion Mining and Lexical Affect Sensing

That's really depends of your research Achives. I worked with Twitter in mine thesis so the big challenge that I had was detect bots