Hi, Sentiment analysis itself faces some challenges from technical perspective in any context not just the smart cities. The general challenges will be domain-dependency, context-dependency, sarcasm, spam, ambivalency, and implicit opinions(or sentiment). These are the challenges that have to be considered in the design and implementation of any application of sentiment analysis.

I think lexicon is important.

https://www.researchgate.net/publication/266160374_Building_an_Arabic_Sentiment_Lexicon_Using_Semi-Supervised_Learning?ev=prf_pub

Knowing first if a sentence is subjective or objective. If there is a sentiment, is it positive or negative and in what degree?

Can we determine the holder of this sentiment?

https://www.researchgate.net/publication/272421575_Towards_Discovering_the_Sentiment_Holder_in_Arabic_Text?ev=prf_pub 

Article Building an Arabic Sentiment Lexicon Using Semi-Supervised Learning

Article Towards Discovering the Sentiment Holder in Arabic Text

Challenges:

Sarcasm - if done as positive will be classified as positive and same for negative.

Neutral opinion- how can one specify wether the opinion is neutral.

Time based.

Domain Dependency

Spam