Tech Terms: Sentiment Analysis

For most planning processes, it is a real challenge to get engagement and input from the public. It is also common to only hear from certain groups, leaving many communities unheard, especially marginalised groups.

It’s now possible to capture not only qualitative data from the public as they use and move through urban spaces, we can also gain qualitative data. Sentiment analysis uses automatic “mining” of online information to work out opinions and emotional responses to place.

Youtube video about using sentiment analysis to optimise public transport journeys in the UK – this video gives an easy to watch introduction to what sentiment analysis is all about and how it can be used to support our city systems. Also check out my earlier post on the ‘base’ technology of Natural Language Processing to find out more.

Natural Language Processing and algorithms create Sentiment Analysis which can identify the public sentiment on a topic. For example, a city which holds a large event could use Sentiment Analysis to determine how well the event was received by the public by analysing what was said online and on social media at or after the event. Counting the public entering the event gives the quantitative data on how well the event was attended, but a qualitative analysis can give greater insight on how much the public enjoyed the event. This can be obtained by analysing whether the discussion online about the event was positive, neutral or negative.

Sentiment Analysis can be used for more refined evaluation than the polarity of “positive” or “negative” sentiment. As in the video linked above, it can collate suggestions for improvements and prompt useful and timely action. Sentiment analysis is huge in product marketing and brand management but it can be used in ways which help us in resource management. You can see environmental topics which are trending and topical. You can use it in many ways in a smart city context once data is flowing freely.

There is a lot of working going in to how to deploy sentiment analysis to support the smart city, so its an interesting space to watch. Here are some articles/papers if you would like to know more:

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s