What is Zencity Sentiment?

Our sentiment analysis algorithm determines if data reflects positive or negative feedback about city-related issues. Every conversation in the platform, be it a post or a comment, is assigned a sentiment score, based upon the content of its text. Likes, comments, and shares are all taken into account in generating the sentiment of a post or comment. 

This means that if residents are satisfied or dissatisfied with the discussed issue then the sentiment is likely to be positive or negative, respectively. There is no difference if negative feedback is about the issue discussed or the city’s role in the issue - the content will carry negative sentiment regardless. The reason for this is that it is extremely hard for an algorithm to differentiate, and we’d rather highlight the issues of highest concern. If a post or a comment contains informative data, it actually carries no sentiment and will probably be neutral. 

Our sentiment analysis is driven by AI and constantly trained by experts. While individual mistakes are possible, the algorithm should pick up on the general sentiment trend of most conversations, and is always improving over time.

How does Zencity’s AI assign sentiment to a text? 

Sentiment is not assigned based on the tone of the words alone. Zencity’s AI is conversation-based and takes into account the context of a piece of text in its entirety when assigning sentiment. We’ve learned that what makes content positive or negative for cities isn’t necessarily the nature of the words or events - for example, while a robbery is a bad thing, informing the public about a robbery that occurred shouldn’t be negative (unless explicit dissatisfaction is expressed in the text). And in fact, a conversation where people express gratitude about stopping the robbery might be considered positive feedback.

What does “neutral” mean and why is it interesting?

Neutral is discourse without sentiment, as defined above. Whereas positive or negative sentiment can be used to pinpoint specific issues, concerns, satisfaction, or feedback related to posts, neutral represents discourse that does not specifically relate to a sentiment. If your post is trending but it’s mostly neutral, it means that it received a lot of attention but not necessarily expressions of positive or negative feedback. In some cases, this can be a helpful indicator in measuring the effectiveness of a social media campaign, in which a high volume of neutral may represent success. 

How can I use sentiment to easily find the issues that are concerning to residents?

First off, events that cause a strong, negative public reaction will appear as such - for example, police misconduct may trigger negative sentiment in the police category. Filtering on negative sentiment in the main dashboard or by specific categories of interest is a good way to understand what people are expressing concern about. You can learn more about filters here

The timeline shows a peak in negative discourse following a story about the police. Some of the comments are shown below

How can I use sentiment to find challenges or issues that need fixing?

Filtering on negative sentiment in issues that fall under the city’s purview, like public works, helps focus on identifying resident concerns. 

The timeline shows a peak in negative discourse following a story about sidewalk and road maintenance. Some of the conversations are shown below.

How can I use sentiment to assess resident feedback on an issue or policy?

Creating a project in Zencity will consolidate discourse on a specific issue, event, or policy. Within the project, you can filter by positive, negative, and neutral sentiment to see how posts and interactions are classified. 

The timeline shows discourse about a project, defined to track conversations about a specific city policy.

By filtering only by conversations that have  sentiment (excluding neutral), it’s clear that feedback on the policy was more positive than negative. Some of the comments are shown below.

How can I use sentiment to see how residents react to a post I published?

Filtering by source for “Official Sources” shows all of the content posted by your city’s official pages across all channels (i.e. Facebook, Twitter, Instagram, etc.) You can view a specific published post and the thread it generated by using the filter of “Official Sources” and to see the breakdown of sentiment on an individual post. Likes, comments, and shares are all taken into account in generating the sentiment of a post. 

How can I use sentiment to get a sense of what residents care about and how?

Looking at trending topics on your main dashboard will prioritize the topics residents are talking about based on popularity, meaning volume of engagement around each topic. Using the sentiment breakdown for each topic, you can have a holistic overview of how residents feel about that specific topic.

Did this answer your question?