Topic Modelling for Engagements

Topic Model takes thematic tagging of open-ended engagement responses to the next level, enabling more accurate, nuanced categorization of open-text responses. The Topic Model identifies specific topics for each response. The model analyzes the semantic meaning of engagement responses, assigning them to one or more relevant topics and subtopics based on the collected answers for each question. This ensures your engagement data is labeled with exceptional precision, uncovering deeper trends and insights from resident comments. Each response is also tagged with a sentiment label. 

How Does the Dynamic Labeling Process Work?

When a response is submitted, it is analyzed and categorized using Zencity’s dynamic topic and subtopic tree. This process follows these steps:

1. Each response is carefully analyzed and broken down into keywords and phrases that reflect its meaning.
2. The analyzed responses are used to identify the most frequently mentioned topics. These topics may include broad themes, such as housing or law enforcement, and specific local issues, like an elected official, a policy change, or a community event.
3. The identified topics are structured into a clear set of labels, which are then applied to tag individual responses that align with each topic.

The model requires a dataset of at least 50 valid, good qualitative responses to start labeling responses. The model will not label a simple yes / no question or questions such as 'what is your zipcode'.  Topic modelling only runs once the engagement has closed and results should be available within 24 hours. 

To view your Topic Clustering & Sentiment Analysis for closed engagements follow the steps in this helpdesk article: https://help.zencity.io/hc/en-us/articles/25553582087953-Viewing-Topic-Clustering-and-Sentiment-Analysis-for-closed-Engagements