Our Listening AI function helps you understand your organization’s open text answers in real-time by analyzing sentences and identifying key words.
Listening AI Analysis
Listening AI can be described as a highly sophisticated filter functionality. The filter functionality identifies actionable insights from large data set of comments through two types of analyses - Entity Analysis and Sentiment Analysis.
Entity Analysis inspects the given text for known entities (proper nouns such as public figures, landmarks, etc.), and returns information about those entities. From this analysis we are using the “salience score”. The salience score for an entity provides information about the importance or centrality of that entity to the entire document text. Scores closer to 0 are less salient, while scores closer to 1.0 are highly salient.
Sentiment Analysis inspects the given text and identifies the prevailing emotional opinion within the text, especially to determine a writer's attitude as positive, negative, or neutral. We are using sentiment score (-10 to 10) and emotional content (0, +inf) from this analysis.
Listening AI Dashboard
The first view of the Listening AI dashboard is a bird's-eye view of the most significant topics distributed over the emotional scale, from negative to positive. The bigger the bubble is, the more significant the topic is.
For more insight, click on a topic. From here you are able to access all comments related to this topic, view the most relatable adjectives, and choose between a scatter plot or bar chart view.
For a more specific view, click on an adjective within the topic. Any comments related to the topic and the chosen adjective will be visible here. The comment summary is based on the topic filter which shows the comment sentiment distribution as well as the average sentiment score for the selected topic or all comments. Sort and filter the data based on the information you want displayed.
Supported languages
The AI analysis is currently done in English since it’s the most developed analysis globally. If comments are made in one of our supported languages, the comments will be first translated to English and then included in the analysis. It is easy to switch between English and the original language for all comments analyzed by AI through the auto-translation functionality.