All analysis is automatic and continuous: it is applied to each response at
the moment it comes in, with no prior configuration and no rules to
maintain.
Automatic classification of comments
The AI engine classifies each comment, whether written text or a transcribed voice note, according to whether it requires action:- Recognition (no action required): there is nothing to do, for example praise or thanks.
- Improvement (requires action): the customer asks for, suggests or implies something your team should do, fix or answer, even when it comes inside praise.
Sentiment
Besides actionability, the AI reads the text sentiment of each comment: positive, neutral or negative. It is an independent reading used only for analytics and it never triggers actions. Cards, statistics and reports show its distribution and the net sentiment (from -100 to +100, like NPS), next to the rating average. See Actionability and sentiment.Rating-based sentiment in topics
In the Review Space, each response also falls into one of three levels, critical, neutral or positive, derived from the rating the customer left. These levels feed the analysis counts: each discovered topic shows its distribution of critical, neutral and positive responses, which lets you see at a glance whether a topic concentrates frustration or praise.Our own research
woku combines market-leading language models with its own research in sentiment analysis for Latin American Spanish, developed in collaboration with the PhD in AI of the University of Concepción (UdeC), the Federico Santa María Technical University (USM), the University of Bío-Bío (UBB) and the Catholic University of the Most Holy Conception (UCSC), the first PhD in Artificial Intelligence in Latin America.Interview about the model's development
Video with the interview of the PhD in AI academic about the development of woku’s own sentiment model.
Keywords and summaries
Keywords are extracted automatically from each piece of feedback. These words feed the word cloud in the woku, folder and NPS reports, which also include an AI-generated summary and suggested actions based on what customers say. CSAT and CES have their own AI Summary, which synthesizes in natural language the responses of each measurement.Reports by period
In every report (of a woku, a folder, an NPS, CSAT or CES tool and the company-wide ones) you can pick the period with the same options as Metrics: All time, 7, 30 or 90 days, or Custom, which opens a calendar to pick the first and the last day. The summary, the numbers and the PDF include only the responses of that period, and the PDF title shows it. The all-time report does not change. The Metrics tab has the same picker: with a custom range, each figure is compared with the same length right before it. With fewer than 5 comments, the report does not write an AI summary, because with so few responses it would invent trends: it says there are few comments and shows them as they are.Search the comments
In the opinions of a woku and in the NPS, CSAT and CES responses you can filter by period and search a word in the comments, regardless of case or accents. For example, “iluminacion” finds “Iluminación”.Emerging topics
Beyond the categories you already know, woku’s semantic engine groups responses by meaning and discovers emerging topics that were not defined in advance, with exact counts: each figure corresponds to real responses you can review. Topics are explored in the reviews space, a 3D universe where each response is a point and responses that talk about the same thing end up close together. Selecting a topic opens a panel with:- Label and summary of the topic.
- Number of responses that make it up.
- Sentiment distribution (critical, neutral, positive).
- Trend and first and last appearance over time.
- Evidence: the real responses that support the topic.
Where it is displayed
Text analytics results appear in several places across the platform:- Instrument and folder reports: word clouds, AI summaries and suggested actions. A folder report brings wokus and NPS, CSAT and CES tools into one analysis (without mixing their score scales); see Folders and tools. In the app, that report is the Text analytics tab; the Metrics by tool tab shows the figures of each tool. The report of each woku, NPS, CSAT or CES has the same two tabs: Text analytics and Metrics, with the figures and sentiment of that tool.
- Review Space: emerging themes and sentiment distribution.
- Data Studio (Corporate): interactive analysis supported by company data.