What it does
This KPI evaluates how well a marketing asset’s text aligns with its intended messages. This is achieved by quantifying to what extent text extracted from the asset matches or implies the user-provided intended messages. Consequently, the KPI establishes the asset’s literal or implied message fit.
Why it matters
Ensuring that text in marketing assets is aligned with the intended message is critical to effective communication. Proper alignment reinforces the message, improves clarity, and prevents misinterpretation, directly influencing consumer behavior and brand perception.
How it works
Text is extracted from assets using a text recognition model, then filtered for brand names. String matching determines whether the intended messages appear verbatim in the text, while a deep learning model assesses semantic alignment with the messages. Scores are calculated for each intended message based on either the string matching or deep learning results, with the higher score prevailing. The output includes individual scores for each message and an overall score.
See below for more details on how the score is calculated in video apps.
How to achieve great results
- Ensure that key messages are clearly and prominently communicated throughout the text.
- Use language that resonates and is closely aligned with your intended messages.
- Balance the use of direct (literal) and implied messages to communicate effectively while maintaining creativity and engagement.
AI models used
This KPI uses a world-class text recognition (OCR) model capable of recognizing a wide range of fonts and styles in diverse visual environments. It also employs deep learning models to assess and quantify the semantic fit between intended messages and asset text. These models have been trained on 160GB of text and are designed to accurately assess alignment with pre-defined messages and values, providing a comprehensive assessment of a text’s strategic fit with the campaign’s intention.
How it works - video apps
Example result:
Explanation:
Lets say a video consists of 5 scenes and 3 labels are inserted in the briefing.
- Vertically you see the score each label gets for each scene resolving in the orange (label) score. I.e. in 20% of the scenes, label 1 was communicated above threshold (threshold = 50). So the score of 20 would be displayed in the table for this label.
- The overall score (Overall video calculation) is then calculated as shown in column E.
- Is at least one of the messages being conveyed above threshold. Here it doesnt matter if only one or all messages are above threshold.
- So Scene 1,2 4 and 5 have at lesat one message above threshold. Scene 3 doesnt. Thus, 4 of 5 scenes communicate at least one message above threshold