Canada Brand Health Methodology

This article covers the methodology behind the Canada Brand Health portal

Data Source

Data is collected online via a consumer survey panel quarterly. Each wave consists of 3,000 respondents age 18+ that were blindly screened for cannabis usage in the past 6 months. The sample is balanced against age, gender, and geography (province). We monitor cannabis usage among our sample to ensure it is representative. 

Data Collection

Canada Brand Health data was first conducted in early 2020. In order to trend the data, the same questionnaire is fielded during each wave apart from minor edits and the addition of new questions.

Social Listening Methodology

Social listening tools for this dashboard monitor a brand directory of key hashtags and accounts associated with top CBD brands. 

• We believe learning more about language patterns and tendencies can help brands more effectively message to and reach receptive audiences. 
• Using cutting edge techniques in differential language analysis and machine learning, we examine the sentiment and topics of posts, as well as attributes about the posters.
• We train language attributes like product categories by training our tagging algorithms with research-in-the loop methodology. We also train poster attributes like consumer and company posters using this same methodology. 
• Our neural networks are trained on hundreds of thousands of products and social posts, which our model then compares against hand-annotated products and social posts to come up with a precise prediction. Due to differences in the types of language used, this methodology is robust against "sponsored" and similar types of posts, identifying real consumer behavior in the wild. Our dashboards benefit from real client and internal feedback loops, so we encourage you to keep a tight communication with us to ensure the social dashboard is meeting your needs with respect to tags and categories.

What defines a loyal consumer?

In our brand health portal, the loyalty metric is based on respondents that chose they are very likely to purchase that brand again.