Understanding Consumer Preferences from Social Media Data

Taylor Bradley
Additional contact information
Taylor Bradley: Black Swan Data, Executive Data Science Director (formerly GfK SE)

NIM Marketing Intelligence Review, 2019, vol. 11, issue 2, 48-53

Abstract: Consumers produce enormous amounts of textual data of product reviews online. Artificial intelligence (AI) can help analyze this data and generate insights about consumer preferences and decision-making. A GfK research project tested how we can use AI to learn consumer preferences and predict choices from publicly available social media and review data. The common AI tool “Word Embeddings” was used and has shown to be a powerful way to analyze the words people use. It helped reveal consumers’ preferred brands, favorite features and main benefits. Language biases uncovered by the analysis can indicate preferences. Compared to actual sales data from GfK panels, they fit reasonably within various categories. Especially when data volumes were large, the method produced very accurate results. By using free, widespread online data it is completely passive, without affecting respondents or leading them into ranking or answering questions they would otherwise not even have thought of. The analysis is fast to run and no fancy processing power is needed.

Keywords: Text Analysis; AI; Preference Measurement (search for similar items in EconPapers)
Date: 2019
References: Add references at CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://doi.org/10.2478/nimmir-2019-0016 (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:vrs:gfkmir:v:11:y:2019:i:2:p:48-53:n:7

DOI: 10.2478/nimmir-2019-0016

Access Statistics for this article

NIM Marketing Intelligence Review is currently edited by Christine Kittinger-Rosanelli

More articles in NIM Marketing Intelligence Review from Sciendo
Bibliographic data for series maintained by Peter Golla ().