Algorithmically-Generated Personas paired with AI-Generated Pain Points Detection

Algorithmically-Generated Personas paired with AI-Generated Pain Point
Algorithmically-Generated Personas paired with AI-Generated Pain Points Detection

One does not often hear personas, AI, and pain points mentioned together. However, the combination can provide better situational awareness and better brainstorming on addressing customer pain points. It is analogous to a mixed-methods approach!


Artificial intelligence carries a high potential to automatically detect customers’ pain points, which is a particular concern the customer expresses that the company can address. However, unstructured data scattered across social media make detection a nontrivial task.

To help businesses gain deeper insights into customers’ pain points, we experimented with and evaluated the performance of various machine learning models to automatically detect pain points and pain point types for enhanced customer insights.

The data consisted of 4.2 million user-generated tweets targeting 20 global brands from five industries. Among the models we trained, neural networks show the best performance at overall pain point detection, with an accuracy of 85% (F1 score =.80). The best model for detecting five specific pain points was RoBERTa 100 samples using SYNONYM augmentation.

Based on the findings, we suggest that firms use pain point profiling to apply subclasses to the identified pain point messages to gain a deeper understanding of their customers’ concerns.

The next step of this research is to take this social media data and enrich it with demographic and other data to create foundational personas. Then, enhance these foundational personas to create complete, useable, algorithmically-generated personas for use throughout the business to address these customer pain points.

You can read about AI pain point detection and algorithmically-generated personas creation in the following articles.


Salminen, J., Mustak, M., Corporan, J., Jung, S., & Jansen, B. J. (2022). Detecting Pain Points from User-Generated Social Media Posts Using Machine LearningJournal of Interactive Marketing. 57(3)

An, J., Kwak, H., Salminen, J., Jung, S.G., and Jansen, B. J. (2018) Imaginary People Representing Real Numbers: Generating Personas from Online Social Media Data. ACM Transactions on the Web. 12, 4, Article 27.

An, J., Kwak, H., Salminen, J., Jung, S.G., and Jansen, B. J. (2018) Customer segmentation using online platforms: isolating behavioral and demographic segments for persona creation via aggregated user data. Social Network Analysis and Mining. 8(1), 54.

Scroll to Top