Personality-Adaptive Chatbots for E-Commerce: Matching Conversational Style to User Type

Personality-Adaptive Chatbots for E-Commerce: Matching Conversational Style to User Type

Aryan Bhadoria, Abheet Singh

Department of Computer Science and Engineering (Artificial Intelligence) IIMT College of Engineering, Greater Noida, India

Emails: aryanbhadoria2003@gmail.com, abheet883@gmail.com

ABSTRACT

Online shopping has changed a lot thanks to AI, especially with chatbots popping up everywhere. They're supposed to make things easier, right? But honestly, most of them feel like talking to a robot – they just don't get you. That's where we wanted to shake things up. We wondered, what if a chatbot could actually understand your personality and talk to you in a way that felt natural? Imagine a chatbot that's super friendly if you're a chatty person, and keeps it short and sweet if you're more business-like. That's what we tried to build. We created a prototype chatbot for an online store that could figure out someone's personality based on how they interacted. We used a mix of simple rules and data analysis, and based it off the "Big Five" personality traits. Then, it would change its tone and style to match. We tested this out with 100 people, half using our personality-matching chatbot, and half using a regular, unchanging one. We wanted to see if people liked the personalized chatbot better. Turns out, they did! People who chatted with the personality-matching chatbot were way happier and spent more time interacting with it. They just clicked with it better. This shows that when a chatbot actually tries to understand you, it makes a huge difference. We're basically saying, chatbots shouldn't just be tools. They should feel like real conversations. And understanding someone's personality is a big part of that. We think this is the future of how we'll talk to computers online.