Personality-Adaptive Chatbots for E-Commerce: Matching Conversational Style to User Type
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.005 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".