Predicting User Trust in Customer-Service Chatbots: A Supervised Learning Study

DOI

10.2991/978-94-6239-664-7_13How to use a DOI?

Keywords

Chatbots; Trust Prediction; Supervised Learning; Customer Service; Probability Calibration; Human-in-the-Loop

Abstract

User trust is the basis of chatbots for customer-service, especially where disclosure of personal information is in question. We frame trust prediction as supervised binary classification on questionnaire data (N=122) with questionnaire items (demographics, frequency of use, overall and recent satisfaction, and sector exposure). The binary label is the will to disclose personal information (Yes/No). We experiment with Logistic Regression, Random Forest, and HistGradientBoosting with stratified 5-fold cross-validation and a 20% held-out test set and report Accuracy, F1, Precision, Recall, ROC–AUC, and PR–AUC. HistGradient-Boosting performs best on the test set (Accuracy 0.88, F1 0.857). Feature attribution across models reveals overall and recent satisfaction, frequent use, and sector context (e.g., bank/healthcare) as top indicators. We calibrate predicted probabilities and propose a conservative escalation rule—handoff to a human where P(trust) < 0.35—to keep low errors in high-risk sectors very sensitive to privacy. Calibrated predicted probabilities and the rule we propose are our contributions towards a safer, sector-aware chatbot design and a set of actionable recommendations for deployment in practice.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Md. Rafiul Islam
AU  - Pulock Kumar Kundu
AU  - Jafir Islam Siam
AU  - Rayhan Rabby
AU  - Md.Mortuza Ahmmed
PY  - 2026
DA  - 2026/06/08
TI  - Predicting User Trust in Customer-Service Chatbots: A Supervised Learning Study
BT  - Proceedings of the International Conference on Intelligent Data Analysis and Applications (IDAA 2025)
PB  - Atlantis Press
SP  - 163
EP  - 176
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-664-7_13
DO  - 10.2991/978-94-6239-664-7_13
ID  - Islam2026
ER  -