Qualifying NEV User Experience: LLM-Based Dimensional Encoding and Hierarchical Clustering of Online Comments
Abstract
As competition in the new-energy-vehicle (NEV) market increasingly shifts from technical specifications to holistic user experience, understanding user-generated feedback has become essential for product optimisation. This report investigates NEV user experience across 12 dimensions, including powertrain performance, handling, space and comfort, intelligent driving, smart cabin functions, charging convenience, and after-sales service, with the aim of identifying distinct user segments from online reviews. Based on a sample of 500 user reviews, the study applies a text-mining pipeline that combines rule-based term standardisation, LLM-based summarisation and classification, semantic encoding with Sentence-BERT, and hierarchical clustering. This workflow converts large-scale, unstructured comments into structured experience features. It also enables the comparison of users according to the similarity of their expressed concerns and evaluations. The analysis identifies five user clusters with clearly differentiated priorities: smart-cabin enthusiasts, comfort-driven users, pragmatic technology users, range-anxious drivers, a space-oriented majority. Research indicates significant diversity among NEV consumers regarding their priorities – in more details, that is intelligent capabilities, seat comfort, driving range, charging accessibility, and powertrain dependability. These results provide data-driven support for targeted product development, user-segment-specific marketing, and strategic expectation management, while also demonstrating the value of text mining for extracting actionable insights from NEV user reviews.
Keywords: LLM, User-Experience, Text-Mining, Semantic-Vector
DOI: 10.54941/ahfe1008374
Cite this paper
More from this volume
- AI-Enhanced Live-Streamed English Language Learning: Designing and Evaluating an Intelligent Platform for Chinese Learners
- "They Will Move": Confirmation Bias, Expectation Frames, and Premature Monitoring Drop Off in COLREG Encounters
- Automation transparency communication does not improve supervisory control performance, but shapes operator trust
- The influence of neuroticism on startle and surprise response: a flight simulator study
- EEG-Based Classification of Reward, Penalty, and Movement Events Across Four Video Games of Varying Complexity
- The Effects of Task Similarity and Time Pressure on Task Performance Following Interruptions in Complex Human-Computer Interaction Systems
- Trusting the Chain, Not the Black Box: A Provenance-Based Architecture for Human-Machine Teaming in Military Autonomy
- Design of a Simplified Humanoid Robot Face: Cultural Differences and Emotional Synchronization
- From Visual Observation to Auditory Interaction: A Human-Centered Tangible Music System Based on Physical Objects
- The Impact of Scarcity-Based Dark Patterns on User Performance, Perceived Darkness, and Workload in Subscription Services
- A Behavioral Observation Tool for Diagnosing Human–AI Interaction Profiles in Engineering Design Education
- The Mediated Moon: Semantic Mediation Between Gesture and Generative Image


AHFE Open Access