A5093941708- Authorship Attribution and Profiling
- AI in Service Interactions
- Natural Language Processing Techniques
- Library Science and Information Systems
- Digital Marketing and Social Media
- Topic Modeling
- Technology Adoption and User Behaviour
Amsterdam University of Applied Sciences
2024-2025
Grounded in the Stereotype Content Model, Risk Perception Theory, Technology Acceptance and Relational Embeddedness this research delves into relationship between chatbot conversation styles, customer risk, mediating role of acceptance tie strength online shopping. A 2 (warm vs. cold) * (competent incompetent) between-subjects experiment is conducted on 320 participants results obtained from two-way ANOVA PROCESS macro revealed that: (a) customer-perceived risk decreases with warmth rather...
Post-training quantization reduces the computational demand of Large Language Models (LLMs) but can weaken some their capabilities. Since LLM abilities emerge with scale, smaller LLMs are more sensitive to quantization. In this paper, we explore how affects LLMs' ability perform retrieval-augmented generation (RAG), specifically in longer contexts. We chose personalization for evaluation because it is a challenging domain using RAG as requires long-context reasoning over multiple documents....