Reference Points in LLM Sentiment Analysis: The Role of Structured Context

In particular, due to their high applicability in textual data, many studies have implemented sentiment analysis using LLMs [2]. LLMs indeed demonstrate remarkable capabilities in understanding textual context; however, the actual'context' is referred to as a relationship between the tokens, which is captured through Transformer [3] and attention mechanisms [4] and most existing approaches limit their analysis to the linguistic context within review texts alone. Regarding real-world marketing applications, the actual context of consumer evaluation contains the factors which extend far beyond the written review, such as past purchasing patterns, prior experiences with the business, comparative evaluations against competitors, and opinions from social media. This gap is particularly relevant in customer relationship management (CRM) [5, 6], where understanding customer sentiment accurately drives business decisions. Marketing research has long established through prospect theory [7] and expectation-disconfirmation theory (EDT) [8] that consumers evaluate experiences relative to these broader reference points. This insight remains largely unexplored in LLM-based sentiment analysis. Furthermore, in practical deployment scenarios, particularly for real-time recommendation systems, two critical challenges emerge. First, computational efficiency is paramount--many businesses cannot deploy large models (70B+ parameters) due to latency and infrastructure constraints. Second, despite having rich contextual data (user histories, business metrics), current methods fail to effectively incorporate this information into LLM-based sentiment analysis.