Consistency Analysis of Sentiment Predictions using Syntactic & Semantic Context Assessment Summarization (SSAS)

2026-04-16

AI Summary

This study addresses the instability of large language models in sentiment prediction, which stems from inherent stochasticity and data noise, thereby failing to meet enterprise-level demands for consistency. To mitigate this, the authors propose the SSAS framework—Syntactic & Semantic Context Assessment Summarization—which constructs syntactic and semantic contextual cues and integrates a hierarchical classification structure based on topic-story-clustering with an iterative “summary-of-summaries” architecture. This approach delivers high-signal, sentiment-dense input prompts that effectively constrain model attention and suppress irrelevant information. Experimental results across three industry-standard datasets demonstrate that SSAS improves data quality by up to 30%, significantly enhancing the stability and reliability of sentiment predictions and offering a novel paradigm for high-consistency decision-oriented analytics.

Technology Category

Natural Language Processing: SummarizationMachine Learning: Large Multimodal Models (LMMs)Reasoning under Uncertainty: Stochastic Optimization

Application Category

Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMsSearch and Retrieval-Augmented AI: Large language models for searchWeb Mining and Content Analysis: Large pretrained models with web data

Abstract

The fundamental challenge of using Large Language Models (LLMs) for reliable, enterprise-grade analytics, such as sentiment prediction, is the conflict between the LLMs' inherent stochasticity (generative, non-deterministic nature) and the analytical requirement for consistency. The LLM inconsistency, coupled with the noisy nature of chaotic modern datasets, renders sentiment predictions too volatile for strategic business decisions. To resolve this, we present a Syntactic & Semantic Context Assessment Summarization (SSAS) framework for establishing context. Context established by SSAS functions as a sophisticated data pre-processing framework that enforces a bounded attention mechanism on LLMs. It achieves this by applying a hierarchical classification structure (Themes, Stories, Clusters) and an iterative Summary-of-Summaries (SoS) based context computation architecture. This endows the raw text with high-signal, sentiment-dense prompts, that effectively mitigate both irrelevant data and analytical variance. We empirically evaluated the efficacy of SSAS, using Gemini 2.0 Flash Lite, against a direct-LLM approach across three industry-standard datasets - Amazon Product Reviews, Google Business Reviews, Goodreads Book Reviews - and multiple robustness scenarios. Our results show that our SSAS framework is capable of significantly improving data quality, up to 30%, through a combination of noise removal and improvement in the estimation of sentiment prediction. Ultimately, consistency in our context-estimation capabilities provides a stable and reliable evidence base for decision-making.

Problem

• Large Language Models
• sentiment prediction
• consistency
• stochasticity
• noisy data

Innovation

• SSAS
• consistency
• sentiment prediction
• context summarization
• large language models