Enhanced Sentiment Interpretation via a Lexicon-Fuzzy-Transformer Framework

2025-10-17

AI Summary

Fine-grained sentiment polarity and intensity recognition remains challenging for informal, domain-specific language in product reviews and social media text. Method: We propose a two-stage sentiment analysis framework integrating symbolic reasoning with neural modeling. Stage one applies VADER to detect explicit sentiment cues; stage two encodes contextual semantics using DistilBERT and employs a customized fuzzy inference system to dynamically calibrate model confidence, yielding continuous sentiment scores in [0,1]. Contributions/Results: (1) A synergistic mechanism combining lexicon-based rules, fuzzy logic, and a lightweight Transformer; (2) A two-stage adjustment strategy mitigating neutral-class bias; (3) Enhanced interpretability and discriminative accuracy. Experiments across four cross-domain datasets demonstrate significantly improved alignment with human ratings, superior identification of sentiment-extreme instances, a 12.6% reduction in misclassification rate, and efficient inference.

Technology Category

• Natural Language Processing: Sentiment Analysis, Stylistic Analysis, and Argument Mining
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Knowledge Representation and Reasoning: Common-Sense Reasoning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Sentiment analysis and opinion mining

Abstract

Accurately detecting sentiment polarity and intensity in product reviews and social media posts remains challenging due to informal and domain-specific language. To address this, we propose a novel hybrid lexicon-fuzzy-transformer framework that combines rule-based heuristics, contextual deep learning, and fuzzy logic to generate continuous sentiment scores reflecting both polarity and strength. The pipeline begins with VADER-based initial sentiment estimations, which are refined through a two-stage adjustment process. This involves leveraging confidence scores from DistilBERT, a lightweight transformer and applying fuzzy logic principles to mitigate excessive neutrality bias and enhance granularity. A custom fuzzy inference system then maps the refined scores onto a 0 to 1 continuum, producing expert)like judgments. The framework is rigorously evaluated on four domain-specific datasets. food delivery, e-commerce, tourism, and fashion. Results show improved alignment with user ratings, better identification of sentiment extremes, and reduced misclassifications. Both quantitative metrics (distributional alignment, confusion matrices) and qualitative insights (case studies, runtime analysis) affirm the models robustness and efficiency. This work demonstrates the value of integrating symbolic reasoning with neural models for interpretable, finegrained sentiment analysis in linguistically dynamic domains.

Problem

• Accurately detecting sentiment polarity and intensity in informal language
• Overcoming domain-specific language challenges in sentiment analysis
• Reducing misclassifications and excessive neutrality bias in sentiment scoring

Innovation

• Hybrid lexicon-fuzzy-transformer framework for sentiment analysis
• Combines VADER, DistilBERT, and fuzzy logic adjustments
• Custom fuzzy inference system maps scores to continuum