Enhanced Sentiment Analysis of Iranian Restaurant Reviews Utilizing Sentiment Intensity Analyzer&Fuzzy Logic

2025-03-15

AI Summary

This work addresses the severe neutrality bias and inadequate sentiment intensity modeling inherent in conventional lexicon-based approaches (e.g., VADER) for sentiment analysis of Persian restaurant reviews. To overcome these limitations, we propose a hybrid framework integrating linguistic rules with fuzzy logic. Specifically, we introduce nonlinear transformations—square root and quartic root functions—to recalibrate VADER’s raw polarity scores, enhancing sensitivity to subtle sentiment gradients. Furthermore, we design a domain-specific fuzzy inference system tailored to restaurant reviews, incorporating cuisine-oriented membership functions, a curated rule base, and center-of-gravity defuzzification. Evaluated on a real-world dataset of 1,266 star-annotated Persian reviews, our method significantly reduces neutral-class misclassification rates and markedly improves alignment between predicted sentiment intensities and both human annotations and user star ratings. The approach effectively mitigates the discretization artifacts and neutrality bias prevalent in traditional polarity classification models.

Technology Category

• Natural Language Processing: Lexical Semantics and Morphology
• Knowledge Representation and Reasoning: Preferences
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Web Mining and Content Analysis: Sentiment analysis and opinion mining
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

This research presents an advanced sentiment analysis framework studied on Iranian restaurant reviews, combining fuzzy logic with conventional sentiment analysis techniques to assess both sentiment polarity and intensity. A dataset of 1266 reviews, alongside corresponding star ratings, was compiled and preprocessed for analysis. Initial sentiment analysis was conducted using the Sentiment Intensity Analyzer (VADER), a rule-based tool that assigns sentiment scores across positive, negative, and neutral categories. However, a noticeable bias toward neutrality often led to an inaccurate representation of sentiment intensity. To mitigate this issue, based on a fuzzy perspective, two refinement techniques were introduced, applying square-root and fourth-root transformations to amplify positive and negative sentiment scores while maintaining neutrality. This led to three distinct methodologies: Approach 1, utilizing unaltered VADER scores; Approach 2, modifying sentiment values using the square root; and Approach 3, applying the fourth root for further refinement. A Fuzzy Inference System incorporating comprehensive fuzzy rules was then developed to process these refined scores and generate a single, continuous sentiment value for each review based on each approach. Comparative analysis, including human supervision and alignment with customer star ratings, revealed that the refined approaches significantly improved sentiment analysis by reducing neutrality bias and better capturing sentiment intensity. Despite these advancements, minor over-amplification and persistent neutrality in domain-specific cases were identified, leading us to propose several future studies to tackle these occasional barriers. The study's methodology and outcomes offer valuable insights for businesses seeking a more precise understanding of consumer sentiment, enhancing sentiment analysis across various industries.

Problem

• Improves sentiment analysis accuracy for Iranian restaurant reviews.
• Reduces neutrality bias using fuzzy logic and sentiment transformations.
• Enhances sentiment intensity assessment through refined methodologies.

Innovation

• Combines fuzzy logic with sentiment analysis techniques
• Applies square-root and fourth-root transformations to scores
• Develops Fuzzy Inference System for refined sentiment values