This study introduces an Improved VADER (IVADER) lexicon-based classification model to evaluate customer sentiment in multiple domains. The model addresses the challenge of domain heterogeneity in sentiment analysis by constructing a domain-specific dictionary based on the VADER lexicon. The methodology involves data preprocessing, Vectorizer transformation, Wordnet Lemmatizer-based feature selection, and an enhanced VADER Lexicon classifier. The IVADER model achieved high accuracy (98.64%), precision (97%), recall (94%), F1-measure (92%), and reduced training time (44 seconds) compared to existing studies. The model's effectiveness is validated using multi-domain datasets and a different dataset, demonstrating its stability and applicability in various domains. The study highlights the importance of domain-specific sentiment dictionaries for accurate sentiment classification and provides a valuable tool for product designers and businesses to evaluate customer sentiment in the digital marketplace.This study introduces an Improved VADER (IVADER) lexicon-based classification model to evaluate customer sentiment in multiple domains. The model addresses the challenge of domain heterogeneity in sentiment analysis by constructing a domain-specific dictionary based on the VADER lexicon. The methodology involves data preprocessing, Vectorizer transformation, Wordnet Lemmatizer-based feature selection, and an enhanced VADER Lexicon classifier. The IVADER model achieved high accuracy (98.64%), precision (97%), recall (94%), F1-measure (92%), and reduced training time (44 seconds) compared to existing studies. The model's effectiveness is validated using multi-domain datasets and a different dataset, demonstrating its stability and applicability in various domains. The study highlights the importance of domain-specific sentiment dictionaries for accurate sentiment classification and provides a valuable tool for product designers and businesses to evaluate customer sentiment in the digital marketplace.